List all Tracks

Technologies 4.0 for biomedical applications in everyday life scenarios

• Domenico Formica

    SEE PRESENTATION

Technologies 4.0 for biomedical applications in everyday life scenarios

×

ABSTRACT

The era of the fourth industrial revolution brings together robotics, digital mobile devices and services, wearable sensors and IoT systems, building a highly interconnected ecosystem often intimately coupled with human beings and their body. In this scenario, humans can be no longer considered as purely biological systems, but rather being part of an artificial-biological mixed complex. These integrated systems are nowadays essential to foster cutting edge research in a wide variety of fields, from basic science research, to medical and industrial applications, to consumers technologies. Based on these considerations, this talk will present how wearable and IoT technologies are used to investigate basic mechanisms of motor neuroscience, to objectively assess brain pathologies, and to provide new tools to help people in everyday life learning. Finally, exploiting the new technologies emerging from Industry 4.0, the talk will introduce a new class of robotic platforms for training children during the acquisition of new sensorimotor skills, through the use of robotics combined with wearable sensors, IoT, Augmented Reality, machine learning and man-machine interfaces, opening the field of Education 4.0.

PRESENTER

Domenico Formica
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

In search of breakthroughs in Industry 4.0 Manufacturing Systems

• George Q. Huang

    SEE PRESENTATION

In search of breakthroughs in Industry 4.0 Manufacturing Systems

×

ABSTRACT

Industry 4.0 has been considered as the fourth industrial revolution. If it is a revolution, it mandates novel breakthroughs. This talk takes another dimension in addition to Automation Artificial Intelligence and Robotics (AIR dimension), which are considered as powerful weapons for this revolution. This dimension focuses on three novel breakthroughs to enable this revolution to come true. The first breakthrough is “Finite element cyber-physical digitization.” A factory is decomposed into finite elements (physical twins) of man, machine and material for most cost-effective creation of corresponding digital twins through industrial wearables. Physical and digital twins, called cyber-physical holons, and their interactions and interoperability are captured through cyber-physical visibility and traceability. This breakthrough significantly innovates a method for systematically digitizing Industry 4.0 factories.

PRESENTER

George Q. Huang
The University of Hong Kong

See Presentation Close

From Condition Monitoring to Predictive Maintenance: the role of Edge Processing

• Nunzio Abbate

    SEE PRESENTATION

From Condition Monitoring to Predictive Maintenance: the role of Edge Processing

×

ABSTRACT

Condition-based Monitoring (CbM) and Predictive Maintenance (PM) are two maintenance strategies which aim at optimizing equipment efficiency and reducing service timing and costs during equipment lifecycle. Condition Monitoring (CM) , in example in the industrial motors, is the monitoring of several parameters such as equipment vibration and temperature to identify potential issues such as misalignments or bearing failures. Predictive maintenance (PdM) is a key component of smart industry that involves monitoring equipment during operation to detect early the warning signs of potential failures. PdM is largely based on condition based monitoring (CbM) through the analysis of vibration, which is the most common method to detect imbalance, misalignment and other anomalies in machinery.

PRESENTER

Nunzio Abbate
STMicroelectronics, Italy

See Presentation Close

Closing and Award Ceremony

• Emiliano Schena

    SEE PRESENTATION

Closing and Award Ceremony

×

ABSTRACT

Closing and Award Ceremony

PRESENTER

Emiliano Schena
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

Speed detection of battery-free nodes based on RF Wireless Power Transfer

• Roberto La Rosa

    SEE PRESENTATION

Speed detection of battery-free nodes based on RF Wireless Power Transfer

×

ABSTRACT

In the Internet of Things (IoT) era, Wireless Sensor Networks (WSNs) are rapidly increasing in terms of relevance and pervasiveness thanks to their notable real-time monitoring performance across several fields, including industrial, domestic, military, biomedical, commercial, environmental, and other sectors. A highly attractive implementation of WSNs is asset tracking with accurate data regarding the location and transportation conditions of goods, equipment, and the like. One highly promising application of WSNs along these lines is the remote speed monitoring of goods, ideally with battery-free sensor nodes that do not require any maintenance. This, however, represents a major challenge in power supply management. The goal of this paper is to investigate Radio Frequency (RF) Wireless Power Transfer (WPT) architecture to power a battery-free measurement system with time-domain readouts, for the speed detection of a moving sensor tag within a Wireless Sensor Network infrastructure. The performance characteristics and key features of a System-on-Chip (SoC) specifically designed to power a node through RF WPT will be discussed. The aim is to provide a strategy and a model to estimate the speed of a specific battery-free sensor that is powered by a transmitting hot-spot. Specific tests and experimental results are provided.

PRESENTER

Roberto La Rosa
STMicroelectronics, Italy

See Presentation Close

Novel Piezoelectric Sensor by Aerosol Jet Printing in Industry 4.0

• Tiziano Fapanni

    SEE PRESENTATION

Novel Piezoelectric Sensor by Aerosol Jet Printing in Industry 4.0

×

ABSTRACT

In the latest years, Industry 4.0 paradigm is leading to a reduction of industrial process tolerances, an increase in machine lifetime and an improvement of the quality of the products. The fundamental concept of this fourth industrial revolution is the data coming from the whole production process. Information is usually extracted by algorithms that work on a large amount of data that are collected on the field by a huge set of sensors. New, customized and cheap sensors that are integrated into objects and processes are required. In this work, we propose a method that allows producing a novel class of piezoelectric force sensors through an additive and novel printing method: Aerosol Jet Printing. This technology allows fabricating electronic components and sensors on a wide set of substrates also directly on the surface of the objects. Therefore, smart objects for Industry 4.0 can be designed and manufactured. With the proposed approach it was possible to fabricate both axial and shear force sensors with a d33 up to 101 nCN-1 with a capacitance of 10.4 pF. The fabricated sensors are approximately 300m thick and can be shaped to fit different custom application requirements.

PRESENTER

Tiziano Fapanni
University of Brescia, Italy

See Presentation Close

3DOPE-DL: Accuracy Evaluation of a Deep Learning Framework for 3D Object Pose Estimation

• Davide Maria Fabris

    SEE PRESENTATION

3DOPE-DL: Accuracy Evaluation of a Deep Learning Framework for 3D Object Pose Estimation

×

ABSTRACT

This work investigates the uncertainty in 3D pose estimation of DenseFusion, a Deep Learning-based 3D Object Pose Estimation (3DOPE) framework. The accuracy and precision of object spatial localization is evaluated on the benchmark Yale Carnegie Berkeley-Video Dataset. The Average Euclidean Distance metric is employed as a figure of merit for the quantitative data analysis. Moreover, the Average Rotational and Translational Distances among the estimated and the ground-truth poses are analyzed. Results gathered on the YCB-Video Dataset are validated on a newly collected 3DOPE dataset, the ISS Dataset. The latter is populated by harnessing a 3D scanner, an RGB-D camera, and an anthropomorphic robot. Outcomes highlight an Average Euclidean Distance value of 1.8 mm on the best-processed item in the YCB-Video Dataset. Similarly, an Average Euclidean Distance value of 1.9 mm is achieved on the ISS Dataset. Eventually, the measurement uncertainty of the six components of the 3D poses is inspected. The latter assessment is performed on the ISS Dataset by relying on the ISO GUM [1].

PRESENTER

Davide Maria Fabris
Politecnico di Milano, Italy

See Presentation Close

A Plain Low Threshold IoT Platform for Enabling New IoT Products from SMEs

• Stefan Forsström

    SEE PRESENTATION

A Plain Low Threshold IoT Platform for Enabling New IoT Products from SMEs

×

ABSTRACT

Many small and medium enterprises have existing products that they want to innovate on and move into the new era of Internet of Things. Because of this, we have developed a plain Internet of Things platform aimed towards businesses who wants to try out these new systems but does not have the resources to develop or maintain a full platform from the traditional providers. We have developed an open source solution that can be run on cheap off the shelf hardware and employs today’s de facto standards for Internet of Things systems. Our solution also provides adequate functionality for an initial effort and innovation, including taking security and privacy concerns into consideration. We have also evaluated our implementation in terms of scale, which shows that the system scales well in scenarios with up to 50 sensor values per second. Which should be enough for a small business first effort to try out their products as an Internet of Things service.

PRESENTER

Stefan Forsström
Mid Sweden University, Sweden

See Presentation Close

Complex Event Processing on the Edge - Bringing Data Consolidation and Processing closer to Wireless Sensor Networks

• David Merkl

    SEE PRESENTATION

Complex Event Processing on the Edge - Bringing Data Consolidation and Processing closer to Wireless Sensor Networks

×

ABSTRACT

In general wireless sensor networks lack the proper hardware resources to analyze and visualize the gathered data by its sensors. Such sensor networks are commonly used to acquire data and forward it to a more powerful device, where the data can be handled properly. These devices could be for instance servers, which monitor, visualize and perform statistical analysis. Based on that current situation, we are proposing an edge computing approach as an addition to sensor networks. With the usage of edge nodes some of the compute-intensive tasks can be brought closer to the sensor network, resulting in a pre-processing of data. Moreover this will be done by using the complex event processing engine Siddhi on an edge node. Our proposal will be applied on a wireless sensor network, which measures several physical quantities to determine the indoor air quality.

PRESENTER

David Merkl
Frankfurt University of Applied Sciences, Germany

See Presentation Close

Low cost, low pass Prism filtering

• Manus Henry

    SEE PRESENTATION

Low cost, low pass Prism filtering

×

ABSTRACT

Prism signal processing is a new FIR signal processing technique offering a fully recursive calculation and minimal design cost, which is well-suited to the requirements of IoT sensing. This paper describes a family of low pass filter designs using one or more layers of Prisms, where the frequency response has minimal stopband gain. Combined with heterodyning and Prism-based tracking, these filters provide flexible and powerful real-time tracking of signal component properties for use in measurement applications.

PRESENTER

Manus Henry
University of Oxford, UK

See Presentation Close

Quality Assurance of Weld Seams Using Laser Triangulation Imaging and Deep Neural Networks

• Andreas Spruck

    SEE PRESENTATION

Quality Assurance of Weld Seams Using Laser Triangulation Imaging and Deep Neural Networks

×

ABSTRACT

In this paper, a novel optical inspection system is presented that is directly suitable for Industry 4.0 and the implementation on IoT-devices controlling the manufacturing process. The proposed system is capable of distinguishing between erroneous and faultless weld seams, without explicitly defining measurement criteria . The developed system uses a deep neural network based classifier for the class prediction. A weld seam dataset was acquired and labelled by an expert committee. Thereby, the visual impression and assessment of the experts is learnt accurately. In the scope of this paper laser triangulation images are used. Due to their special characteristics, the images must be pre-processed to enable the use of a deep neural network. Furthermore, two different approaches are investigated to enable an inspection of differently sized weld seams. Both approaches yield very high classification accuracies of up to 96.88%, which is competitive to current state of the art optical inspection systems. Moreover, the proposed system enables a higher flexibility and an increased robustness towards systematic errors and environmental conditions due to its ability to generalize. A further benefit of the proposed system is the fast decision process enabling the usage directly within the manufacturing line. Furthermore, standard hardware is used throughout the whole presented work, keeping the roll-out costs for the proposed system as low as possible.

PRESENTER

Andreas Spruck
Friedrich Alexander University Erlangen Nürnberg, Germany

See Presentation Close

Test bench for the measurement of scissors' cutting torque

• Stefano Marelli

    SEE PRESENTATION

Test bench for the measurement of scissors' cutting torque

×

ABSTRACT

This work describes a test bench developed to measure the cutting torque of scissors as a function of the blades position. The prototype of the machine has been validated by evaluating repeatability and reproducibility of torque measurement while cutting fabric. The dependence of the measured torque from parameters such as the scissors’ wear, cutting velocity, fabric pre-tensioning and fabric mechanical properties were investigated. The scissors’ wear has been investigated by analysing results of more than 20’000 consecutive cutting cycles. The study sets the bases for the creation of the equivalent of ISO 8442-5 (2004) for scissors.

PRESENTER

Stefano Marelli
Politecnico di Milano, Italy

See Presentation Close

Deploying Wifi, RF and BLE sensors for pervasive monitoring and control

• Alberto Faro

    SEE PRESENTATION

Deploying Wifi, RF and BLE sensors for pervasive monitoring and control

×

ABSTRACT

This paper presents the structure and the main functionalities of a cyber-physical-system, denoted as CPSc, to monitor and control common applications in the field of domotics and healthcare. From the features to be owned by such CPSc, the paper derives some guidelines for their implementation. In particular, the paper suggests: i) the use of the secured version of the Message Queuing Telemetry Transport (MQTT) protocol to collect data taken by the sensors and to send commands to the actuators, ii) how to use the main types of devices, i.e., Wifi, RF and Bluetooth Low Energy (BLE), for pervasive monitoring and control, and iii) how to use an automation system integrated with MQTT to react timely to undesired events. The use of smartphones for data visualization and not for bridging control services and sensors/actuators is widely discussed. Also, the paper illustrates how CPSc may be implemented and some code examples are provided to contribute to the implementation. Alternative solutions to be compared in further studies are outlined. The proposed architecture is under testing in the I-HOSP project, an initiative supported by EC Regional Funds aiming to deploy a healthcare system to assist remotely patients affected by risky pathologies.

PRESENTER

Alberto Faro
Deepsensing srl, Italy

See Presentation Close

ISO/IEC 15189 Implementation in Microbiology Laboratory – General Concepts

• Amina Aleta

    SEE PRESENTATION

ISO/IEC 15189 Implementation in Microbiology Laboratory – General Concepts

×

ABSTRACT

Microbiology laboratory is a type of medical laboratory and should be safe and efficient environment. Even it is not a mandatory for the accreditation in most of the countries, ISO/IEC 15189 remains the most common reference for quality of work in medical laboratories. It is mostly based on good laboratory practices and is oriented to support accurate clinical decisions. ISO/IEC 15189 has potential to become very effective instrument for development and improvement of medical laboratories. Results from laboratory should guide the majority of clinical decisions and help in providing adequate patient care. This article provides a simple approach to meet the minimum requirements set. To achieve intended goal and strictly follow the requirements proposed in the standard, the trained and well-motivated laboratory staff is necessary to implement the system. The objective of this article is for it to be used as a guideline for evaluation and implementation of the ISO 15189.

PRESENTER

Amina Aleta
International Burch University, Bosnia and Herzegovina

See Presentation Close

Informational Space and Messages Interaction Models for Smart Factory Concept

• Maria Usova

    SEE PRESENTATION

Informational Space and Messages Interaction Models for Smart Factory Concept

×

ABSTRACT

Nowadays Smart Factory concept becomes a reality. We meet the greatest challenge of implementing autonomous manufacturing processes such as an organization of robots interaction in the framework of cyber-physical systems. This issue seems to be one of the most important, as it is considered as the basis of fully automated systems and provides mechanisms for self-organization and decentralized control. In this paper, we describe Informational Space and messages interaction models as the way for robots communication, considered under the Smart Factory environment. The main contributions of the work are the developed models and a software simulator of an adaptive production model, that responds to changing customer personalized needs. The performed case study showed that the developed software simulator, based on the presented theoretical models, can successfully imitate the autonomous production process.

PRESENTER

Maria Usova
ITMO University, Russia

See Presentation Close

SPIRIT - A Software Framework for the Efficient Setup of Industrial Inspection Robots

• Daniele Evangelista

    SEE PRESENTATION

SPIRIT - A Software Framework for the Efficient Setup of Industrial Inspection Robots

×

ABSTRACT

SPIRIT aims to develop an "inspection skill" for robots that takes the step from programming of complex inspection tasks to configuring such tasks. Result of the project is a software framework that includes an "offline framework" with features such as model-based automatic coverage planning for complex parts, automatic robot program generation and an "inline framework" that deals with sensor data mapping to transfer sensor measurements to the 3D object model. At the heart of the project is an accurate process-specific model that represents the sensor data acquisition process. This representation is sufficiently accurate to allow automatic planning in off-line settings using simulated workcells and then reproducing the inspection procedure on the real one, with some adaptations and corrections. More in detail, the "offline framework" will include a generic interface to allow the easy exchange of process models (for different inspection technologies), of the CAD model of the part (for a different type of product to be inspected) or of the work-cell model (for a different robot kinematic structure). The generic "inline framework" will provide the backbone for the execution of the actual inspection process. Relying on such a proven frameworks will reduce the risks of implementing complex inspection tasks and thus help the deployment of inspection robots. In this work initial results from the two main use cases are presented, they consist of inspection tasks for the automotive and aerospace industry respectively.

PRESENTER

Daniele Evangelista
Università degli Studi di Padova, Italy

See Presentation Close

Evaluation of the bounding box uncertainty of deeplearning object detection in HALCON software

• Daniele Marchisotti

    SEE PRESENTATION

Evaluation of the bounding box uncertainty of deeplearning object detection in HALCON software

×

ABSTRACT

Deep neural networks have become more and more relevant for vision systems, for object detection and classification in industrial fields, such as robot navigation, monitoring and tracking. For such applications, vision systems have to be robust to environment conditions, occlusions and very accurate, as for bin picking. In this paper, we evaluate the performances of deep learning object detection neural networks in HALCON software, by investigating the uncertainty of bounding box position for object detection and the impact of disturbances. In this study, results evidenced the increase of bounding box uncertainty and the reduction of confidence of neural networks when disturbances are introduced, as well as the increment of uncertainty, when confidence lowers. When errors are introduced in labeling, the uncertainty of the bounding box position becomes higher, but lower than the error introduced.

PRESENTER

Daniele Marchisotti
Politecnico di Milano, Italy

See Presentation Close

Analysis of reproducibility and repeatability of a hand-held laser scanner for gap&flush measurement in car-assembly line

• Alessia Baleani

    SEE PRESENTATION

Analysis of reproducibility and repeatability of a hand-held laser scanner for gap&flush measurement in car-assembly line

×

ABSTRACT

Industry 4.0 has pushed online quality control to be distributed along the production line, therefore, data are acquiring a progressively more important role. The quality of the collected data necessarily depends on the uncertainty of measurement and for this reason, today the main focus is to reduce this uncertainty to the minimum level. In this study the measurement uncertainty of a hand-held non-contact laser scanner (G3F) and the uncertainty associated to the measurement process, i.e. the uncertainty associated to the whole measurement process when the device is operated in the production line by human operators, were evaluated. Data were collected from a Toyota Auris and each measuring point was inspected at least 20 times by three different operators on different parts. This data set has been, at first, processed by a type A uncertainty analysis. Then, a Gage R&R analysis helped investigate reproducibility, repeatability and the system variability.

PRESENTER

Alessia Baleani
Università Politecnica delle Marche, Italy

See Presentation Close

IoT Indoor Localization with AI Technique

• Matteo D'Aloia

    SEE PRESENTATION

IoT Indoor Localization with AI Technique

×

ABSTRACT

In this paper, an innovative method for indoor localization based on Bluetooth Low Energy (BLE4) technology has been developed. By employing a mobile beacon, a wearable device and stationary anchors, the conceived tracking system is able to predict people position within buildings. Adopting the received signal strength indicator and a machine learning approach, good accuracy is reached without limiting the freedom and privacy of users.

PRESENTER

Matteo D'Aloia
MASVIS SRL, Italy

See Presentation Close

Robot Localisation using UHF-RFID Tags for Industrial IoT Applications

• Farhad Shamsfakhr

    SEE PRESENTATION

Robot Localisation using UHF-RFID Tags for Industrial IoT Applications

×

ABSTRACT

Autonomous systems are becoming more and more affordable and effective in dynamic industrial environments. Effective localisation algorithm are usually considered as enablers to increase the efficiency and the flexibility of industrial warehouses and production plants using automation. The paper presents a solution to both localise a mobile agent and reconstruct its entire trajectory through sensor fusion and using UHF-RFID passive tags. Solutions on dummy trajectories are reported to show the effectiveness of the proposed method.

PRESENTER

Farhad Shamsfakhr
University of Trento, Italy

See Presentation Close

A wearable system for respiratory and pace monitoring in running activities: a feasibility study

• Joshua Di Tocco

    SEE PRESENTATION

A wearable system for respiratory and pace monitoring in running activities: a feasibility study

×

ABSTRACT

Wearable devices are extensively used for monitoring physiological parameters both in clinical settings and in sports science. Among others, respiratory rate is mostly neglected but is a valid index to assess athletes' performance. The purpose of this work was to test a wearable device composed of two elastic bands embedding conductive textiles during a running session of approximately 9.5 km. The test has been carried out by a young healthy volunteer who worn two bands on the rib cage (one on the upper thorax and one on the umbilicus). The frequency-domain analysis allowed estimating both respiratory parameters (i.e., the average respiratory rate, and running related parameters (i.e., estimated running distance and average running pace). The wearable system was able to perform a good estimation of both respiratory and gait parameters allowing a better understanding of the relationship between the fatigue and the respiratory activity, enabling a more accurate running performance evaluation.

PRESENTER

Joshua Di Tocco
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

Respiratory monitoring during cycling exercise: performance assessment of a smart t-shirt embedding fiber optic sensors

• Carlo Massaroni

    SEE PRESENTATION

Respiratory monitoring during cycling exercise: performance assessment of a smart t-shirt embedding fiber optic sensors

×

ABSTRACT

In the present study, we assessed the performances of a smart t-shirt embedding twelve fiber-optic sensors located in different areas of the trunk during a cycling incremental exercise test. Four volunteers were asked to wear simultaneously our tshirt and a reference instrument based on airflow measurement with the purpose of validating the measure of respiratory frequency (fR). The study aimed to identify the areas of the trunk which are most suitable for measuring fR, with important implications for the design of sports respiratory wearables specifically developed for monitoring fR during cycling exercise.

PRESENTER

Carlo Massaroni
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

Optoelectronic plethysmography derived breathing parameters can differ between athletes with and without a dysfunctional breathing pattern during exercise

• Carol Smyth

    SEE PRESENTATION

Optoelectronic plethysmography derived breathing parameters can differ between athletes with and without a dysfunctional breathing pattern during exercise

×

ABSTRACT

Dysfunctional breathing pattern (DBP) is a term that can be used to describe a collection of breathing disorders in which an individual displays chronic changes in breathing pattern. This can occur with or without another respiratory disorder/disease. Currently, there is no diagnostic method for DBP and it is diagnosed through the exclusion of other pathologies. Optoelectronic plethysmography (OEP) is a 3D motion capture technique which allows for a noninvasive method of measuring the movement of the chest wall, compartmentalizing the torso. The purpose of this study was to investigate if OEP could differ between athletes with and without a dysfunctional breathing pattern during exercise. Forty-seven athletes with a healthy breathing pattern (HBP) and twenty-six athletes with a suspected dysfunctional breathing pattern (DBP) performed an incremental cycle test to volitional exhaustion. Inspiratory time (tI), expiratory time (tE), the phase angle between the left and right side of the pulmonary ribcage (RCpHTA), between the pulmonary and abdominal ribcage (RCpRCaPhase), between the shoulders and the abdominal ribcage (RCaSPhase), and between the shoulders and the pulmonary ribcage (RCpSPhase) were calculated at rest and during high intensity exercise. It was found that each breathing parameters displayed no significant differences between the two groups at rest. However, during high intensity exercise these breathing patterns were found to be significantly different. The DBP group displayed significantly lower values for tI (HBP: 0.9 s , DBP: 0.8 s) and tE (HBP: 1.0 s, DBP: 0.8 s) and significantly higher values for each of the phase angles when compared to the healthy group, including RCpHTA (HBP: 0.0º, DBP: 0.2 º), RCpRCaPhase (HBP: -0.4 º, DBP: 0.5 º), RCaSPhase (HBP: -0.3 º, DBP: 0.5 º), and RCpSPhase (HBP: 0.2 º, DBP: 0.6 º). This indicates that individuals with a DBP took shorter breaths and had greater asynchrony within their breathing pattern during exercise but not at rest. This also demonstrates that OEP is sensitive enough to detect differences between these two group during high intensity exercise.

PRESENTER

Carol Smyth
University of Kent, UK

See Presentation Close

Augmented Reality App to improve quality of life of people with cognitive and sensory disabilities

• Mirko Rossi

    SEE PRESENTATION

Augmented Reality App to improve quality of life of people with cognitive and sensory disabilities

×

ABSTRACT

In the last decades, number of people affected by cognitive decline is rising significantly. The main cause of this problem is believed to be the overall drift of the average population age. In general, cognitive impairment varies from mild to severe with mild represented as people may begin to notice a slight change in their cognitive functions while still be able to conduct their daily activities without major limitations; on the other hand, severe state of cognitive impairment leads to a progressive loss of comprehensive abilities as well as evaluating situations. These impairments may be represented by losing the ability to talk and write that leads to the inability to conduct an independent lifestyle. The decay of intellectual functions is associated with a progressive increase of sensory impairment (vision and hearing). In this paper we present a tool to help and support people who suffer from both mild agerelated cognitive decline and sensory impairment. We developed an augmented reality home-made App designed for smart glasses. This App would be a useful tool to provide more independence to patients during actual daily living activities and it will be able to notify users about a potentially dangerous situations, by providing cues in real time. In this way, elderly people, will be able continue their life at home for a longer time before having the need to move into an assisting living facility.

PRESENTER

Mirko Rossi
Sapienza University of Rome, Italy

See Presentation Close

Wearable stretchable sensor based on conductive textile fabric for shoulder motion monitoring

• Arianna Carnevale

    SEE PRESENTATION

Wearable stretchable sensor based on conductive textile fabric for shoulder motion monitoring

×

ABSTRACT

Wearable stretchable sensors are gaining significant interest in application related to joint motion monitoring. Stretchable strain sensors are a promising technological solution to develop wearable systems for several applications (e.g., sports, rehabilitation, health science) thanks to their flexibility, lightweight, compliance, and ease to wear. The aim of this study is twofold: i) to perform the metrological characterization of a stretchable sensing element based on a conductive textile fabric for developing a wearable sensor intended for joint motion monitoring and ii) to provide a preliminary assessment of the developed sensor in shoulder motion monitoring. The static characterization and the hysteresis analysis at different speeds (i.e., 50 mm∙min-1, 100 mm∙min-1, 200 mm∙min-1, 400 mm∙min-1 and 600 mm∙min-1) were carried out to assess the sensor’s characteristics to mechanical strain. An explorative test to assess the sensor feasibility in monitoring horizontal flexion-extension of the shoulder was performed on one healthy volunteer. Results showed that the sensor’s resistance decreased from 75 kΩ at 0% strain level to 52 kΩ at 10% strain level during static characterization. Moreover, the maximum hysteresis error eh% was always lower than 2.59% during loadingunloading hysteresis cycles at different speeds. The developed stretchable sensor seems to be a promising solution for monitoring shoulder range of motion in applications were unobtrusiveness and wearability are key factors.

PRESENTER

Arianna Carnevale
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

Performance assessment in clay pigeon shooting using machine vision for gaze detection

• Massimiliano Micheli

    SEE PRESENTATION

Performance assessment in clay pigeon shooting using machine vision for gaze detection

×

ABSTRACT

This study was a part of a wider project with the aim of describing the athletic gesture in the Olympic trap discipline. The study aimed to identify the most relevant ocular features and their contribution to athletic performance, developing solutions to monitor athlete’s pupils. The results obtained are promising considering the particular athlete configuration and the uncontrolled conditions characterizing this shooting discipline, but improvements are needed to enhance the required accuracy.

PRESENTER

Massimiliano Micheli
University of Brescia, Italy

See Presentation Close

A preliminary approach for swimming performance analysis of FISDIR elite athletes with intellectual impairment using an inertial sensor

• Teodorico Caporaso

    SEE PRESENTATION

A preliminary approach for swimming performance analysis of FISDIR elite athletes with intellectual impairment using an inertial sensor

×

ABSTRACT

People with intellectual impairment show low performances in motor control, especially in complex movements. Performance analysis methods, based on wearable inertial sensor, are often used in typical developed swimmers but have never been used in swimmers with intellectual impairment, for whom the use of quantitative systems would be even more important. This paper presents a case study conducted on freestyle swimmers from the functional evaluation project of the Italian Sport Federation for athletes with Intellectual Impairment (FISDIR). The tests were conducted by five Italian elite swimmers with intellectual impairment using a structured experimental protocol which foresees an inertial sensor located on the wrist. Key freestyle temporal and kinematic parameters were assessed. A high-speed camera was used as a benchmark to validate the inertial-based parameters. The preliminary results indicate that the proposed inertial-based approach correlates over 90% with the performance indices obtained with the camera-based approach, and therefore it could represent a useful tool for monitoring and improving the training.

PRESENTER

Teodorico Caporaso
University of Naples Federico II, Italy

See Presentation Close

Assessment of running training sessions using IMU sensors: evaluation of existing parameters and choice of new indicators

• Emanuele Portuese

    SEE PRESENTATION

Assessment of running training sessions using IMU sensors: evaluation of existing parameters and choice of new indicators

×

ABSTRACT

The fatigue is not simple to be evaluated and it is most commonly referred to a reduced capacity for maximal performance. It is a parameter that constantly affects the performance of runners and there are no wearable devices on the market enable to calculate it. The purpose of the study is to find a correlation between the parameters of the gait cycle and fatigue. An inertial sensor had been placed on the dorsum of the right foot during two 5-minute running trials in an highintensity intermittent exercise (HIIE) protocol. The parameters of the gait analysis have been calculated and studied according to the heart rate in order to define a fatigue index. A linear regression algorithm was used to establish this relationship. The mid-high R2indicates a good regression. Therefore it suggests us that it is possible to compute the FI using the only gait parameters without the use of an HR band.

PRESENTER

Emanuele Portuese
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

Effect of Running Intensity on Leg Force Asymmetry and its Relationship to Internal Load Biomarkers

• Filipe Sousa

    SEE PRESENTATION

Effect of Running Intensity on Leg Force Asymmetry and its Relationship to Internal Load Biomarkers

×

ABSTRACT

Higher leg force asymmetry had been linked to increased energy expenditure during long-distance running. Muscle fatigue would be expected to influence leg force asymmetry during the effort due to its influence on coordination, but previous studies failed to show this effect. Considering the influence of exercise intensity on fatigue, leg force asymmetry progression may be intensity-dependent. This study aims to investigate the effect of running intensity on the leg force asymmetry in the vertical and horizontal orientations and their relationship to a physiological response. Nine recreational long-distance runners were submitted to three test sessions interspaced by 48-72 hours on an instrumented nonmotorized treadmill, consisting of an incremental test and three constant intensity efforts, below RCP, at RCP and above VO2max (38.1 ± 10.9, 59.8 ± 14.7, and 126.7 ± 11.8 % of the VO2max, respectively). Results shows a significant effect of intensity on leg force asymmetry in the horizontal orientation (p = 0.04; ηp2 = 0.167), but not in the vertical orientation (p = 0.14; ηp2 = 0.067). Leg asymmetries do not tend to progress along with the effort, irrespective of force orientation or the intensities included here (p > 0.97; ηp2 < 0.011 for time). However, the association between leg force asymmetry and biomarkers of physiological stress may be intensity-dependent, with the intensity at RCP showing the stronger coefficient of determination between the studied variables (R² between 0.52 and 0.93) compared to the other intensities (R² between 0.08 to 0.16).

PRESENTER

Filipe Sousa
Federal university of Alagoas, Brazil

See Presentation Close

Validation of a novel wearable solution for measuring L5/S1 load during manual material handling tasks

• Ilaria Conforti

    SEE PRESENTATION

Validation of a novel wearable solution for measuring L5/S1 load during manual material handling tasks

×

ABSTRACT

Excessive values of force on L5/S1 joint can cause work-related musculoskeletal disorders, such as low back pain. Currently, the reference solution for estimating such variables is the combination of optoelectronic system and force platform, used for calculating the bottom up inverse dynamics in laboratory settings. Here we propose and validate a novel, completely wearable solution, composed by twelve inertial measurement units and pressure insole sensors. We validate the wearable solution with respect to the output of the reference solution, with data collected simultaneously on a subject performing lifting and releasing tasks with two different loads. The results are encouraging towards the use of the wearable methodology, considering the great impact of such a solution in a real manufacturing scenario.

PRESENTER

Ilaria Conforti
Università degli Studi di Roma "La Sapienza", Italy

See Presentation Close

A Body Hydration Analysis System to improve running performance

• Valerio Lapadula

    SEE PRESENTATION

A Body Hydration Analysis System to improve running performance

×

ABSTRACT

During an intense activity, such as marathon or bicycle training, body is subjected to a high physical stress. This brings the performance decreasing, given by several factors such as reduction of body hydration. Low hydration gives a loss of body cooling’s efficiency on which athlete’s performance capabilities depend. Body hydration monitoring devices have poor accuracy and moreover it’s very difficult to find them on the market. In this work we do not aspire to the production of a hydration sensor, but rather we want to analyse and identify possible measures related to body hydration, acquired during a running and not yet observed in literature. For these reasons,we present an acquisition system to collect data from whether, subject performance and saliva, an experimentation protocol and features relevance analysis. The preliminary results shown in this work are obtained using the Bio-electric Impedance Analysis as benchmark measure of body hydration.

PRESENTER

Valerio Lapadula
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

Comparison among different inertial-based algorithms for the automatic detection of temporal events in sprint tests: a preliminary study on elite athletes with intellectual impairment

• Teodorico Caporaso

    SEE PRESENTATION

Comparison among different inertial-based algorithms for the automatic detection of temporal events in sprint tests: a preliminary study on elite athletes with intellectual impairment

×

ABSTRACT

A fast and objective evaluation of kinematic characteristics of an elite athlete’s gesture is necessary for refining her/his performance. When the athlete has a reduced capacity and/or reliability of expression, as in the case of subjects with intellectual impairment, objective performance analyses are even more important. In this work, we present a preliminary study regarding performance analysis on sprint tests performed by elite athletes with intellectual impairment, wearing an inertial sensor at the bottom end of their vertebral column. In particular, we compare three different inertial-based algorithms for automatic detection of temporal events, in steady-state velocity phase, with respect to the benchmark values obtained through video analysis.

PRESENTER

Teodorico Caporaso
University of Naples Federico II, Italy

See Presentation Close

Bluetooth Performance Evaluation based on Notify for Real-time Body-Area Sensor Networks

• Olaf Reich

    SEE PRESENTATION

Bluetooth Performance Evaluation based on Notify for Real-time Body-Area Sensor Networks

×

ABSTRACT

This work focuses on the analysis of Bluetooth Sensor Networks and the maximum number of Bluetooth sensors nodes for real-time human activity recognition (HAR). M:1 multipairing is used as network topology. The tests use notify for the Bluetooth data transmission. We investigated the quality of service (QoS) for the maximum number of Bluetooth connections with real-time sensor data based on inertial measurement units (IMU). We show how many Bluetooth sensor nodes can be simultaneously connected using different commercial off-theshelf hardware and OS. On top of that we point out how the package loss behaves depending on the set time interval and used hardware. Our results show that a maximum number of 13 Bluetooth sensor nodes can be connected using an external Bluetooth dongle with the Linux OS. Connecting more than 10 Bluetooth sensor nodes at a frequency of 0.025 s tested in the Thinkpad P53 in combination with the DeLock Bluetooth dongle being most useful. This combination allowed a maximum number of simultaneous connections by having only a package loss of about 1.2%.

PRESENTER

Olaf Reich
Frankfurt University of Applied Sciences, Germany

See Presentation Close

Design and development of an instrumented glove for hand rehabilitation in children suffering from cerebral palsy: a digital manufacturing approach

• Giorgia Cusimano

    SEE PRESENTATION

Design and development of an instrumented glove for hand rehabilitation in children suffering from cerebral palsy: a digital manufacturing approach

×

ABSTRACT

Cerebral palsy in infancy represents one of the major causes of permanent motor deficit in the upper limb movements. An early diagnosis and timely rehabilitation therapy would facilitate the partial or total recovery of the physiological movement range. Unfortunately, currently available technological solutions for rehabilitation and assessment of upper limb are not suited for children younger than 5 years of age. The advancements in manufacturing technologies have made possible the fabrication of highly accurate custom physical models of patient anatomy and, more recently, patient specific implants. This work investigates the possibility to develop a workflow based on digital manufacturing technologies to design parametric solutions for rehabilitation and motor assessment in children younger than 5 years of age. In details, this work presents the development of an instrumented glove for the assessment of thumb therapy in children aged between 4 and 5 years suffering from the "thumb in the palm syndrome".

PRESENTER

Giorgia Cusimano
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

BEAT: Balance Evaluation Automated Testbed for the standardization of balance assessment in human wearing exoskeleton

• Juri Taborri

    SEE PRESENTATION

BEAT: Balance Evaluation Automated Testbed for the standardization of balance assessment in human wearing exoskeleton

×

ABSTRACT

The absence of standardized methodologies for the assessment of wearable exoskeleton performance still represents the main issue to overcome for their complete spread in real life. From this perspective, EUROBENCH project purposes to create the first benchmarking for robots in Europe. Within this project, BEAT (Balance Evaluation Automated Testbed) aims at realizing a testbed to benchmark the ability of exoskeleton in assisting static and dynamic balance. The testbed consists in a robotic platform and standardized software routines for the computation of performance indices. The present paper aims at presenting the main outcomes of the BEAT project considering both the mechanical aspects of the moving platform, the embedded sensors systems, as well as the proposed testing protocols. Such outcomes could be useful for all researchers involved in the development of exoskeleton in order to provide specific guidelines for testing exoskeleton performance. In addition, they could represent a fundamental starting point for the definitive use of exoskeletons in daily life and not only in laboratory environments.

PRESENTER

Juri Taborri
University of Tuscia - DEIM, Italy

See Presentation Close

An FBG-based Smart Wearable Device for Monitoring Seated Posture in Video Terminal Workers

• Martina Zaltieri

    SEE PRESENTATION

An FBG-based Smart Wearable Device for Monitoring Seated Posture in Video Terminal Workers

×

ABSTRACT

In the last decades, ever more employees spend most of their working time at video screens, frequently assuming ergonomically incorrect postures. This condition often leads to the occurrence of musculoskeletal disorders. Among others, low back pain is the most widespread and socially expensive disease since it causes a reduction of work productivity and use of public healthcare. In this context, monitoring back postures to prevent the occurrence of such a condition and to support clinicians during postural treatments can be useful. To achieve this aim, many tools based on different technologies have been developed for the monitoring of the spinal range of motions. Recently, the increased use of fiber optic sensors led to the creation of ever more light and comfortable devices. In this work, a new custom wearable system based on Fiber Bragg Gratings technology for monitoring lumbar flexion-extension (F/E) movements is presented. The sensitivity to strain (i.e., Sε) was assessed, as well as its capability of detecting lumbar F/E in the sagittal plane. Results show a high value of Sε and ascertain the wearable system ability to monitor back lumbar F/E over time.

PRESENTER

Martina Zaltieri
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

Decisional Support System with Artificial Intelligence oriented on Health Prediction using a Wearable Device and Big Data

• Alessandro Massaro

    SEE PRESENTATION

Decisional Support System with Artificial Intelligence oriented on Health Prediction using a Wearable Device and Big Data

×

ABSTRACT

The proposed work describes a decision support system (DSS) based on artificial intelligence algorithms and health wearable sensors predicting health status. The discussion is mainly focused on the description of the innovative architecture of the prototype platform related to a research industry project. The platform is able to control different wearable sensors storing data into a Cassandra Big Data system. Support Vector machine (SVM) and Long Short Term Memory (LSTM) algorithms have been applied to experimental datasets, proving the basic function of physiological data prediction. The work is suitable for the implementation of multi-dimensional risk map of health status.

PRESENTER

Alessandro Massaro
Dyrecta Lab

See Presentation Close

Development of an In-Ear Photoplethysmography Wearable System

• Andrea Pedrana

    SEE PRESENTATION

Development of an In-Ear Photoplethysmography Wearable System

×

ABSTRACT

In this paper, a wearable electronic platform for in-ear photoplethysmography is presented. The system was specifically designed with a miniaturized form factor in order to enable the potential monitoring of athletes during physical activity, as well professionals wearing earbuds or headphones during their normal duties. Measurements have been collected to address the main factors affecting the signal quality: as a result, the fine tuning of the configuration parameters allowed the extension of the battery lifetime of the system to over 3 days of continuous monitoring. Moreover, an investigation of the best body measurement location has been carried out.

PRESENTER

Andrea Pedrana
Università di Bergamo, Italy

See Presentation Close

Contactless Heart Rate Monitoring Using A Standard RGB Camera

• Soumyajyoti Maji

    SEE PRESENTATION

Contactless Heart Rate Monitoring Using A Standard RGB Camera

×

ABSTRACT

Video photo-plethysmography (VPG) methods have been used over the years to monitor the heart rate. In this work, we report the usage of two different algorithms to extract cardiac signals from the recorded videos. Video recordings on six different subjects have been carried out at two different experimental setup conditions- front view and side view. Tests are also performed at three different Region of Interest (ROI)- forehead, cheek, and the carotid region. Results suggest that the carotid region offers the best performance in terms of accuracy. The accuracy rate remained consistently high on almost all the trials that underwent side view measurements. It is also noteworthy to mention that in many cases, the green channel exhibited much more accurate results than its counterpart sRGB color space.

PRESENTER

Soumyajyoti Maji
Trinity College Dublin, Ireland

See Presentation Close

Clean-Breathing: a Novel Sensor Fusion Algorithm Based on ICA to Remove Motion Artifacts from Breathing Signal

• Luigi Raiano

    SEE PRESENTATION

Clean-Breathing: a Novel Sensor Fusion Algorithm Based on ICA to Remove Motion Artifacts from Breathing Signal

×

ABSTRACT

Although smart-textile solutions based on piezoresistive technology have emerged as a tool to assess unobtrusively breathing activity, their signals are affected by the artifacts related to the subjects’ movements during common activities (e.g. walking or running). In order to remove such artifacts, we implemented a novel algorithm combining the information recorded by four piezoresistive textile sensors, which allowed to measure rib cage movements due to the breathing activity, with the data synchronously recorded by an inertial measurement unit. Specifically, by using an Independent Component Analysis (ICA), our algorithm allowed to blindly reduce movement artifacts from the signals recorded by the piezo sensors, leading to highlight the breathing activity. We tested our algorithm in a pilot study, in which we enrolled one healthy subject during a free-running task. In order to assess our approach, we compared the signal spectrum obtained applying our algorithm with the one computed after a standard band-pass filter at 0.05-3 Hz. To this aim, we compared the average amplitude of the Power Spectral Densities (PSDs), computed after both approaches, along three frequency ranges: i) [0-1] Hz, related to the breathing activity; ii) [1-2] Hz, related with the torso rotation, during a running a task; iii) [2-3] Hz, related with the pace, during a running a task. Although the study was performed on one single subject, the results obtained seem to be promising. Indeed, within the range [0-1] Hz, the average reduction of the Power Spectral Density (PSD) is only about 4%, while it is considerably higher within frequency range related to the walking/running activity. Specifically, considering the ranges [1-2] Hz and [2-3] Hz such a reduction is around 39% and 36% respectively.

PRESENTER

Luigi Raiano
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

New Perspectives on Wearable Devices and Electronic Health Record Systems

• Giacomo Assenza

    SEE PRESENTATION

New Perspectives on Wearable Devices and Electronic Health Record Systems

×

ABSTRACT

In recent years, wearable sensors and smart devices, such as smartphones, smart-bands, and smart watches, are frequently adopted in order to monitor the user’s physical activities. Despite the increasing accuracy of the sensors embedded in these devices, such systems are not recognized as medical devices. However, the innovation process in the context of Medicine 4.0 is proposing novel solutions based on wearable sensors, smart clothing and wireless technologies for monitoring patients in remote. At the same time, over the past few years, the most important hospitals, clinics, and medical centres invested to adopt new software platforms, such as electronic health record management systems, able to better manage the patient’s medical data. In this work we want to review the main wearable solutions for activity recognition and medical devices, with the aim to analyze new perspectives based on the integration of these systems within management platforms for electronic health records.

PRESENTER

Giacomo Assenza
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

Infrared Thermography applied on Fresh Food Monitoring in Automated Alerting Systems

• Antonio Panarese

    SEE PRESENTATION

Infrared Thermography applied on Fresh Food Monitoring in Automated Alerting Systems

×

ABSTRACT

The infrared thermography approach is applied for the monitoring of fresh foods located into a refrigerator by controlling the temperature and automatizing the deterioration risk alert. Specifically, the paper discusses the results about infrared thermography methodology combined with image processing technique. The study is performed to check during the time the evolution of the meat temperature when placed out of the refrigerator at room temperature. The experimentation is performed by analyzing the meat oxidation time evolution and checking the minimum temperature behavior defining food quality. A K-Means algorithm is applied in order to locally process the radiometric image highlighting the oxidation effect. Finally are discussed different aspects about radiometric approaches.

PRESENTER

Antonio Panarese
Dyrecta Lab

See Presentation Close

Infrared Thermography and Image Processing applied on Weldings Quality Monitoring

• Giovanni Dipierro

    SEE PRESENTATION

Infrared Thermography and Image Processing applied on Weldings Quality Monitoring

×

ABSTRACT

The present paper proposes a methodological approach to evaluate welding quality in the context of tank production. In particular, infrared thermography was adopted to control the structural homogeneity achieved after welding. The analysis was implemented by applying the K-Means algorithm, morphological image processing and artificial neural network based on the Long Short Term Memory - LSTM - technique. The adopted approach was chosen to perform different image post-processing analysis and therefore highlights, identifies, and quantifies welding inhomogeneities, as cracks and defects. The work was developed within the research framework of an industrial project. The proposed approach could be implemented in inline production systems which integrate an artificial intelligence processor for real time quality monitoring.

PRESENTER

Giovanni Dipierro
DYRECTA LAB SRL

See Presentation Close

Image Processing Segmentation applied on Defect Estimation in Production Processes

• Giovanni Dipierro

    SEE PRESENTATION

Image Processing Segmentation applied on Defect Estimation in Production Processes

×

ABSTRACT

The proposed work focused on a methodological approach to check defects by adopting the Watershed approach. The adopted image segmentation technique was applied by estimating the defect extent of manufactured pieces. In particular, the experimental tests were performed by characterizing defected holes and defining tolerance gaps on the performed measurements. Information about image segmentation sensitivity was provided by varying camera distances from the sample. Additionally, the defect identification was proved by applying the K-Means algorithm as a processing tool on the analyzed image. The work was developed within a research industrial project.

PRESENTER

Giovanni Dipierro
DYRECTA LAB SRL

See Presentation Close

Production Optimization Monitoring System Implementing Artificial Intelligence and Big Data

• Antonio Panarese

    SEE PRESENTATION

Production Optimization Monitoring System Implementing Artificial Intelligence and Big Data

×

ABSTRACT

The proposed work describes an architecture able to optimize production supporting wheat transformation processes, developed within the framework of an industry research project. The architecture is designed in order to integrate and enable different systems and technologies including big data systems and artificial intelligence algorithms. Preliminary results about detected field data and data flow implementation are discussed. A particular attention is focused on predictive maintenance of production machines by infrared thermography imaging and accelerometer signal processing.

PRESENTER

Antonio Panarese
Dyrecta Lab

See Presentation Close

Low Cost IoT Sensor System for Real-time Remote Monitoring

• Matteo D'Aloia

    SEE PRESENTATION

Low Cost IoT Sensor System for Real-time Remote Monitoring

×

ABSTRACT

Over the past few years, remote monitoring based services are developing in different domains such as traffic monitoring, healthcare, emergency management and environment protection. These applications presuppose the system ability to manage a lot of data coming from different systems. In this paper, the design of a module for remote and real-time monitoring of environmental parameters is indicated. The conceived architecture is based on the microservice paradigm and adopts the 2G data communication network.

PRESENTER

Matteo D'Aloia
MASVIS SRL, Italy

See Presentation Close

Use of internal sensors for the identification of wear conditions in automatic machines

• Emanuela Natale

    SEE PRESENTATION

Use of internal sensors for the identification of wear conditions in automatic machines

×

ABSTRACT

In this work a Condition Monitor (CM) procedure has been applied to an automatic machine for cutting and bending of reinforcing bar, with the aim of classifying different wear levels of specific components, mainly using the information provided by sensors inside the system. The methodology has been applied to two different units of the considered machine, with the aim of testing its ability to distinguish different operating conditions in different points of the system. The results appear to be interesting and encouraging, showing a satisfactory ability to classify the different states of wear.

PRESENTER

Emanuela Natale
University of L'Aquila, Italy

See Presentation Close

Comparative Cost and Benefit Analysis of TCal and Classical Calibration

• Sasho Andonov

    SEE PRESENTATION

Comparative Cost and Benefit Analysis of TCal and Classical Calibration

×

ABSTRACT

The concept of Touchless Calibration (TCal), comprising the idea of calibration of measurement equipment in own premises/laboratories instead of sending the instrument far away in a calibration laboratory, is as much attractive as challenging job. TCal leads to reduction of time and costs of the manufacturing companies with acceptable level of quality loss in the calibration. The lower cost is one of the most important benefits of TCal, compared to traditional calibration, and it is subject of analysis in this paper. Following the main request of the ISO/IEC 17025:2017, the risk assessment analysis based on FMEA, is conducted for the purposes of the savings. Calibration is requested in all industries, however, the focus of this contribution is restricted to industrial calibrations of measurement instruments for electric quantities.

PRESENTER

Sasho Andonov
Ss Cyril and Methdius University, Macedonia

See Presentation Close

Prediction of the remaining useful life of mechatronic systems using internal sensors

• Antonella Gaspari

    SEE PRESENTATION

Prediction of the remaining useful life of mechatronic systems using internal sensors

×

ABSTRACT

In this work, a Condition Monitor (CM) procedure has been applied to an automatic machine for cutting of steel bars, for the purpose of estimating the Remaining Useful Life (RUL) of specific components of the system. Two sensors inside the system and an external one have been used to monitor the wear condition of the blade in the cutting unit. Experimental data have been processed to extract synthetic features and, on the basis of those, a fitting Artificial Neural Network (ANN) has been trained and tested. The preliminary results appear to be interesting, showing a satisfactory ability of the ANN to identify the number of working cycles. This study represents a first step towards the ultimate goal of improving the maintenance strategies of the automatic machine.

PRESENTER

Antonella Gaspari
University of L'Aquila, Italy

See Presentation Close

A Sensor System for Non-Destructive Monitoring of Food Ripening Processes

• Alessandro Zompanti

    SEE PRESENTATION

A Sensor System for Non-Destructive Monitoring of Food Ripening Processes

×

ABSTRACT

Food quality, processing and preservation are nodal points in the block chain of food industry. In this context the key points are: non-destructive approach and a design oriented to IoT applications. In this work dry cured ham has been selected as food product for a pilot study checking for feasibility in a large-scale food industry scenario. A measure chain including a non-destructive sampling device and a gas sensor array have been designed and fabricated. The sampler, named FLUTE (Food Life Upkeep Tester), has been patented. It has shown to be effective in a minimal invasive capture of ham aroma during the curing process. The aroma sampled has been analysed with a gas sensor array (named BIONOTE) based on quartz microbalances functionalized with anthocyanins. The dry-cured ham samples were obtained from the ham factory “Prosciuttificio di Bassiano srl” (Bassiano, Italy). A total number of 168 legs of ham were characterized through the BIONOTE system. The ripening stage was correctly classified in the 88.09% of the cases, with an error of 17 days in the worst case. The sensor system was also able to identify meat origin and place of ripening. This system could be developed for automated control of food quality along the block chain by uploading the classification model in cloud and moving the sensors inside the FLUTE.

PRESENTER

Alessandro Zompanti
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

A Smart Spindle Component concept as a standalone measurement system for Industry 4.0 Machine Tools

• Jeremi Wójcicki

    SEE PRESENTATION

A Smart Spindle Component concept as a standalone measurement system for Industry 4.0 Machine Tools

×

ABSTRACT

The increasing diffusion of high performance, low cost sensors and processors has encouraged their integration in several automation devices. Their interconnection and exploitation are supported by the Industry 4.0 paradigm. The paper elaborates on the Smart Component approach, referring to the case of a Smart Spindle for machine tools, considering in particular a spindle designed for robotic machining applications. A Smart Component must be able to perform acquisition locally, sensor fusion, information extraction and data presentation, with a bi-directional data transmission between the Machine Tool and other network nodes. Potential applications and persisting limitations are discussed.

PRESENTER

Jeremi Wójcicki
CNR-STIIMA, Italy

See Presentation Close

Compensation of Temperature Effects on an Automatic System for Diameter Measurement

• Valerio Marcotuli

    SEE PRESENTATION

Compensation of Temperature Effects on an Automatic System for Diameter Measurement

×

ABSTRACT

This work describes the metrological characterization of an automatic measurement system for the identification of the diameter of rectified cylinders with multiple LVDT sensors. This system varies its temperature because of the fluctuation of the ambient temperature (from 15 to 35 °C) while the workpiece exhibits temperature gradients along its axis because of the grinding process used to obtain the final diameter; the effect of these temperature variations can reach up to 25 micrometers, that is very large considering a manufacturing tolerance of 12 micrometers. The first part of the work focused on the evaluation of the repeatability and reproducibility of measurements. The second part aimed to develop a compensation algorithm, for the interfering effects of temperature, based on multiple thermocouple measurements. The algorithm uses two Coefficients of Linear Thermal Expansion estimated by fit-to-purpose experiments, for the workbench and for the measurands respectively. This method allows to reduce measurement uncertainty to 1.1 micrometers.

PRESENTER

Valerio Marcotuli
Politecnico di Milano, Italy

See Presentation Close

A Vision-based Measurement System for Semi-finished Cylindrical Geometries

• Valerio Marcotuli

    SEE PRESENTATION

A Vision-based Measurement System for Semi-finished Cylindrical Geometries

×

ABSTRACT

This work describes a vision-based system for measuring the dimensions of a semi-finished cylinder in open forging, as a function of the rotation angle, in near real-time conditions. To evaluate the performance of the system, we designed a laboratory setup consisting of patterned cylinder at room temperature, with a diameter of approximately 70 mm that can rotate around a horizontal axis. A single camera observes the rotating cylinder and detects simultaneously the diameter and the rotation angle. Images were acquired with different resolutions, as well as at different distances from the cylinder. The tests have shown that, at a distance of 0.7 m from the measurand, the measurement systematic error in the diameter estimation is 0.22 mm with maximum resolution whereas uncertainty of the rotation angle was close to 5°.

PRESENTER

Valerio Marcotuli
Politecnico di Milano, Italy

See Presentation Close

A flexible method to detect the fault of components in an injection group of a diecasting machine.

• Luca Provezza

    SEE PRESENTATION

A flexible method to detect the fault of components in an injection group of a diecasting machine.

×

ABSTRACT

This work presents a simple method to detect the fault of components in an injection group of a diecasting machine. A usual problem in predictive diagnostics in industrial applications is the lack of replicable failure and fatal data: the parameters of the diecasting process are often changed to adapt the machine to a new production cycle and this makes difficult to identify faults using automated data analysis. The proposed method is based on an algorithm able to re-train itself when a change in production is detected. The final prediction of each fault condition is performed by combining classical machine learning analysis and experts' knowledge of the field by identifying discriminant weights to insert in the machine learning analysis. These weights are quantities that represent the experts' knowledge and the algorithm take into account.

PRESENTER

Luca Provezza
University of Study of Brescia, Italy

See Presentation Close

Assessment of the measurments contribution on composites thermoforming processes: a case study of an automotive component

• Antonios Stamopoulos

    SEE PRESENTATION

Assessment of the measurments contribution on composites thermoforming processes: a case study of an automotive component

×

ABSTRACT

The thermoforming manufacturing process appears as one of most promising for obtaining high quality components made of thermoplastic based composites. Many industrial sectors are keen on implementing this method on the production of primary or secondary structures of their products. Nevertheless, a significant number of problems are risen due to the complexity of the process and the materials themselves. Some of them are related to the correct thermoforming conditions, which are difficult to be monitored, while others to the materials architecture. In the present work, presented is a case study of an automotive part made of thermoplastic composites and manufactured via thermoforming. A priori, numerical analysis of the component is conducted to identify fabrication defects and to optimize the stamping and material configuration respectively. After the production of the component, measurements are conducted to identify the variations in several parameters that may influence the product both on its structural integrity as well as its esthetic characteristics.

PRESENTER

Antonios Stamopoulos
UNIVAQ-DIIIE, Italy

See Presentation Close

Development of security mechanisms for a remote sensing system based on opportunistic and mesh networks

• Lucas S. dos Santos

    SEE PRESENTATION

Development of security mechanisms for a remote sensing system based on opportunistic and mesh networks

×

ABSTRACT

The present work describes a remote environment monitoring system based on the paradigms of mesh networks and opportunistic networks, whereby a sensor node can explore “connectivity windows” to transmit information that will eventually reach another network participants. We discuss the threats to the system’s security and propose security mechanisms for the system ensuring the integrity and availability of monitoring information, something identified as critical to its proper operation.

PRESENTER

Lucas S. dos Santos
Federal University of Rio de Janeiro, Brazil

See Presentation Close

Combining exposure indicators and predictive analytics for threats detection in real industrial IoT sensor networks

• Silvio Mazzaro

    SEE PRESENTATION

Combining exposure indicators and predictive analytics for threats detection in real industrial IoT sensor networks

×

ABSTRACT

We present a framework able to combine exposure indicators and predictive analytics using AI-tools and big data architectures for threats detection inside a real industrial IoT sensors network. The described framework, able to fill the gaps between these two worlds, provides mechanisms to internally assess and evaluate products, services and share results without disclosing any sensitive and private information. We analyze the actual state of the art and a possible future research on top of a real case scenario implemented into a technological platform being developed under the H2020 ECHO project, for sharing and evaluating cybersecurity relevant informations, increasing trust and transparency among different stakeholders.

PRESENTER

Silvio Mazzaro
Vitrociset - a Leonardo Company SpA, Italy

See Presentation Close

Public-Key Infrastructure for Smart Meters using Blockchains

• Wilson Melo

    SEE PRESENTATION

Public-Key Infrastructure for Smart Meters using Blockchains

×

ABSTRACT

Public-Key Infrastructures are elementary building blocks to implement digital signatures (i.e., digital notarization) and, hence, ensure information integrity, authenticity, and nonrepudiation. This feature is a promising alternative to improve the reliability of smart meters. However, conventional PKIs can be too expensive in scenarios that consist of a significant number of meters. In this work, we propose a blockchain-based PKI, describing how to tailor this solution to deal with specific aspects related to smart meter protection. We also implement our proposal as a smart contract with the Hyperledger Fabric platform. The results show our solution’s feasibility and provide a reliable model to manage digital certificates for a wide diversity of smart devices.

PRESENTER

Wilson Melo
Brazilian National Institute of Metrology Quality and Technology

See Presentation Close

A Digital Twins Approach to Smart Grid Security Testing and Standardization

• Manolya Atalay

    SEE PRESENTATION

A Digital Twins Approach to Smart Grid Security Testing and Standardization

×

ABSTRACT

The exponential growth of the Internet of Things in recent years has created an ever larger cyber attack surface, introducing new security vulnerabilities for all computerized systems. Among the most significant of those systems are industrial control systems (ICS) consisting of many cyber physical components, and smart grids are a prominent example of ICS, whose failures have potential to cause major disruptions in all aspects of our daily lives. In this paper, we provide an overview of smart grid cybersecurity standards, and review major threats to smart grid environments at the physical, network and application layers. In order to overcome the current lack of standards for security evaluation of smart grids, we propose a digital twins based approach for the complete lifecycle of a smart grid, which accurately models the functioning of the physical grid and avoids service disruptions caused by running security tests on the actual grid. A digital twins based approach is promising to provide a common ground for the development of standardized models for continuous and comprehensive penetration testing of smart grids.

PRESENTER

Manolya Atalay
Middle East Technical University, Turkey

See Presentation Close

Proficiency Testing for Software Analysis and Cybersecurity Laboratories

• Raphael Machado

    SEE PRESENTATION

Proficiency Testing for Software Analysis and Cybersecurity Laboratories

×

ABSTRACT

Proficiency tests are a central activity in demonstrating the competence of accredited laboratories. In the present work, we developed a proposal for the realization of Proficiency Testing for laboratories that work in the areas of software testing and cybersecurity. This is the first example of a Proficiency Testing round focusing on software code analysis activities, an important activity in software compliance assessment programs. The proposed approach uses code coverage metrics to evaluate the ability of laboratories in evaluating the source code of a software. We prove the feasibility of the proposal through the execution of a proficiency test “round” with the participation of six laboratories accredited to conduct software tests in compliance assessment programs in Brazil.

PRESENTER

Raphael Machado
Inmetro and UFF, Brazil

See Presentation Close

Identification of Data Injection Attacks in Networked Control Systems with Varying Setpoint Condition

• Alan de Sá

    SEE PRESENTATION

Identification of Data Injection Attacks in Networked Control Systems with Varying Setpoint Condition

×

ABSTRACT

The Industry 4.0, which widely uses Networked Control Systems (NCS), plays a relevant role in nowadays society and can be threatened by cyberattacks. In this context, recent literature presents a countermeasure that uses white gaussian noise and a Noise Impulse Integration technique to identify controlled data injection attacks in NCSs. Despite the high accuracy of such countermeasure when the NCS setpoint does not vary, the literature indicates that it presents loss of performance when the NCS setpoint is slowly changing. To overcome this constraint, this work proposes a novel approach to improve the performance of the referred countermeasure in order to make it resilient to variations in the NCS setpoint.

PRESENTER

Alan de Sá
Brazilian Navy, Brazil

See Presentation Close

Security vulnerability in Internet of Things sensor networks protected by Advanced Encryption Standard

• Antonella Cioffi

    SEE PRESENTATION

Security vulnerability in Internet of Things sensor networks protected by Advanced Encryption Standard

×

ABSTRACT

In the new era of Internet of Things, the emerging of smart devices makes security and privacy the first requirements and the major challenges of a distributed network. Despite the implementation of security measures, as encryption mechanisms protecting sensor data, and cryptographic algorithms, various attacks seem to undermine the IoT devices security. This paper reports the preliminary results of a side-channel attack (scatter attack) addressed on an 8-bit IoT microcontroller protected by the Advanced Encryption Standard. The attack, based on an high-SNR data acquisition micro-system and a suitable statistical analysis, allows to discover part of the encryption key, demonstrating the security vulnerability of Internet of Things sensor networks protected by the AES.

PRESENTER

Antonella Cioffi
University of Naples Federico II, Italy

See Presentation Close

A Low Cost and Flexible Power Line Communication Sensory System for Home Automation

• Vittoriano Muttillo

    SEE PRESENTATION

A Low Cost and Flexible Power Line Communication Sensory System for Home Automation

×

ABSTRACT

This work focuses on the definition of a home automation system based on power line communication. A low cost and non invasive system has been developed and tested with successful results. It is based on the Cypress CY8CPLC10, an integrated power line communication chip which embeds both a PHY modem and a network protocol stack. The information management and data generation processes are demanded to a microcontroller, in this first prototype, being implemented with a standard commercial board. Combining the use of a microcontroller with a power line modem and a dedicated software application it is possible to manage sensors and actuators in the neighbors through the power grid and without modifying the existing electrical and network systems.

PRESENTER

Vittoriano Muttillo
University of L'Aquila, Italy

See Presentation Close

Towards the Design of Microcontroller Based Embedded Sensory systems with a Five-Parameter Single Diode Estimation Method for Photovoltaic Panels

• Vittoriano Muttillo

    SEE PRESENTATION

Towards the Design of Microcontroller Based Embedded Sensory systems with a Five-Parameter Single Diode Estimation Method for Photovoltaic Panels

×

ABSTRACT

We here propose the extension of the Arduino Based Embedded Sensory systems Design of a five-parameter single diode estimation method for photovoltaic panels. The first attempt shows how to implement an already proposed algorithm into a microcontroller-based system embedded in the PV panel module communicating with a long-range commercial high-frequency radio transmitter. Concerning the five parameter estimation method, it is based on an iterative algorithm, to estimate the parameter of the electrical single-diode model of the panel starting from the panel's datasheet. The proposed very low-cost architecture can be further integrated into a single chip apparatus in order to be implemented directly in the panel embedded electronics.

PRESENTER

Vittoriano Muttillo
University of L'Aquila, Italy

See Presentation Close

RFID interface for compact pliable EMG wireless epidermal sensor

• Carolina Miozzi

    SEE PRESENTATION

RFID interface for compact pliable EMG wireless epidermal sensor

×

ABSTRACT

The growth of epidermal electronics requires low-cost, compact, wireless and low-power consumer technologies. Commercially available electromyographic (EMG) sensors do not fully meet these requirements. Radiofrequency Identification (RFID) is a low-cost wireless communication technology that helps in reducing sensor size and power requests. This work proposes the design of a 3cm x 3cm RFID antenna surrounding an ad hoc EMG sensor circuitry and supporting the mid-range data communication between 40cm – 1m. The resulting RFID-EMG sensor is a compact, pliable and conformable device, suitable for sport, wellness, healthcare and medical applications.

PRESENTER

Carolina Miozzi
University of Rome Tor Vergata, Italy

See Presentation Close

Modular QMB sensors array for E-health applications

• Alessandro Zompanti

    SEE PRESENTATION

Modular QMB sensors array for E-health applications

×

ABSTRACT

This work describes the design and development of a gas sensor module, using QMBs (Quartz Crystal Microbalances) as sensing element, for E-health applications (e.g. Exhaled Breath Analysis). The developed module can be used with other modules, as an array of gas sensors, in a master-slave architecture based on an I2C communication bus. A custom electronic interface has been developed to properly drive the QMBs and a microcontroller has been used to read the output signal: the module is able to use QMBs with a fundamental resonant frequency ranging from 20 to 50 MHz, with a sensing resolution of about 1 Hz. The performances of the sensing modules have been investigated with a particular focus on sensor's responses to typical Relative Humidity and Temperature levels of exhaled breath samples.

PRESENTER

Alessandro Zompanti
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

Empowering Blind People Mobility: a Millimeter- Wave Radar Cane

• Emanuele Cardillo

    SEE PRESENTATION

Empowering Blind People Mobility: a Millimeter- Wave Radar Cane

×

ABSTRACT

In this paper, a millimeter-wave radar cane for enhancing the mobility of visually impaired and blind people is presented. The system exploits a compact 122 GHz radar system that can be easily integrated on the stick. The millimeter-wave radar cane is able to detect obstacles in the area scanned by the user, providing a feedback about their distance. Moreover, it is capable of discerning between human and non-human obstacles by detecting their breathing vital sign. This is not a straightforward task due to the concurrent little chest displacement to be measured and the movements of both the user and the human target. The operating principle and the feasibility of the proposed solution are shown by simulating the entire scenario, whereas the effectiveness of the system is demonstrated by employing a 122 GHz radar board.

PRESENTER

Emanuele Cardillo
University of Messina, Italy

See Presentation Close

Active Filter and RFID Based Identifier for Heartbeat Monitoring

• Alfiero Leoni

    SEE PRESENTATION

Active Filter and RFID Based Identifier for Heartbeat Monitoring

×

ABSTRACT

In this work, we present an autonomous system for monitoring the heart rate that has been conceived by using a piezoelectric sensor, an active bandpass filter (ABF) and a Radio Frequency Identifier (RFID) tag combined with an external tag reader. The system can be implemented in a single chip for wearable and portable applications. A sensitive piezoelectric sensor generates a voltage signal from the heartbeat and this signal acts as a control voltage for the ABF and RFID accordingly to the heart rate detection. The piezoelectric sensor and the RFID system that have been considered now are commercial components, while the ABF is the core of the proposed system since it has been designed in such a way that it changes its transfer function allowing the RFID matching, and so the transmission, when a heartbeat occurs.

PRESENTER

Alfiero Leoni
University of L'Aquila, Italy

See Presentation Close

Software for calculation with physical quantities

• Blair Hall

    SEE PRESENTATION

Software for calculation with physical quantities

×

ABSTRACT

Software support for calculations involving physical quantities is discussed. A Python package (called Quantity-Value) is presented that allows a measured value to be paired with a measurement unit (scale), in an entity that can be used in mathematical operations. The software applies the rules of quantity calculus so that the nature of quantities, and the measurement scales, become an integral part of calculations. To overcome traditional difficulties with unit-checking systems, the software places emphasis on quantities, rather than units. Quantities of interest in the problem domain can be declared and dimensional information for ‘dimensionless’ quantity ratios can be retained. This approach appears to be more powerful than systems designed to work directly with measurement units.

PRESENTER

Blair Hall
Measurement Standards Laboratory of New Zealand

See Presentation Close

Quantifying Metrological Redundancy in an Industry 4.0 Environment

• Gertjan Kok

    SEE PRESENTATION

Quantifying Metrological Redundancy in an Industry 4.0 Environment

×

ABSTRACT

Industry is moving rapidly towards a fourthindustrial revolution in which connectivity and data flow play a crucial role. Sensor networks in so-called Factories of the Future are measuring many different quantities and should be robust against failing sensors and other faults. Therefore, it is good design practice to incorporate some form of redundancy in the network. Part of that redundancy simply consists of having spare parts at hand for when the system hardware fails. In this paper we will rather take a measurement centered approach and assess how much the quality of a measurement – as quantified by its measurement uncertainty – degrades when one or more sensors fail. Various types of metrological redundancy will be defined which may fill a gap in ontology concepts relevant for Industry 4.0. The system performance over time can be evaluated by the proposed metrics which are of a metrological nature as they are ‘uncertainty aware’. Finally, the concepts will be applied to datasets produced by two industrial test environments.

PRESENTER

Gertjan Kok
VSL, The Netherlands

See Presentation Close

Semantic Information in Sensor Networks: How to Combine Existing Ontologies, Vocabularies and Data Schemes to Fit a Metrology Use Case

• Maximilian Gruber

    SEE PRESENTATION

Semantic Information in Sensor Networks: How to Combine Existing Ontologies, Vocabularies and Data Schemes to Fit a Metrology Use Case

×

ABSTRACT

Self-describing sensors and measurements are a key component to establish (semi-)automated data-analysis in the context of Industry 4.0. In this contribution, multiple popular ontologies and vocabularies in the field of metrology are evaluated regarding their suitability for an industry-oriented metrological use case. The results are used to map necessary concepts from existing knowledge bases into a coherent new ontology that fulfills metrological requirements of sensor and measurement descriptions. We are considering use cases where aspects of sensor networks, network topology, network robustness, information fusion, calibration models for dynamic uncertainty, correct metrological representation and implementation performance are of interest.

PRESENTER

Maximilian Gruber
Physikalisch-Technische Bundesanstalt, Germany

See Presentation Close

Fundamental Physical Constants Ready for Machine Communication in a Digitalized World

• Shan Lin

    SEE PRESENTATION

Fundamental Physical Constants Ready for Machine Communication in a Digitalized World

×

ABSTRACT

The complete set of values of the fundamental constants as recommended by the Committee on Data for Science and Technology (CODATA) are provided in a machinereadable format. This provides a mechanism for the secure and unambiguous communication of all digitised metrology data. The format is based on a data model for machine-readable exchange of metrological data (D-SI), which is under development at the Physikalisch-Technische Bundesanstalt (PTB). The representation of the Defining Constants of the SI as available in the 2014 and 2018 CODATA listings are discussed as examples.

PRESENTER

Shan Lin
Physikalisch-Technische Bundesanstalt, Germany

See Presentation Close

A Measurement Information Infrastructure's Benefits for Industrial Metrology and IoT

• Mark J. Kuster

    SEE PRESENTATION

A Measurement Information Infrastructure's Benefits for Industrial Metrology and IoT

×

ABSTRACT

Previous work has economically motivated and proposed a measurement information infrastructure (MII) as one means of digitally transforming the measurement information economy within the international quality infrastructure’s context. This paper summarizes ongoing work toward, and requirements for, an MII and proposes rules for a standard taxonomy of measurands. It offers a further economic argument regarding the effects of intrinsic standard technology advances and considers an MII’s potential impacts on cost-effective industrial metrology and risks for IoT measuring instruments adoption. The paper argues that quickly adopting an MII and digital metrology in general should lead to large cost savings in national quality infrastructures, which in turn will improve the cost-risk balance for reliance on IoT sensors in particular.

PRESENTER

Mark J. Kuster
Consultant, USA

See Presentation Close

Infrastructure for Digital Calibration Certificates

• Clifford Brown

    SEE PRESENTATION

Infrastructure for Digital Calibration Certificates

×

ABSTRACT

Digital Calibration Certificates (DCCs) will soon replace Paper Calibration Certificates (PCCs). As electronic files they can be communicated instantly and securely to the customer and are machine readable. However, DCCs require a digital security and software infrastructure to fulfil the current ‘analogue’ processes of authentication and validation that deliver a fully traceable calibration chain to primary standards. Additionally, software and knowledge representation systems will need to be put in place to support the use of DCCs both for the metrology community and for industry. We present in this work an initial analysis of the requirements of this infrastructure for DCCs in order to support Industry 4.0, the Internet of Things (IoT) and future digital metrology.

PRESENTER

Clifford Brown
National Physical Laboratory, UK

See Presentation Close

A universal metadata model for metrological complex quantities

• Vincenzo Paciello

    SEE PRESENTATION

A universal metadata model for metrological complex quantities

×

ABSTRACT

In a digital network in which existing and new applications communicate with each other, the digitalization of metrology acquires ever greater importance for the exchange of measurement values. This paper specifies a harmonized, universal, coherent machine-readable metadata model for the exchange of digital complex measurement values following the specifications of the International System of Units. Conventions for the evaluation and expression of measurement uncertainty are based on the internationally recognized Guide to the Expression of Uncertainty in Measurement.

PRESENTER

Vincenzo Paciello
University of Cassino and Southern Lazio, Italy

See Presentation Close

A new LoRaWAN adaptive strategy for smart metering applications

• Emiliano Sisinni

    SEE PRESENTATION

A new LoRaWAN adaptive strategy for smart metering applications

×

ABSTRACT

One of the most widespread applications of IoT technologies is smart metering. Despite remote metering in smart grids is not a novelty, the advent of Low Power Wide Area Network (LPWAN) wireless technologies allowed to extend the concept to gas and water distribution. However, these batterysupplied meters must ensure an operating lifetime longer than 10 years without any maintenance, thus leading to battery oversizing. This work focuses on LoRaWAN and proposes an innovative adaptive strategy for equalizing the message time duration in order to maximize the battery exploitation. A simulator has been purposely designed to evaluate the performance in a real-world scenario, considering a node density of hundreds of nodes per square km. The simulation results demonstrate that a better exploitation of the battery is possible, ensuring an increase by 10 times of the amount of the amount of useful user data bytes transferred by meters.

PRESENTER

Emiliano Sisinni
University of Brescia, Italy

See Presentation Close

Performance Evaluation of an evolving data compression algorithm embedded into an OBD-II edge device

• Marianne Silva

    SEE PRESENTATION

Performance Evaluation of an evolving data compression algorithm embedded into an OBD-II edge device

×

ABSTRACT

The new industrial revolution, known as industry 4.0, aims to create value throughout the product life cycle into all industries sectors. In the automotive industry perspective, data can be obtained throughout the life cycle of vehicles if they are appropriately instrumented with an On-Board Diagnostic scanner (OBD-II). Communications interfaces (3G/4G/LoraWan/Wi-Fi) assume essentials rules in order to relay all collected data to services in the cloud. Challenges emerge when using the Low Power, Wide-Area Network (LPWAN) protocols, as the case of LoRaWAN. This article aims to evaluate the feasibility of embedding a data compression algorithm driven by a light-weight evolving real-time approach in order to reduce the amount of data to be transmitted periodically. The proposal was embedded in a low-cost, low-power system on a chip microcontroller based on Edge OBD-II Freematics ONE+TM. Results have shown the feasibility of the proposal and indicated compression rates of up to 98% without impact the primary operation of the edge device.

PRESENTER

Marianne Silva
Federal University of Rio Grande do Norte, Brazil

See Presentation Close

Proposal of a Hybrid LoRa Mesh / LoRaWAN Network

• Eduardo Paciencia Godoy

    SEE PRESENTATION

Proposal of a Hybrid LoRa Mesh / LoRaWAN Network

×

ABSTRACT

There is a recent interest in the deployment of Low Power Wide Area Networks (LPWANs), such as LoRaWAN, to support Internet of Things (IoT) applications. Even though the main advantage of these LPWANs are the long rage communication, the challenge of providing seamless and shadow area coverage still remains. This paper presents a proposal of a hybrid LoRa Mesh/LoRaWAN network to cope with this challenge. In this proposal, a mesh network of LoRa nodes are connected to a Proxy node that works as a mesh coordinator and is also connected to the LoRaWAN network. The advantage of this topology is the improvement of the communication coverage in shadow areas where a regular LoRaWAN node cannot be reachable in cases of obstacles or topography. The development of the LoRa Mesh network as well as the routing mechanism are presented and verified with experimental results. Finally, the integration of the LoRa Mesh with the LoRaWAN networks is discussed and a proposal is presented.

PRESENTER

Eduardo Paciencia Godoy
São Paulo State University (Unesp), Brazil

See Presentation Close

Introducing a survey methodology for assessing LoRaWAN coverage in Smart Campus scenarios

• Rafael Cunha

    SEE PRESENTATION

Introducing a survey methodology for assessing LoRaWAN coverage in Smart Campus scenarios

×

ABSTRACT

The LoRa is a Low Power Wide Area Network (LPWAN) technology. It has been proposed as a viable wireless connection method for the implementation of the Internet of Things (IoT), thanks to its wide coverage, low complexity and low energy consumption. Several studies ave been carried out about real coverage performance. In this article, a new test methodology for the experimental evaluation of LoRaWAN coverage within a smart campus is presented. The new approach consists in the definition of devices, method and procedures. The architecture of the mobile node is outlined. The survey procedure is based on a mapping phase, necessary to highlight the LoRaWAN coverage in the test area. Finally, a use case is described in the article: it is not intended for evaluating a specific implementation, but for assessing the suitability of the proposed methodology. The use case results demonstrate the effectiveness of the survey methodology in a real smart campus.

PRESENTER

Rafael Cunha
Universidade Federal do Rio Grande do Norte

See Presentation Close

Systems for an intelligent application of Automated Processes in industry: a case study from "PMI IoT Industry 4.0" project

• Alessandro Massaro

    SEE PRESENTATION

Systems for an intelligent application of Automated Processes in industry: a case study from "PMI IoT Industry 4.0" project

×

ABSTRACT

The proposed work describes the work done in the industry research project based mainly in the implementation of technologies enabling Internet of Things -IoT-, Industry 4.0, and Decision Support System (DSS) facilities for a Small and medium-sized enterprise (SME). The initial part of the paper discusses some important aspect about data processing by showing generic graphical user interfaces (GUIs) suitable for data processing and for DSS implementing data mining algorithms. In the second part is designed an architecture able to acquire sensor data, improving technological and scientific innovations. Finally, is designed and developed a prototype sensors agent system interconnected with a neural network data cluster, proving the DSS functionality of the whole designed architecture.

PRESENTER

Alessandro Massaro
Dyrecta Lab

See Presentation Close

Fault Classification Driven by Maintenance Management for Smart Maintenance Applications

• Roberto Bodo

    SEE PRESENTATION

Fault Classification Driven by Maintenance Management for Smart Maintenance Applications

×

ABSTRACT

The study focuses on health monitoring applications that enables companies to offer smart maintenance services in the general context of industry 4.0. To this aim, a common practice consists in acquiring technical data, mining them using machine learning algorithms, and then deciding by taking into account commercial policies too. This work aims to demonstrate that business information can be advantageously embedded in a modified machine learning workflow. The main idea is supported by a frequent fact: practical maintenance procedures are less than the possible fault types. This assumption allows a task redefinition, thus providing an output ready for taking a final decision with better overall performances. A case study is analyzed in order to show the performance of the proposed strategy in an industrial application of condition monitoring. A combination of hypotheses and classification algorithms commonly used for predictive maintenance has been tested in order to check the performance improvement. In particular, Decision Trees, Nearest Neighbors, Linear SVM, Random Forest, AdaBoost, Naive Bayes and XGBoost have been considered. In all cases having a statistical significance, an improvement has been observed. Moreover, for the case of decision trees the advantages are gained regardless the tree heights, that is really interesting when low-performance computing platforms are actually available, as it happens for the case of IoT nodes.

PRESENTER

Roberto Bodo
Università degli Studi di Padova, Italy

See Presentation Close

A Cloud-Oriented Measurement System for Radiological Investigation and Traceability of Stones

• Marco Marini

    SEE PRESENTATION

A Cloud-Oriented Measurement System for Radiological Investigation and Traceability of Stones

×

ABSTRACT

Radiological measurements and traceability of materials are becoming more and more important in the industrial sector of stones and building materials for both producers and users. This is due to the recent European regulatory restrictions on the maximum level of radiological emissions for materials intended for use in public and private building structures. The proposed system, called CORSAIR (Cloud Oriented Radiation Sensor for Advanced Investigation of Rocks) is a cyber-physical system empowered by cloud-based technologies that consists of sensing nodes, data collection gateways and a centralized cloud application. These components are interconnected in a star-of-stars topology, exploiting respectively LoRaWAN, Internet network, and provide specialized user interface. The system includes also handheld devices with dedicated user interface to control the sensing nodes on the field via WiFi Direct connection. The system introduces a fast, repeatable, real-time and nondestructive method to measure radiological emissions and other parameters of each single building material item, uniquely identified by an applied RFID tags. Moreover, it makes those data available to all stakeholders, enabling to trace the materials along the full market chain, from extraction to the final customer, with modern technologies.

PRESENTER

Marco Marini
Università di Pisa, Italy

See Presentation Close

An IoT condition monitoring system for resilience based on spectral analysis of vibration

• Andrea Fioravanti

    SEE PRESENTATION

An IoT condition monitoring system for resilience based on spectral analysis of vibration

×

ABSTRACT

In these years, the Industry 4.0 paradigm has widespread in worldwide. Smart new automation tools and technologies are rapidly changing the face of manufacturing and industry. The use of new strategies in maintenance management increases the company's competitiveness on the market. The most important task is the reduction of production costs, which can be pursued by reducing downtime and increasing maintenance efficiency. These objectives can be achieved through the widespread use of low-cost smart devices, which can provide a detailed and online view of the operating conditions of the machines. For these reasons, in this paper an IoT system has been proposed. This system analyzes the machinery vibration spectrum, in order to have a conditional and continuous monitoring for the resilience of the machinery after a failure.

PRESENTER

Andrea Fioravanti
University of L'Aquila, Italy

See Presentation Close

Evaluation of the impact on industrial applications of NTP used by IoT devices

• Paolo Ferrari

    SEE PRESENTATION

Evaluation of the impact on industrial applications of NTP used by IoT devices

×

ABSTRACT

The requirements of distributed systems implemented using IoT paradigms include the sharing of a common time reference. When the applications are intended for industrial scenarios, the desired time synchronization uncertainty decreases, due to the real-time needs of this kind of systems. Currently, the most diffused way to obtain a time reference for an Internet connected device is to use NTP (Network Time Protocol) for querying time servers. This paper is focused on industrial IoT applications and it is aimed to evaluate the impact that NTP synchronization performance and NTP throughput may have on the real-time host network. Analytical formulas for estimating the NTP impact are introduced. The work is complemented by the presentation of a use case that shows the use of NTP for the synchronization of a large industrial plant at field level. The results highlight the threat to the real-time behavior of the automation system caused by the uncontrolled peaks of traffic due to NTP. Last, some design considerations for mitigation of the impact are discussed.

PRESENTER

Paolo Ferrari
University of Brescia, Italy

See Presentation Close

Evaluating Human-Machine Translation with Attention Mechanisms for Industry 4.0 Environment SQL-Based Systems

• Silvan da Silva

    SEE PRESENTATION

Evaluating Human-Machine Translation with Attention Mechanisms for Industry 4.0 Environment SQL-Based Systems

×

ABSTRACT

The use of relational databases is increasingly present in the industry. Applications in medical, IoT and industry 4.0 are examples of this. Despite the large capacity and efficiency in storing and retrieving data, this type of database requires technical knowledge in specific query languages to access this information, which distances these types of application from the lay public. In this work, we propose an application of recent models in natural language processing that use neural networks, as well as attention mechanisms for the translation of natural language in English to SQL applied in an SQL database of a system to store data from sensors, focused on the concept of Industry 4.0. Paired examples of natural language phrases were generated with their corresponding SQL query to be used for training and validation. By training the neural network, we obtained a language model with an accuracy of approximately 99% in the validation set.

PRESENTER

Silvan da Silva
Federal University of Rio Grande do Norte

See Presentation Close

Introducing a cloud based architecture for the distributed analysis of Real-Time Ethernet traffic

• Andre Dias

    SEE PRESENTATION

Introducing a cloud based architecture for the distributed analysis of Real-Time Ethernet traffic

×

ABSTRACT

The use of industrial communication protocols based on Real-Time Ethernet (RTE) standards is completely replacing traditional industrial fieldbuses. As usual, when a technology becomes mature, the need of efficient diagnostic and maintenance tools quickly raises. Very often, following the paradigm of Industry 4.0, the most effective diagnostic systems are today based on distributed, cloud-centric, architectures and artificial intelligence. However, the distributed analysis of RTE systems is challenging, considering the plurality of protocols and the stringent cost constrains which are common in industry. In this paper, a new architecture for the distributed analysis of RTE networks is proposed, leveraging on distributed probes that send traffic samples to Matlab cloud for remote analysis. The paper also proposes a software conversion tool to adapt general PCAP files captured by popular sniffers (e.g. Wireshark) into MAT file for easier Matlab elaboration. Last, a test bench for characterization (in terms of transfer delays) of the first part of the chain for RTE traffic sampling is described. The results show that in less than 10 seconds it is possible to transfer chunks of RTE traffic data (captured on industrial networks with hundreds of real-time devices) directly to the cloud and to have them converted in Matlab format.

PRESENTER

Andre Dias
Federal Institute of São Paulo, Brazil

See Presentation Close

Development of an Energy Meter based on IoT

• Allyson Franklin M. Borges

    SEE PRESENTATION

Development of an Energy Meter based on IoT

×

ABSTRACT

Managing energy consumption in houses, industries or cities is a critical area in which IoT can contribute. This work present a low cost energy meter based on IoT, capable of measuring several energy circuits with a single microcontroller. The meter also provides power quality parameters, and is capable of online and bidirectional communication, so that the system can receive data and send commands to the meter. This enables configuring its measuring parameters and also creating energy saving policies or equipment protection. Experimental results show the system works as proposed.

PRESENTER

Allyson Franklin M. Borges
UFRN - Universidade Federal do Rio Grande do Norte, Brazil

See Presentation Close

Microservice Orchestration for Process Control in Industry 4.0

• Eduardo Paciencia Godoy

    SEE PRESENTATION

Microservice Orchestration for Process Control in Industry 4.0

×

ABSTRACT

New manufacturing applications in Industry 4.0 (I4.0) focus on the combination of industrial informatics and automation technologies, including the Industrial Internet of Things, Network Control Systems, Service Oriented Architectures and Cloud Computing. The great challenge of these applications is to promote the integration between these technologies, equipment and systems allocated at different hierarchical levels of industrial systems, making automation collaborative through the use and sharing of services. This paper focuses on the study, implementation and performance analysis of microservices orchestration for process control applications in I4.0. The Microservice-Oriented Architecture is described, as well as the development of microservices related to process control. The microservice orchestration is evaluated through experimental results considering a process control loop and the performance analysis of the service communication.

PRESENTER

Eduardo Paciencia Godoy
São Paulo State University (Unesp), Brazil

See Presentation Close

Sensor Nodes for Continuous Monitoring of Structures Through Accelerometric Measurements

• Federico Zanelli

    SEE PRESENTATION

Sensor Nodes for Continuous Monitoring of Structures Through Accelerometric Measurements

×

ABSTRACT

Nowadays, the need of continuous monitoring systems on different type of structures is becoming crucial in many sectors. Data collected through this type of measurement devices can be used for real time alarm generation in case of possible dangerous situations or gathered in order to figure out the remaining fatigue life of the structure and to schedule accordingly the predictive maintenance. A custom sensor has been designed to this purpose. The focus of the paper is the sensor node architecture: the device has been specifically designed in order to perform accelerometric measurements, to process data on board, to send synthetic data wirelessly. In the design stage particular attention has been paid to the energy consumption, in order to make the node energetically autonomous using harvesters or small power sources. Sensors have been realized and tested in two use cases, both in severe environmental conditions in order to assess the reliability of the whole system in real operative scenarios.

PRESENTER

Federico Zanelli
Politecnico di Milano, Italy

See Presentation Close

SAW Sensors Directly Integrated onto Industrial Metallic Parts for Manufacturing 4.0

• Prince Mengue

    SEE PRESENTATION

SAW Sensors Directly Integrated onto Industrial Metallic Parts for Manufacturing 4.0

×

ABSTRACT

In this communication, we describe the direct integration of thin film SAW resonators on industrial metals. Two different structures were studied numerically and experimentally: Al/ZnO/Duralumin and Al/ZnO/Titanium. Resonators were manufactured on ZnO thin film directly deposited by RF magnetron sputtering on polished Duralumin and Titanium substrates. The presence of Rayleigh waves was demonstrated. The aim of these resonators is an application in the field of structural health monitoring.

PRESENTER

Prince Mengue
Institut Jean Lamour, France

See Presentation Close

Prototyping and Metrological Characterization of a Data Acquisition and Processing System Based on Edge Computing

• Giuseppe Lorenzini

    SEE PRESENTATION

Prototyping and Metrological Characterization of a Data Acquisition and Processing System Based on Edge Computing

×

ABSTRACT

This paper describes a data acquisition and processing architecture developed for monitoring industrial machineries. The architecture is based on the paradigm of edge computing and is developed using single-board computers Raspberry Pi 3B+ connected to more WeMos Lolin D1 Mini microcontrollers. All the components underwent to a metrological characterization, and compensation algorithms were proposed for the bias errors, in accordance with the ISO GUM framework. The measurements' repeatability and reproducibility were performed in accordance with current standards. The measurement chain was verified with vibration measurements; tests performed on a shaker highlight a type A uncertainty of 0.35 m/s2. The SINAD was larger than 60 dB, with no meaningful dependencies from the temperature. The comparison with a common industrial acquisition system showed the validity of the proposed architecture.

PRESENTER

Giuseppe Lorenzini
Politecnico di Milano, Italy

See Presentation Close

Online Fault Detection: a Smart Approach for Industry 4.0

• Mariorosario Prist

    SEE PRESENTATION

Online Fault Detection: a Smart Approach for Industry 4.0

×

ABSTRACT

The fourth industrial age takes the manufacturing factory to a new level by introducing smart, extendible, flexible, modular and customized mass production technologies. Production lines or machines need to be integrated at the management level to be industry 4.0 compliant: in this way they can create and optimize a customer-oriented production, while constantly maintaining good performance conditions. In this context, one of the main challenges is the possibility to detect faults as fast as possible, to accurately diagnose those faults which can negatively affect the overall production cycle, and finally address them before it is too late. Due to the great importance that electric motors play in this context, an online smart algorithm for fault detection in electric motors is proposed in this paper. The effectiveness of the proposed method has been validated by applying it on an experimental benchmark, where the results show that the method is accurate and fast in detection of faults.

PRESENTER

Mariorosario Prist
Università Politecnica delle Marche

See Presentation Close

Transformation matrices for 3D shape sensing with polyimide-coated multicore optical fiber

• Davide Paloschi

    SEE PRESENTATION

Transformation matrices for 3D shape sensing with polyimide-coated multicore optical fiber

×

ABSTRACT

This paper presents a three-dimensional shapereconstructing algorithm applied on a shape sensing system based on a polyimide-coated 7-core optical fiber. Fiber opticbased shape sensing consists in numerically evaluating the strains applied to the fiber in order to identify useful spatial parameters such as the curvature radii defining its shape. Multicore fibers are preferable since they can also provide information regarding the direction of bending. The proposed method relies on the homogeneous transformation matrices normally used in robotics, which can express the position of a point in different frames, i.e. from local to global coordinates. The results are shown for both a two-dimensional and a threedimensional configuration, achieving an average relative error of 0.23% and 0.19% of the total length respectively. The small computation time (0.0023 s) makes this algorithm suitable for real-time shape reconstructions in a variety of engineering fields.

PRESENTER

Davide Paloschi
Politecnico di Milano, Italy

See Presentation Close

Temperature Monitoring During Microwave Thermal Ablation of Ex Vivo Bovine Bone: a Pilot Test

• Elena De Vita

    SEE PRESENTATION

Temperature Monitoring During Microwave Thermal Ablation of Ex Vivo Bovine Bone: a Pilot Test

×

ABSTRACT

Many minimally invasive thermal techniques, such as radiofrequency ablation, laser ablation, and microwave ablation (MWA) have gained substantial attention and broad clinical acceptance for the treatment of several tumors. All these treatments cause a high temperature increment, cytotoxic for the cells within the target organ. The knowledge of the ablation process effects in terms of temperature increment can be crucial to optimize the treatment settings and to avoid the occurrence of damages the healthy structures located around the tumor. During the last years, several feasibility studies on the use of MWA for bone tumor have been carried out, but an experimental analysis of the temperature reached within the bone during the treatment has not been performed. The aim of this work is to present a multi-point temperature measurement reached within the bone during MWA. Experiments were performed on an ex vivo bovine femur using a MWA system at a power of 75 W and a treatment time of 8 min. Femur temperature was measured in 30 points inside the bone and around the MW antenna, covering a large area. The measurements were performed by using three fiber optics embedding 10 fiber Bragg grating sensors each. Results of this pilot study showed the capability of the proposed approach for a multi-point temperature monitoring in bone undergoing MWA.

PRESENTER

Elena De Vita
University of Naples Parthenope, Italy

See Presentation Close

Optical Fiber Biosensor Based on an Etched High-Scattering Fiber: Towards Reflector-Less Biosensors

• Daniele Tosi

    SEE PRESENTATION

Optical Fiber Biosensor Based on an Etched High-Scattering Fiber: Towards Reflector-Less Biosensors

×

ABSTRACT

We propose an optical fiber biosensor based on a minimalistic architecture, labelled 'reflector-less biosensor'. The sensing unit is simply a high-scattering fiber (doped with MgO nanoparticles), wet-etched in a hydrofluoric acid bath. The Rayleigh scattering signatures are detected in reflection, achieving a sensitivity up to over 10 nm/RIU (refractive index units). The system has been functionalized for thrombin biosensing, achieving a detection of tens of nanomolar concentrations.

PRESENTER

Daniele Tosi
Nazarbayev University, Kazakhstan

See Presentation Close

Laser Beam Self-Focusing in Optical Fiber controlled through FBG integration

• Lorenzo Dinia

    SEE PRESENTATION

Laser Beam Self-Focusing in Optical Fiber controlled through FBG integration

×

ABSTRACT

Optical fibers are elements that are mainly used as a means to transmit light. In this paper, a fiber optic constituted by a core, a cladding and a Bragg grating in the core center has been studied. A laser beam with a Gaussian shape is let to propagate through the core of the fiber with an intensitydependent refractive index. In the center of the fiber, the refractive index will reach the highest value, focusing the beam. This property of the Gaussian beam to a specific intensity induces positive focusing is called self-focusing. A fiber Bragg grating is integrated inside the core of the fiber in order to control the self-focusing phenomenon. Five different materials are used for the grating for this purpose. An important relationship between the intensity of the beam inside the grating and, thus, the self-focusing and the material used is shown. The setup arrangement of the optical sensor is modeled through Comsol Multiphysics (Wave Optics Module), based on the FEM (Finite Element Method) solver.

PRESENTER

Lorenzo Dinia
Sapienza University of Rome, Italy

See Presentation Close

Towards temperature-controlled laser ablation based on fiber Bragg grating array temperature measurements

• Sanzhar Korganbayev

    SEE PRESENTATION

Towards temperature-controlled laser ablation based on fiber Bragg grating array temperature measurements

×

ABSTRACT

In this paper we present a temperature-controlled laser ablation technique based on fiber Bragg grating (FBG) array temperature measurements. Highly dense FBG array with 0.9 mm-long gratings was specially fabricated with the femtosecond point-by-point writing technology to have the high spatial resolution needed for accurate temperature profile measurements during laser ablation. Real-time temperature monitoring was used for laser power regulation based on ONOFF control logic to maintain stable peak temperature during ablation. Two temperature thresholds and two comparison times dt were set: 43 and 48 °C, and 1 and 2.5 s, respectively. The outcomes of these settings were evaluated in terms of temperature distribution in an ex vivo porcine liver undergoing laser ablation. Results show that the proposed use of FBG array for controlled ablation provides several advantages over regulation with traditional thermometers.

PRESENTER

Sanzhar Korganbayev
Politecnico di Milano, Italy

See Presentation Close

A wearable system for knee flexion/extension monitoring: design and assessment

• Daniela Lo Presti

    SEE PRESENTATION

A wearable system for knee flexion/extension monitoring: design and assessment

×

ABSTRACT

Human gait is a significant health indicator used in a wide range of applications, including diagnosis, monitoring, rehabilitation, and sport. Among all the human joints movements, the knee flexion/extension is a crucial movement, and its evaluation may provide valuable information related to pathologies, walking disorders, to evaluate the efficiency of prescribed therapies and the rehabilitation of patients, and to improve performances of athletes. In this work, we designed, fabricated, and tested a wearable system (i.e., an instrumented knee brace) for monitoring knee movements under static and dynamic conditions. The system consists of a single fiber Bragg grating (FBG) sensor encapsulated in a soft and flexible polymer matrix in contact with the knee brace.

PRESENTER

Daniela Lo Presti
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

A non-invasive system for epidural space detection: comparison with Compuflo®

• Riccardo Sabbadini

    SEE PRESENTATION

A non-invasive system for epidural space detection: comparison with Compuflo®

×

ABSTRACT

Epidural blockade is a method often used in clinical practice to obtain pain relief during labor. Basically, the epidural puncture blocks the nerve impulses from the lower spinal segments with a consequent decrease of sensation in the lower half of the body. In this arena, the correct localization of the epidural space is crucial to perform the procedure. The loss of resistance (LOR) technique is the most popular approach to localize the epidural space. The LOR is caused by the fact that the ligamentum flavum is much harder than the epidural space, therefore when the needle tip pierces this ligamentum, there is an abrupt decrease of pressure (known as LOR). Although, there are several commercially available tools to support the clinicians in this task, the large part of epidural punctures is performed without any support. Our group of research has developed a novel and noninvasive tool to detect the LOR during epidural puncture. The aim of this study is to compare the output collected by the proposed system (i.e., the Epidural Space Management Tool, ESMT) with the output provided by a commercial system (i.e., CompuFlo®, Milestone Scientific, Inc.).

PRESENTER

Riccardo Sabbadini
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

Digital Signage by Real-Time Gender Recognition From Face Images

• Antonio Greco

    SEE PRESENTATION

Digital Signage by Real-Time Gender Recognition From Face Images

×

ABSTRACT

Digital signage is a new advertising strategy using smart multimedia screens, which carries out the dynamic customization of the promotional content according to the customers who are looking at the monitor. Gender recognition from face images is among the most popular applications for digital signage, since it allows to select in real-time advertising spots customized for males or females. In this paper, we propose a system which implements this solution using a smart camera mounted above the monitor, dedicated to gender recognition in real-time, and a component that dynamically modifies the content projected on the screen according to the gender of the audience. The computer vision algorithm is designed to be as fast as effective, since the whole processing chain must be performed in real-time in order to avoid missing people passing in front of the screen. We evaluated the performance of the proposed solution on a standard dataset for gender recognition in the wild and in a real fair, obtaining a gender recognition accuracy of 94:99% and 92:70%, respectively, that is very relevant in such unconstrained scenarios. In addition, the method is able to process 5 fps on a smart camera and, thus, it can be used in a digital signage application.

PRESENTER

Antonio Greco
University of Salerno, Italy

See Presentation Close

VITAL-ECG : a de-bias algorithm embedded in a gender-immune device

• Annunziata Paviglianiti

    SEE PRESENTATION

VITAL-ECG : a de-bias algorithm embedded in a gender-immune device

×

ABSTRACT

Artificial intelligence, sensors technology and sensors networks influence people behavior in everyday life. The diffusion of mobile devices, based on Internet of Things (IoT) paradigms, has created specific solutions for applications, in which physical objects are connected to Internet system. Wearable IoT (WIoT) represents a new IoT area, concerning detection, processing and communication capabilities in the field of healthcare. Vital-ECG is a smart device, related to health monitoring, which complies with gender equality. The wearable device takes the form of a smartwatch, which monitors heart activity and the most important vital parameters: blood oxygen saturation, skin temperature and fatigue level. Electrocardiogram and plethysmogram signals are acquired from Vital-ECG, which is able to track the blood pressure values, through a deep learning implementation. The neural algorithm has been implemented avoiding the "Gender Bias". The gender balance in machine learning, especially in biomedical application, is a crucial point to prevent algorithms from making a distorted prediction, disadvantaging women.

PRESENTER

Annunziata Paviglianiti
Politecnico di Torino, Italy

See Presentation Close

Human-Machine Interaction Personalization: a Review on Gender and Emotion Recognition Through Speech Analysis

• Monica La Mura

    SEE PRESENTATION

Human-Machine Interaction Personalization: a Review on Gender and Emotion Recognition Through Speech Analysis

×

ABSTRACT

The increasing spread of pervasive technology has led to the fast development of human-centered connected systems, such as cloud-based voice services, assisted driving systems, domotics control systems, personal digital assistants. The user interacts with these systems by speaking to an artificial intelligence, which interprets the speaker’s requests and takes decision accordingly. In such scenario, the real-time collection of personal information from the speaker’s voice is a keyfunction to develop in order to offer personalized services. Gender is part of the basic information needed to customize the user experience. Furthermore, knowledge about the sex of the speaker also proves useful in automatic speaker recognition and voice-based identity recognition systems, since it restricts the search space to individuals of one gender, thus speeding up the system response. Therefore, gender recognition techniques through speech analysis have largely attracted the researchers’ attention. Speech analysis is usually performed by extracting some features from the speech signal that can be affected by additional factors other than the gender: emotional state of the speaker, for example, is conveyed in the speech by altering some parameters that take part to the gender recognition process. At the same time, the outcome of emotion recognition systems based on speech analysis can be affected by the speaker’s gender. This paper briefly summarizes the techniques used to perform gender recognition through speech analysis and proposes a practice to take gender into account in emotion recognition methods.

PRESENTER

Monica La Mura
University of Salerno, Italy

See Presentation Close

Is Really IoT Technology Gender Neutral?

• Dajana Cassioli

    SEE PRESENTATION

Is Really IoT Technology Gender Neutral?

×

ABSTRACT

Surprisingly, gender aspects are rarely included as fundamental requirements in the design of technology and systems. Actually, the introduction of gender into research will offer new dimensions to technological innovation. False assumptions may derive from gender stereotypes and lead to envisage misleading technological needs. Indeed, user needs, acceptance degree and usage models of technology and systems may differ according to gender and sex variances. In particular, Internet-of-Things technology and services would get new inspirations from exploring the gender dimensions. In this paper, we elaborate on this delicate theme by comparing approaches and solutions that exploit gender diversity vs. gender neutral solutions.

PRESENTER

Dajana Cassioli
University of L'Aquila, Italy + WIE AG IEEE Italy Section

See Presentation Close

Traceablity Chain for Acoustic Sensors Based on the Direct Definition of the Acoustic Pascal by Optical Method

• Wan-Ho Cho

    SEE PRESENTATION

Traceablity Chain for Acoustic Sensors Based on the Direct Definition of the Acoustic Pascal by Optical Method

×

ABSTRACT

A new traceability chain for non-standardized acoustic sensors is proposed by using the absolute measurement method of acoustic pressures. The current traceability chain for sound-in-air measurements is based on the laboratory standard microphone. However, this approach has clear limitations and cannot be applied to non-standard sensors such as MEMS microphones. This is because the unit of sound-in-air measurement is indirectly defined via the sensitivity of laboratory standard microphones. As a method to determine the acoustic pressure in an absolute manner, the optical method based on photon correlation is applied and the new traceability chain is proposed based on the direct traceability of the SI unit. As an example, the calibration of a MEMS microphone is demonstrated with the photon correlation method.

PRESENTER

Wan-Ho Cho
Korea Research Institute of Standards and Science

See Presentation Close

Assuring Measurement Traceability to ATE Systems for MEMS Temperature Sensors Testing and Calibration

• Vito Fernicola

    SEE PRESENTATION

Assuring Measurement Traceability to ATE Systems for MEMS Temperature Sensors Testing and Calibration

×

ABSTRACT

In the framework of an EMPIR joint research project (MET4FoF - Metrology for Factory of Future), a facility is being developed to provide in-situ measurement traceability to next-generation of Automated Test Equipment (ATE) systems used in MEMS temperature sensors testing and calibration. The above measurement traceability concepts are demonstrated in a testbed developed by SPEA in collaboration with INRIM and IPQ. The experimental work comprises both the factory-side implementation and the laboratory-side developments of a special calibration facility, to cover the temperature range between approximately -60 °C and 200 °C.

PRESENTER

Vito Fernicola
INRiM, Italy

See Presentation Close

A reliable sampling method to reduce large sets of measurements: a case study on the calibration of digital 3-axis MEMS accelerometers

• Andrea Prato

    SEE PRESENTATION

A reliable sampling method to reduce large sets of measurements: a case study on the calibration of digital 3-axis MEMS accelerometers

×

ABSTRACT

The large-scale production of digital sensors, based on MEMS/NEMS technology, and the increasingly widespread use in many surveys and innovative applications, such as smart manufacturing and Industry 4.0, poses new metrological challenges for the characterization of their technological performance. In fact, in specific applications, where measurement reliability is an essential requirement, it is necessary to have accurate and traceable sensors, therefore actually calibrated. In this work, a recently developed calibration system for digital tri-axial MEMS accelerometers is applied. The calibration procedure allows to simultaneously evaluate the main sensitivities and the transverse sensitivities, based on the single-axis excitation of an inclined plane, on which the sensor under calibration is fixed. In order to verify the effectiveness of the calibration system in dynamic conditions (from 5 Hz to 3000 Hz), 48 different configurations are explored, in order to exclude correlations between the independent variables; therefore, on the basis of a reliable sampling method, it is possible to reduce the calibration procedure to only 4 configurations, providing the values of main sensitivity and transverse sensitivity of the sensor, in compliance with the values obtained from the 48 configurations.

PRESENTER

Andrea Prato
INRiM, Italy

See Presentation Close

Calibration of digital 3-axis MEMS accelerometers: A double-blind «multi-bilateral» comparison

• Alessandro Schiavi

    SEE PRESENTATION

Calibration of digital 3-axis MEMS accelerometers: A double-blind «multi-bilateral» comparison

×

ABSTRACT

Nowadays, digital sensors based on MEMS/NEMS technology, are produced in very huge quantities by manufacturers. Beyond typical applications, e.g., in the predominant market of smartphones, these sensors began to be largely used in a wide range of monitoring systems and survey, in applied engineering and in advanced application, such as Internet of Things (IoT) and Industry 4.0. In these technological applications, accuracy and reliability of digital MEMS sensors, are emerging quality attributes of interest, allowing to improve, in general terms, the management of processes under investigation, on the basis of high data quality. On the other hand, quality of measurements data depends on a specific metrological characterization, in terms of traceability and accuracy. Although some methods and procedures for the digital MEMS sensors calibration, as well as proper sensitivity parameters for digital output, are nowadays available, it is not possible to calibrate every single device, but it is necessary to define suitable protocols of sampling, in order to deliver statistically acceptable levels of performance and reliability while reducing manufacturing costs. In this paper a doubleblind «multi-bilateral» comparison on large-sample scale of 25 digital MEMS accelerometers calibration data, is carried out and results are discussed.

PRESENTER

Alessandro Schiavi
INRiM, Italy

See Presentation Close

Big Data management: A Vibration Monitoring point of view

• Alessandro Paolo Daga

    SEE PRESENTATION

Big Data management: A Vibration Monitoring point of view

×

ABSTRACT

Vibration Monitoring is a particular kind of Condition Monitoring meant to infer the state of health of a machine from accelerometric measurements. From a practical point of view, the scope is then to extract from the acceleration data some valuable diagnostic information which could be used to detect the presence of possible damages (i.e., to produce knowledge about the state of health). When the monitoring is implemented online, in a continuous way, the raw accelerometric data sets can be very large and complex to be dealt with, as usually involve multiple channels (i.e., multiple locations and directions) and high sample rates (i.e., order of ksps - 103 samples per second), but the final knowledge about the state of health can, in principle, be summarized by a single binary information (i.e., healthy – 0 vs damaged – 1). This is commonly called Damage Detection. In this work, the big data management challenge is tackled from the point of view of statistical signal processing, so as to aggregate the multivariate data and condense them into single information of distance with respect to a healthy reference condition (i.e., the Novelty). When confounding influences (such as the work condition or the environmental condition) can be disregarded, the novelty information has a direct correspondence to the health information, so that an alarm indicating the detection of damage can be triggered upon exceeding a selected threshold for the limit novelty. Many different ways of solving such a binary classification problem can be found in the literature. Starting from the simplest, some of the more effective are compared in the present analysis, to finally select a reliable procedure for the big data management in vibration monitoring.

PRESENTER

Alessandro Paolo Daga
Politecnico di Torino, Italy

See Presentation Close

Uncertainty Evaluation for Metrologically Redundant Industrial Sensor Networks

• Gertjan Kok

    SEE PRESENTATION

Uncertainty Evaluation for Metrologically Redundant Industrial Sensor Networks

×

ABSTRACT

Sensor networks are ubiquitous in Industry 4.0 environments. Large volumes of data are being produced and need to be processed. If some form of metrological redundancy is present in the network, the question arises how this redundancy can be used to identify and reject possibly faulty sensors and/ or to reduce the measurement uncertainty of the estimate of the measurand. This paper will address these questions. An algorithm, called the LCSS algorithm, will be presented that can be used to identify sensor values that are metrologically of questionable quality and that can identify a largest subset of consistent sensor values. The algorithm will be illustrated on a real dataset produced by an industrial test environment at ZeMA.

PRESENTER

Gertjan Kok
VSL, The Netherlands

See Presentation Close

A Bayesian approach to account for timing effects in industrial sensor networks

• Liam Wright

    SEE PRESENTATION

A Bayesian approach to account for timing effects in industrial sensor networks

×

ABSTRACT

Smart sensors are a key driver of Industry 4.0 and can be harnessed to bring about efficiency and ensure quality in manufacturing. Many industrial sensor measurements relate to dynamical systems that evolve over time. It is critical, especially for spatially distributed sensors, to work on a common timescale which could be achieved through traceability to UTC for instance. Sensor data can also be affected by timing errors such as jitter, and noise in the measured signal. Pre-processing the sensor signals can remove these effects of jitter and noise. This paper describes a Bayesian approach for removing the effects of jitter and noise, resulting in an estimate of the true signal along with its associated uncertainty. This pre-processed signal can then be used to make decisions in industrial settings with a degree of confidence dictated by the uncertainty associated with the estimated signal. A Metropolis-Hastings algorithm is used to sample from the posterior distribution of model parameters and inferences are made based on these posterior samples. The Bayesian framework is illustrated on some simulated data.

PRESENTER

Liam Wright
National Physical Laboratory, UK

See Presentation Close

Uncertainty in Data Analysis for STRATH Testbed

• Yuhui Luo

    SEE PRESENTATION

Uncertainty in Data Analysis for STRATH Testbed

×

ABSTRACT

In this paper, we study the problem of process optimisation, exemplified by a testbed concerned with radial forging of parts, henceforth called the STRATH testbed. A total of 81 parts have been forged for the test. The forging process has been recorded with 99 sensors. Given these time series observations, the aim of the study is to predict or classify the dimensional variations of manufactured metal parts. Classification for STRATH testbed is challenging. This is because not only there are very limited number of completed parts in current dataset, but also the dimensions of parts are all within the tolerance range. Meanwhile, the dimensional data does not have clear cluster structure. However, despite the disadvantage stated above, STRATH testbed still serves as a good example for demonstrating the treatment of uncertainty as part of the data analysis for such problems. It shows that uncertainty is essential and valuable in all stages of signal processing and uncertainty can be propagated down the signal processing chain.

PRESENTER

Yuhui Luo
National Physical Laboratory, UK

See Presentation Close

Uncertainty of the Classification Result from a Linear Discriminant Analysis

• Yuhui Luo

    SEE PRESENTATION

Uncertainty of the Classification Result from a Linear Discriminant Analysis

×

ABSTRACT

Due to its simplicity and the ability for dimensional reduction, linear discriminant analysis (LDA) is considered as a classical classification algorithm and has been applied in many applications. Its properties and performance under various circumstances have been well studied in literature. However, for a new data input, although the algorithm is able to provide a decision about which class the new data most likely belongs, no information about the quality of the result is provided. This information is of great importance, especially for data in the boundary region where the result is more likely altered, or in the situation when multiple classification results disagree. In this paper, a statistical method of bootstrap sampling is applied for the purpose of providing an uncertainty for the result from the LDA algorithm. Using Bayesian inference, uncertainty associated with the posteriori probability of the classification result is derived. Numerical simulations are performed to demonstrate our analysis and to show the effectiveness of our proposed method.

PRESENTER

Yuhui Luo
National Physical Laboratory, UK

See Presentation Close

Bayesian Autoencoders for Drift Detection in Industrial Environments

• Bang Xiang Yong

    SEE PRESENTATION

Bayesian Autoencoders for Drift Detection in Industrial Environments

×

ABSTRACT

Autoencoders are unsupervised models which have been used for detecting anomalies in multi-sensor environments. A typical use includes training a predictive model with data from sensors operating under normal conditions and using the model to detect anomalies. Anomalies can come either from real changes in the environment (real drift) or from faulty sensory devices (virtual drift); however, the use of Autoencoders to distinguish between different anomalies has not yet been considered. To this end, we first propose the development of Bayesian Autoencoders to quantify epistemic and aleatoric uncertainties. We then test the Bayesian Autoencoder using a real-world industrial dataset for hydraulic condition monitoring. The system is injected with noise and drifts, and we have found the epistemic uncertainty to be less sensitive to sensor perturbations as compared to the reconstruction loss. By observing the reconstructed signals with the uncertainties, we gain interpretable insights, and these uncertainties offer a potential avenue for distinguishing real and virtual drifts.

PRESENTER

Bang Xiang Yong
University of Cambridge, UK

See Presentation Close

From dynamic measurement uncertainty to the Internet of Things and Industry 4.0

• Sascha Eichstädt

    SEE PRESENTATION

From dynamic measurement uncertainty to the Internet of Things and Industry 4.0

×

ABSTRACT

Evaluation of measurement uncertainty is at the core of metrology and with the Guide to the Expression of Uncertainty in Measurement (GUM) a widely accepted quasistandard is available. Analysis of time-dependent, i.e. dynamic, measurements has gained interest and relevance in metrology in the last two decades. With the rapid evolvement of the Internet of Things (IoT) and Industry 4.0, this development has gained much more importance. This contribution lays out the foundations of dynamic measurement uncertainty and their evolution to uncertainties in the IoT. The topics covered in this contribution are by no means complete, but intend to provide an introduction to the relevance of work carried out for dynamic measurements in the context of IoT and Industry 4.0.

PRESENTER

Sascha Eichstädt
Physikalisch-Technische Bundesanstalt, Germany

See Presentation Close

Stochastic approach for controllable measurement uncertainty in Industry 4.0 applications

• Marjan Urekar1

    SEE PRESENTATION

Stochastic approach for controllable measurement uncertainty in Industry 4.0 applications

×

ABSTRACT

Increasing demands for measurement instrumentation, based on standard sampling with analog-todigital converters in Industry 4.0 applications, like: high precision, high accuracy, low uncertainty, low power consumption, high reliability and low cost, are resulting in unavoidable tradeoffs. A novel and radically different approach – stochastic digital measurement method, is used to meet all of the former demands in a single solution. Using lowresolution converters made with high-speed voltage comparators, with added stochastic dithering signal for reducing measurement error, enables simple, robust, yet high precision solution, able to operate at high sampling frequencies. The main feature of this solution is rather unique – measurement uncertainty is determined by the length of the time period over which the input is measured, and gives the user full control over the desired level of measurement error by varying the period of measurement. This eliminates the need for many different hardware solutions with different grades of measurement errors, with a single instrument able to perform either at laboratory standard level of precision, or with higher levels of error but with ability to perform a large number multi-channel measurements at high speed, all at low cost and high reliability, thanks to the simple hardware. This solution enables drop-in replacement of the existing analog and digital equipment, and a smart upgrade in Industry 4.0 systems. An example of practical prototype is given, the stochastic smart grid meter with uncertainty level of 0.0080 % for voltage and current measurements. With appropriate sensor and transducer, almost any quantity could be measured with high accuracy and benefits of compatibility with Industrial Internet of Things.

PRESENTER

Marjan Urekar1
University of Novi Sad, Serbia

See Presentation Close

AWC C. elegans neuron: a biological sensor model

• Martina Nicoletti

    SEE PRESENTATION

AWC C. elegans neuron: a biological sensor model

×

ABSTRACT

AWC sensory neurons of the nematode Caenorhabditis elegans are capable of detecting a wide variety of volatile compounds, as well as electric fields and temperature. In this work we present a detailed biophysical model of the neuron response to odor stimuli. Our model couples the intracellular transduction pathway to the electrical activity, giving a comprehensive view of the neuron functioning. This work represents a fist attempt for the realistic modeling of the stimulus-response coupling to be used for deep investigation of sensing function in C. elegans.

PRESENTER

Martina Nicoletti
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

Optical CO2 detectors for smart packaging of food in modified atmosphere

• Anna Sabatini

    SEE PRESENTATION

Optical CO2 detectors for smart packaging of food in modified atmosphere

×

ABSTRACT

In the last decades, thanks to the significant application of the newest technologies applied to food production and considering consumer’s awareness with respect to food safety and quality, food industry is hardly working on smart packaging, with the aim of finding out a monitoring strategy which does not require package opening. Here an optical indicator is presented, based on an agarose gel containing anthocyanins, which turns in colour as a result of the deterioration of the packaged food. The colour change has been assessed via digital microscope but also verified with a smartphone: this last method opens the way to a wide application of the indicator down to each consumer via a sensor network modality based on the IoT approach. The sensors respond to percentages of carbon dioxide usually used in the modified atmospheres of foods, such as cured meats, making them, therefore, usable as intelligent packaging able to assess their state of deterioration.

PRESENTER

Anna Sabatini
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

Chinese Sign Language Alphabet Recognition Based On Random Forest Algorithm

• Yuan Wang

    SEE PRESENTATION

Chinese Sign Language Alphabet Recognition Based On Random Forest Algorithm

×

ABSTRACT

Sign language is the language deaf-mute people use to communicate with each other. While people with normal hearing generally can not understand it. Sign language recognition allows hard of hearing people to communicate with general society. In this study, we utilized surface Electromyography (sEMG) to recognize Chinese Sign Language alphabet which is an important part of Chinese Sign Language and recognizing them accurately is critical. For this purpose we attached 8 sEMG sensors on the right forearm of the subjects and collected sEMG signal when they were performing all the 30 alphabet letters. Random forest algorithm was used to classify the data after filtering and feature extraction process. Experimental results showed that random forest algorithm achieved an average recognition rate of 95.48% which was higher than Artificial Neural Networks (ANN) and Support Vector Machine (SVM) and had a more stable performance.

PRESENTER

Yuan Wang
Chinese Academy of Sciences, China

See Presentation Close

A Pilot Study on Auditory Brainstem Response Evoked with Randomized Stimulation Rate

• Xin Wang

    SEE PRESENTATION

A Pilot Study on Auditory Brainstem Response Evoked with Randomized Stimulation Rate

×

ABSTRACT

Comparing with pure tone audiometry which is recognized as the gold standard in clinical hearing assessments, auditory brainstem response (ABR) that is a kind of electric brain activity evoked by acoustic stimuli can achieve objective hearing screening without the needs of patients’ response. However, the traditionally used click approach generates relatively poor ABR waveforms for high stimulation rates, due to the contamination of the auditory evoked potentials (AEP) during the averaging of epochs. To resolve this issue, this study proposed a randomized stimulate rate (RSR) method to mitigate interferences from AEP via the introduction of a random interval between two consecutive stimuli. The performance of the method was compared with the commonly used fixed-rate method and the swept tone method. Results showed that the ABR waveform of the proposed method was rather consistent with that of the commonly applied fixed-rate click method for low stimulation rate, but showed significantly better waveform differentiation for high stimulation rate. Moreover, the proposed RSR method showed comparable performance when compared with the swept tone method under different stimulus levels. The findings of this study would potentially improve the reliability of the existing methods to aid a more accurate hearing loss screening and diagnosis.

PRESENTER

Xin Wang
Chinese Academy of Sciences, China

See Presentation Close

The Effects of Electrode Locations on Silent Speech Recognition using High-density sEMG

• Shixiong Chen

    SEE PRESENTATION

The Effects of Electrode Locations on Silent Speech Recognition using High-density sEMG

×

ABSTRACT

In circumstances when silent speech is necessary, it is an attractive technology to use the surface electromyography (sEMG) signals recorded from electrodes placed on the face and neck regions for automatic speech recognition. For this technology, the electrode location is an important factor for the performance of speech recognition. However, it remains unclear how the electrode positions affect the performance, so there is no guideline for electrode placement in practical applications. Thus, the method of high-density sEMG was proposed to record sEMG signals from four electrode arrays over the facial and neck muscles. The high-density sEMG signals were utilized to analyze the effects of the electrode locations on the classification accuracies when increasing the category number of speaking tasks. The results showed that the increase in category numbers of speaking tasks would lead to the decline of classification accuracies, no matter which of the four electrode arrays were used. Meanwhile, the declining rates were the highest when using signals from the face electrodes (F-40ch), while those were the lowest when using the neck electrodes (NO-40ch and NE-40ch). There was no significant difference in the accuracies between the cases of the NO-40ch and NE-40ch electrodes. The findings indicated that the muscles on the neck region might be a more important contributor for automatic silent speech recognition. The study might provide new clues and guidelines for electrode placement when using sEMG for automatic silent speech recognition, which is important to develop a practical communication system for dysphonia.

PRESENTER

Shixiong Chen
Chinese Academy of Sciences, China

See Presentation Close

The Performance Evaluation of SSVEP-BCI Actuated Wheelchair with Parameter Setting of Time-Window Length and Stimulation Layout

• Jun Xie

    SEE PRESENTATION

The Performance Evaluation of SSVEP-BCI Actuated Wheelchair with Parameter Setting of Time-Window Length and Stimulation Layout

×

ABSTRACT

Due to the advantages of prominent brain responses, less training duration, and robustness to artifacts, steady-state visual evoked potential (SSVEP) based braincomputer interface (BCI) has been recently applied to intelligent wheelchair navigation. Recent researches mainly focused on the implementation of a specific recognition method to analyze the wheelchair navigation performance under fixed stimulation target number. The navigation performance evaluation under different recognition methods and different BCI target numbers is rarely compared. In this paper, the navigation performance comparison between different numbers of stimulation targets and different recognition methods was carried out. The multichannel integrated GT2circ and canonical correlation analysis (CCA) recognition methods were used to compare the wheelchair navigation performance under different timewindow (TW) lengths. And the 3-target and 4-target arrangement layouts were adopted to compare the navigation performance between the “No feedback” and the “Feedback” conditions. Experimental results showed that the GT2circ recognition method with TW length of 2 s would promote the navigation efficiency and different stimulation target number could be tailored for different wheelchair application purposes, which would bring tutorial instructions to the applicable navigation of the BCI-actuated wheelchair.

PRESENTER

Jun Xie
Xi'an Jiaotong University

See Presentation Close

A New Approach for Hand Gesture Recognition Based on the Fusion of sEMG and Impedance Information

• Yuan Wang

    SEE PRESENTATION

A New Approach for Hand Gesture Recognition Based on the Fusion of sEMG and Impedance Information

×

ABSTRACT

Surface electromyogram (sEMG) signals associated with multiple patterns of hand gestures is commonly used as input for prosthetic control. However, placing a relatively large number of sEMG sensors on the residual limb of the amputees, particularly via the prosthetic cavity constitute a major challenge. In this article, a new acquisition system that integrates fewer electrodes is developed to acquire high-quality physiological information for adequate recognition of various hand gestures. The developed system utilizes the characteristics of the chip and special circuit design to enable simultaneous acquisition of sEMG signal and hybrid-impedance (HI) signal from a pair of differential electrodes. The results obtained based on the recordings from 10 subjects indicate that adding impedance information increases the sEMG recognition rate of hand gesture with fewer electrodes. This study might provide a new solution for achieving high-precision of the hand gesture recognition with fewer electrodes.

PRESENTER

Yuan Wang
Chinese Academy of Sciences, China

See Presentation Close

A Smart Solution for Proprioceptive Rehabilitation through M-IMU Sensors

• Martina Lapresa

    SEE PRESENTATION

A Smart Solution for Proprioceptive Rehabilitation through M-IMU Sensors

×

ABSTRACT

The decrease of proprioception is a common consequence of neuromuscular and musculoskeletal diseases, and a rehabilitation treatment is needed to recover proprioceptive abilities. Many studies demonstrate that biofeedback training of sensory-motor functions can improve the outcome of rehabilitation. The combined use of biofeedback, wearable sensors and Internet of Things represents a very useful solution to develop smart wearable devices to be used for augmenting rehabilitation, both in clinics and at home. This paper proposes and validates a smart and easy-to-use system for proprioceptive training, which provides biofeedback to the patient thanks to a customdesigned Virtual Reality game. Attention is paid to reduce the complexity of the system and the amount of data to be exchanged for controlling the game and to be stored for assessing the patient’s progresses, still ensuring the effectiveness of the system to monitor the patient also in home-rehabilitation scenarios. The system was experimentally validated on 8 healthy subjects and the obtained results demonstrated that the Virtual Reality game is easy and intuitive, as confirmed by the high performance of the subjects (success rate > 90%), and that allows training different features of limb proprioception.

PRESENTER

Martina Lapresa
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

IoT Gateways for Industrial and Medical Applications: Architecture and Performance Assessment

• Luca Vollero

    SEE PRESENTATION

IoT Gateways for Industrial and Medical Applications: Architecture and Performance Assessment

×

ABSTRACT

The goal of the Internet of Things is to enable the connection of objects to the Internet, making it possible new paradigms and applications for humans and machines. Typical architecture of IoT systems relies on cloud services: simple sensors and actuators entrust to cloud intelligence for data analysis and action planning. The significant number of devices, the throughput requirements of data flows and latencydemanding applications impose today new paradigms as decentralized computing based on gateways. In this paper, we present a general gateway architecture and evaluate its performance in managing routine tasks of IoT applications. The architecture enables decentralized intelligence and distributed computing, and it introduces a low computational burden. These aspects, with the flexibility of the proposed architecture, make it a promising solution in typical IoT applications.

PRESENTER

Luca Vollero
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

Efficient Classification of Motor Imagery using Particle Swarm Optimization-based Neural Network for IoT Applications

• Oluwagbenga Paul Idowu

    SEE PRESENTATION

Efficient Classification of Motor Imagery using Particle Swarm Optimization-based Neural Network for IoT Applications

×

ABSTRACT

The Internet of Things (IoT) has found wide applications in human endeavors, and has recently drawn massive attention in the field of cognitive science by connecting the Brain-Computer Interface (BCI) to the cloud. The integration of EEG-based BCI with internet is rapidly developing due to its non-invasiveness, and the benefits are inexhaustible such as control of assistive robots, telemedicine and telehealth for secured monitoring. However, some challenges exist which would prevent the application of BCIs, including the accurately predicting movement intention from EEG signals, computational complexity while preprocessing EEG tasks, and the problem of overfitting. Several algorithms have been used to address these challenges, but they are still limited to be applied efficiently on the BCI-based IoT. In this paper, in order to tackle the above mentioned issues, we proposed an extended Particle Swarm Optimization (PSO)-based neural network (NN) which is able to provide a seamless interaction between the BCI and IoT devices. In the experiments, we designed a BCI system that captured relevant EEG information by means of the PSO, and then projected the features into a neural network system for training. The experimental results demonstrated the feasibility of the proposed PSO-based NN technique in classifying the motor imagery (MI) tasks with an accuracy of 98.9%. Some possible improvement in future work was also suggested.

PRESENTER

Oluwagbenga Paul Idowu
Chinese Academy of Sciences, China

See Presentation Close

An Automatic Battery Recharge and Condition Monitoring System for Autonomous Drones

• Elia Landi

    SEE PRESENTATION

An Automatic Battery Recharge and Condition Monitoring System for Autonomous Drones

×

ABSTRACT

The use of drones and unmanned aerial vehicles for monitoring infrastructures to guarantee safety and security is day by day more important. The possibility of a complete autonomous system for this kind of applications, in which drones can accomplish tasks 24 hours a day, seven days a week, without human intervention, is becoming a realistic scenario. From this standpoint a challenging issue is the automatic dronebatteries recharging and condition monitoring. In this article the authors present the solution adopted in a prototype drone hangar, able to manage up to 4 independent drones, that was developed with the support of the Italian Railway System (RFI).

PRESENTER

Elia Landi
University of Siena, Italy

See Presentation Close

A New Class of Chaotic Sources in Programmable Logic Devices

• Riccardo Moretti

    SEE PRESENTATION

A New Class of Chaotic Sources in Programmable Logic Devices

×

ABSTRACT

We introduce a new method for the design of information entropy sources in Programmable Logic Devices (PLDs), based on a novel class of circuits called Digital Nonlinear Oscillators (DNOs) supporting complex dynamics, including chaos. Following this method, we designed a fully digital entropy source, i.e. entirely described in VHDL. The solution has been implemented on a Xilinx FPGA, showing, according to some tuning, periodic and chaotic behaviors.

PRESENTER

Riccardo Moretti
University of Siena, Italy

See Presentation Close

A Characterization System for Bearing Condition Monitoring Sensors, a Case Study with a Low Power Wireless Triaxial MEMS Based Sensor

• Lorenzo Parri

    SEE PRESENTATION

A Characterization System for Bearing Condition Monitoring Sensors, a Case Study with a Low Power Wireless Triaxial MEMS Based Sensor

×

ABSTRACT

In this work the authors present an ad hoc characterization system able to emulate vibration signatures related to various typical rotating machinery failures. In particular, the proposed system is aimed at testing distributed condition monitoring systems based on vibration measurements with MEMS accelerometers. The system, fully programmable, embeds a reference triaxial piezoelectric transducer, which provides reference measurements. The system has been applied, as a case study, to the test of a developed standalone low power triaxial MEMS based accelerometer node sensor for IoT applications for bearing faults diagnosis.

PRESENTER

Lorenzo Parri
University of Siena, Italy

See Presentation Close

Design of a robotic platform for landmine detection based on Industry 4.0 paradigm with data sensors integration

• Luca Bossi

    SEE PRESENTATION

Design of a robotic platform for landmine detection based on Industry 4.0 paradigm with data sensors integration

×

ABSTRACT

A new generation of instruments capable of detecting plastic landmines aims to increase operator safety and productivity for humanitarian demining. The complex environmental conditions require the measurements of several physical parameters to enhance the detection of plastic and metal landmines by metal detectors and ground penetrating radars mounted on a robotic platform. The architecture of the multisensor robotic platform, based on the Industry 4.0 paradigm, is described, and an example is provided which describes how to exploit the multiple sensor information with experiments carried out in a test bed with landmine simulants.

PRESENTER

Luca Bossi
Università degli Studi di Firenze

See Presentation Close

Sensors and Algorithm Evaluation for Tripwire Detection in the Landmine Detection 4.0 Project

• Jonathon Sinton

    SEE PRESENTATION

Sensors and Algorithm Evaluation for Tripwire Detection in the Landmine Detection 4.0 Project

×

ABSTRACT

This paper covers advances made in the tripwire detection aspect of the Landmine Detection 4.0 project. This includes algorithmic improvements - most importantly a comparison between a gradient-sigmoid filter and a derivative subtraction filter - and testing of these algorithms on tripwire scenes. We used a Canon DSLR camera for testing, which provides higher resolution and a different spectral range than the FLIR thermal camera we had used in previous testing. We have also begun investigating the use of near-infrared cameras as a possible alternative. Additionally, we have investigated methods to reduce false-positive detections within images with the intention to implement and test some of these methods in the near future.

PRESENTER

Jonathon Sinton
Franklin and Marshall College, USA

See Presentation Close

Interoperability among Sub-GHz Technologies for Metallic Assets Tracking and Monitoring

• Gabriele Di Renzone

    SEE PRESENTATION

Interoperability among Sub-GHz Technologies for Metallic Assets Tracking and Monitoring

×

ABSTRACT

This paper focuses on a prototype of an Internet of Things (IoT) system for the tracking and monitoring of intermodal containers throughout their whole shipment which may include heterogeneous methods (e.g., road transport and sea transport). The system accounts for a couple of devices for each container. The former is a sensor node placed on the inner surface of the container and it is in charge of monitoring the state of the shipped goods by sampling endo-container environmental parameters (i.e., temperature, moisture and air pressure). Such measurements are wirelessly sent outside the container by exploiting the Amplitude Shift Keying (ASK) modulation over a 433 MHz carrier. The other device is mounted on the outer surface of the container just above the inside one. This receives the data broadcast from the sensor node and forwards such information to a cloud service by making use of Sigfox technology. In so doing, a twofold scope is achieved: remote monitoring of goods since each Sigfox packet carries the aforementioned air related parameters and tracking of the containers. Indeed, Sigfox gateways also collect metadata of the received packets (e.g., timestamp, Received Signal Strength Indicator (RSSI)) on which trilateration algorithms and probabilistic calculations are applied by Sigfox cloud. Tests results proved the system capability of integrating different Sub-GHz technologies within the same application along with its effectiveness in retrieving any sort of measured data from sealed containers or from analogous metallic assets.

PRESENTER

Gabriele Di Renzone
University of Siena, Italy

See Presentation Close

Low-cost, robust gravimetric system for enhanced security of accesses to public places

• Matteo Intravaia

    SEE PRESENTATION

Low-cost, robust gravimetric system for enhanced security of accesses to public places

×

ABSTRACT

This paper describes a novel application of a tailored robust and low-cost gravimetric system for access control purposes in public spaces. The aim of the proposed device is to detect the abnormalities in the passage of people (multiple persons passing together) and, on the other hand, to recognize useful events for physical security control activities (e.g. person with stroller or trolley). The proposed system consists of a gravimetric system based on a small number of load cells, of the front-end electronics, and of data acquisition and processing hardware and software. The proposed system performs a low-level signal processing, which exploits the basic equations of statics, to obtain information on the walkthrough trajectory, and a high-level statistical processing to classify in real time different events. The results are encouraging, showing a very high detectability of the irregularities, 100% of the tested cases, and a satisfactory recognition of the other event types.

PRESENTER

Matteo Intravaia
University of Siena, Italy

See Presentation Close

Virtual Sensors: a Tool to Improve Reliability

• Loredana Cristaldi

    SEE PRESENTATION

Virtual Sensors: a Tool to Improve Reliability

×

ABSTRACT

Virtual sensors is a powerful concept applicable in new application domain like health-care, entertainment, fitness, sport, social interaction etc. tanks its capability of integration of new components and functionality. Actually, virtual sensors can potentially use heterogeneous physical sensors in order to combine different types of data to compute a measurement. The concept “virtual Sensor" allows to apply the principle so-called analytical redundancy. This point is important because it allows to also achieving the objective of extending reliability and availability of the application domain without adding extra hardware complexity. Starting from the previous consideration, Virtual Sensors (VS) can be candidate to offer a solution to reduce the criticality of high-risk failures increasing their detectability and predicting the related failure mode. VS and the validation procedure in the measurement process allowed by their use, offer a new tool in the Industry 4.0 scenario. In the paper, an example of virtual sensor devoted to monitoring different sections of an inverter dedicated to photovoltaic application will be analyzed. In particular, will be shown how it is possible to monitor the temperature of the CPU employed on the control board.

PRESENTER

Loredana Cristaldi
Politecnico di Milano, Italy

See Presentation Close

RADON Project: From Children's Game To Intelligent Personal Dosimeter

• Marina Popolizio

    SEE PRESENTATION

RADON Project: From Children's Game To Intelligent Personal Dosimeter

×

ABSTRACT

Aim of this work is to present some relevant results of the Radon Project, relating to the design of innovative systems to increase public interest in the effects of radon gas on human health. The communication of complex phenomena has required the development of specific interfaces in relation to users’ characteristics. The innovative systems include: 1) an interactive board game for children to be used in schools 2) an app acting as a virtual sensor for ionizing particles for non-expert adults 3) a low-cost IoT based node using a solid-state sensor for radon monitoring.

PRESENTER

Marina Popolizio
Politecnico di Bari, Italy

See Presentation Close

Proof-of-Concept Millimeter-Wave Free-Space Nondestructive Testing Implemented on Collaborative Mobile Robots

• Bilal Daass

    SEE PRESENTATION

Proof-of-Concept Millimeter-Wave Free-Space Nondestructive Testing Implemented on Collaborative Mobile Robots

×

ABSTRACT

A proof-of-concept nondestructive testing and Evaluation (NDT&E) technique using millimeter-wave electromagnetic sensing is proposed. The method is based on a free-space millimeter-wave characterization instrumentation interfaced with collaborative mobile robots. In particular, 60 GHz emitter and scalar transceiver are mounted on two mobile robots controlled and positioned on either side of the structure under investigation. Planar dielectric materials are preliminary characterized to demonstrate the viability of the proposed approach. This feasibility study is beneficial for future investigation devoted to the implementation of vector measurement instrumentation on the robotic platform.

PRESENTER

Bilal Daass
University of Lille, France

See Presentation Close

Interaction Force Computation Exploiting Environment Stiffness Estimation for Sensorless Robot Applications

• Loris Roveda

    SEE PRESENTATION

Interaction Force Computation Exploiting Environment Stiffness Estimation for Sensorless Robot Applications

×

ABSTRACT

Industrial robots are increasingly used to perform tasks requiring an interaction with the surrounding environment. However, standard controllers require force/torque measurements to close the loop. Most of the industrial manipulators do not have embedded force/torque sensor(s), requiring additional efforts (i.e., additional costs and implementation resources) for such integration in the robotic setup. To extend the use of compliant controllers to sensorless force control, a model-based methodology is presented in this paper. Relying on sensorless Cartesian impedance control, an Extended Kalman Filter (EKF) is proposed to estimate the interaction environment stiffness. Exploiting such estimation, the interaction force can be computed, e.g., to close the force loop, making the sensorless robot able to perform the target task (e.g., probing task, assembly task). The described approach has been validated with experiments. A Franka EMIKA panda robot has been used as a test platform. A probing task involving different materials (i.e., with different - unknown - stiffness properties) has been considered to show the capabilities of the developed EKF. The computed interaction force (on the basis of the estimated environment stiffness) has been compared with the Franka EMIKA panda robot force measurements to prove the effectiveness of the proposed approach.

PRESENTER

Loris Roveda
SUPSI-IDSIA, Switzerland

See Presentation Close

Tactile sensing with gesture-controlled collaborative robot

• Bozica Bojovic

    SEE PRESENTATION

Tactile sensing with gesture-controlled collaborative robot

×

ABSTRACT

Sensors and human machine interfaces for collaborative robotics will allow smooth interaction in contexts ranging from industry to tele-medicine and rescue. This paper introduces a bidirectional communication system to achieve multisensory telepresence during the gestural control of an industrial robotic arm. Force and motion from the robot are converted in neuromorphic haptic stimuli delivered on the user’s hand through a vibro-tactile glove. Untrained personnel participated in an experimental task benchmarking a pickand- place operation. The robot end-effector was used to sequentially press six buttons, illuminated according to a random sequence, and comparing the tasks executed without and with tactile feedback. The results demonstrated the reliability of the hand tracking strategy developed for controlling the robotic arm, and the effectiveness of a neuronal spiking model for encoding hand displacement and exerted forces in order to promote a fluid embodiment of the haptic interface and control strategy. The main contribution of this paper is in presenting a robotic arm under gesture-based remote control with multisensory telepresence, demonstrating for the first time that a spiking haptic interface can be used to effectively deliver on the skin surface a sequence of stimuli emulating the neural code of the mechanoreceptors beneath.

PRESENTER

Bozica Bojovic
Belgrade University, Serbia

See Presentation Close

A Pneumatic Haptic Display for Collaborative Robotics applications

• Debadrata Sarkar

    SEE PRESENTATION

A Pneumatic Haptic Display for Collaborative Robotics applications

×

ABSTRACT

A pneumatic haptic display for collaborative robotics applications is presented within this paper. The 3x3 tactor array consists of a polymeric parallelepiped with 9 cylindrical chambers (3mm diameter) providing haptic feedback by means of pneumatic actuation. A preliminary study, on four subjects, has been performed to identify the optimal pressure to deliver the tactile stimulation and assess system functionality. Four different spatial stimuli, based on the activation of different chambers of the tactor array, were provided at three different pressure levels (35, 70, 105 kPa). Results suggest that a pressure of 70 kPa leads to a detection accuracy of 96.9%. Further studies will focus on a deeper assessment of the tactile display using different configurations.

PRESENTER

Debadrata Sarkar
National Institute of Technology Durgapur

See Presentation Close

In-Line Quality Control in Semiconductors Production and Availability for Industry 4.0

• Enrico Petritoli

    SEE PRESENTATION

In-Line Quality Control in Semiconductors Production and Availability for Industry 4.0

×

ABSTRACT

This paper exposes a new theoretical approach to in-line quality control that has a healthy effect on the operational availability of the automated production line for industry 4.0. Our philosophy of action is this: through an accurate analysis of the production processes and an appropriate flow of post-product test data (in our case: electronic components), it is possible to correct the quality drift of the product during the production itself without waiting for the lot to run out. All this greatly reduces the line's stop times with evident economic repercussions.

PRESENTER

Enrico Petritoli
Università Roma Tre, Italy

See Presentation Close

An IoT Application for Industry 4.0: a New and Efficient Public Lighting Management Model

• Mariagrazia Leccisi

    SEE PRESENTATION

An IoT Application for Industry 4.0: a New and Efficient Public Lighting Management Model

×

ABSTRACT

Public lighting is one of higher expenditure for municipal administrations, in fact it is an energy-intensive service because of its inefficient functioning and consumption. One of the major problems is the lack of information about the actual state of public lighting systems, which would allow us to know its consumption, costs and performance, safety, compliance with standards and potential for improvement. Lunched by ENEA, PELL project has been developed as operative instrument of the Lumiere project, to improve the development of a new efficient and effective management model for public lighting to help turn urban centers into smart cities. This work describes the main goals of the project and the underlying infrastructure: big data platform, portal and related services provided to end users joining the PELL project directives.

PRESENTER

Mariagrazia Leccisi
Università Roma Tre, Italy

See Presentation Close

Optical Wireless Communication and Li-Fi: a New Infrastructure for Wireless Communication in Saving Energy Era

• Lorenzo Cozzella

    SEE PRESENTATION

Optical Wireless Communication and Li-Fi: a New Infrastructure for Wireless Communication in Saving Energy Era

×

ABSTRACT

Traditional wireless communication methods tend to saturate in terms of data rate, frequency spectrum and reliability. Visible Light Communication (VLC) integrated with the emerging technology of Internet-of-Things (IoT) opens up to a wide range of indoor applications. In this work we will describe the potential of an optical wireless communication infrastructure and we will make a comparison with the emerging 5G and 6G Wi-Fi (RF) technologies.

PRESENTER

Lorenzo Cozzella
Università Roma Tre, Italy

See Presentation Close

Aspect ratio optimization of piezoceramic disks for maximizing electromechanical energy conversion in energy harvesting applications

• Antonio Iula

    SEE PRESENTATION

Aspect ratio optimization of piezoceramic disks for maximizing electromechanical energy conversion in energy harvesting applications

×

ABSTRACT

A wide variety of devices based on piezoceramic elements, vibrating in several modes, have been proposed and developed for energy harvesting applications. The evaluation of the capability of converting mechanical energy into electric energy is a main issue in the device design. In this work, the dependence of the piezoceramic element performances on the aspect ratio, i.e., the ratio between thickness and diameter, is analyzed with the aim of maximizing the energy conversion. To the end, the effective electromechanic coupling factor (keff ), which is a parameter that can be easily measured, is the investigated parameter. Results obtained with analytical and FE models have shown that the higher keff value is obtained when the thickness and the diameter of the piezoceramic element are comparable. A first experimental validation of simulation results is finally provided.

PRESENTER

Antonio Iula
University of Basilicata, Italy

See Presentation Close

Double Perovskite Oxide for Chemical Sensors

• Fabio Zaza

    SEE PRESENTATION

Double Perovskite Oxide for Chemical Sensors

×

ABSTRACT

Chemical sensor technology is useful for monitoring environmental pollutions, controlling sustainable production systems and managing cultural heritage. The most promising devices are resistive sensors based on semiconductor metal oxides sensing materials because of their low cost, high sensitivity and quick response. Even though Perovskite oxides are promising sensing material due to their high thermal and chemical stability, their applicability is limited by their electrical conductivity and, consequently, their working temperature, that has to be high to guarantee a measurable electrical resistance. It is possible to overcame this problem by using an A-site layered ordering double Perovskite oxides, such as (Pr0.5Ba0.5)(Mn0.9Fe0.1)O3 (PBMFO). The alternating layers of Pr+3 and Ba+2 lead to layer-ordered oxygen vacancies by the layer of Pr+3, that is the largest cation. The crystalline structure provide high electrical conductivity. This work is focused to optimize the operating conditions for autocombustion synthesis method in order to have performing sensing material for carbon monoxide.

PRESENTER

Fabio Zaza
ENEA, Italy

See Presentation Close

Ultrasound exposure in a workplace and a potential way to improve its measurement methodology

• Michal Cieslak

    SEE PRESENTATION

Ultrasound exposure in a workplace and a potential way to improve its measurement methodology

×

ABSTRACT

Prolonged exposure to airborne ultrasound in a workplace can have a detrimental influence on worker's wellbeing. Given the large number of industrial machines producing ultrasound, it is of vital importance, and can also be regulated by law, to monitor one’s ultrasound exposure during a normal workday as part of risk assessment in a workplace. However, currently utilized devices exhibit limitations in regard to their operational frequency, as well as their portability (wearability). These limitations have been recognized by the Physikalisch-Technische Bundesanstalt (PTB) and the Institute for Occupational Safety and Health of the German Social Accident Insurance (IFA of DGUV). In this paper, specific requirements, based on national and international standards, for a portable ultrasound exposimeter are discussed. Key elements of such a device are also identified and selected for practical investigation. Two analog to digital converters (ADS127L01 and ADS1672), with the sampling rate covering the ultrasound spectrum up to at least 100 kHz, were tested. They were in turn connected to a readout electronics centered around 180 MHz ARM-based Cortex-M4 microcontroller. Results obtained during tests with purely electrical signals suggest a good potential of these devices to be able to reliably record ultrasonic signals. A new approach to personal ultrasound instrumentation, based on recent developments in the field of microelectronics, is then discussed. Future directions of this work are subsequently indicated, together with its applicability to other research fields.

PRESENTER

Michal Cieslak
Physikalisch-Technische Bundesanstalt, Germany

See Presentation Close

Multiphysics Modeling of a Wearable Sensor for Sweat Rate Measurements

• Jorge Prada

    SEE PRESENTATION

Multiphysics Modeling of a Wearable Sensor for Sweat Rate Measurements

×

ABSTRACT

Innovative wearable devices are allowing the noninvasive and remote collection of physiological signals from the human body. Sweat analysis has gained remarkable interest for the non-invasive determination of electrolytes and metabolites, particularly in athletes. Monitoring of sweat rate is of interest to support measurements concerning sweat composition and to assess the overall water loss due to physical activity. The final aim is to prevent dehydration and keep an optimal balance of electrolytes, which is important for the safety of athletes and to obtain the best possible performances. We speculate that these devices can also be useful for the protection of workers performing heavy physical tasks. The evaporation of sweat from the skin surface, which is essential for thermal regulation in humans, is largely influenced by ambient factors. Depending on the measurement approach, ambient temperature and humidity as well as air flow do not only affect evaporation but also the measurement of sweat rate. This paper presents a multiphysics model describing the effect of air speed and ambient humidity on an open chamber based sweat rate sensor. Results of simulations will allow to optimize the design of the device so that interferences from ambient conditions are minimized.

PRESENTER

Jorge Prada
Università di Pisa, Italy

See Presentation Close

A Test Bench to Assess Systems for Respiratory Monitoring of Workers

• Martina Zaltieri

    SEE PRESENTATION

A Test Bench to Assess Systems for Respiratory Monitoring of Workers

×

ABSTRACT

Safety at work is driving the development of new technological solutions in the era of Industry 4.0. Among others, systems able to monitor physiological parameters are gaining high relevance since such devices have the potential to improve the workers’ safety. In this perspective, the respiratory rate can provide useful information since it is sensitive to many environmental stressors. In this study, we focused on the development of a test bench to assess the performance of a wearable system for respiratory monitoring. The presented system achieves data collection and synchronization from FBG sensors, a reference flowmeter and, an M-IMU unit. In addition, a GUI has been developed in order to guide the volunteer in the execution of selected movements during the experimental session. The proposed system could further facilitate the design and development of solutions for assessing wearables for workers’ activities monitoring.

PRESENTER

Martina Zaltieri
Università Campus Bio-Medico di Roma, Italy

See Presentation Close

A New Smart-Fabric based Body Area Sensor Network for Work Risk Assessment

• Antonio Lanatà

    SEE PRESENTATION

A New Smart-Fabric based Body Area Sensor Network for Work Risk Assessment

×

ABSTRACT

This study reports on a novel Smart-Fabric based wireless Body Area Sensor Network for assessing psychological and physiological work risk levels. The combination of smartsensing fabrics advantages, high electronic miniaturization, and the latest machine learning enables the system to assess the risk level of the worker. The body area sensor network includes a smartphone, an artificial intelligence algorithm for risk assessment, and a set of sensor-nodes integrated into a textile substrate (i.e., activity detection, electrocardiogram (ECG), sweat rate, body temperature, and textile integrated respiration sensors). Preliminary and encouraging results are shown in terms of physiological signals and physical activity detection.

PRESENTER

Antonio Lanatà
University of Florence, Italy

See Presentation Close