Home
IEEE MELECON 2020
MELECON 2020 - 3.3

Technical Session

IEEE Mediterranean Eletrotechnical Conference 2020

IEEE MELECON 2020

CONFERENCE HOME SCHEDULE TRACKS

Conference Track

Session 3.3 - Neural and Cognitive Engineering: Methods and Technological Solutions

JOIN THE LIVE SESSION

To join the Live Session, click on "Join the Live Session" below.

JOIN NOW THE LIVE SESSION

Not Authorized

You don't have privileges to see this content.

Learn more about how to register for an individual account.

GET ACCESS

Please Login

You should be logged in to see this content.

Don't you have an account?
Learn more about how to register for an individual account.

GET ACCESS

PRESENTATIONS
SESSION DETAILS

EEG monitoring during software development

Alessandra Calcagno - Politecnico di Milano, Italy

PREVIEW e-BADGE PRESENTATION

EEG monitoring during software development

ABSTRACT

This paper focuses on the analysis of experienced programmers’ central nervous system response during a software development protocol. The main aim was to explore the neurological mechanisms (i.e., involved brain areas and rhythms) triggered by such a complex task. To do this, a 29-channel EEG signal was acquired on ten experienced programmers during a software development-like exercise. Then, the power spectral density at each EEG channel in standard Delta, Theta, Alpha and Beta bands has been computed and evaluated. The acquired subjects show on average a significant increase of Delta, Theta and Beta powers with respect to the baseline condition. Delta and Theta rhythms increase mostly in the frontal and parieto-occipital regions, while the Beta activity is more diffused. Furthermore, from the statistical analysis it emerged that the power increase in these three bands is significant in different time instants. Moreover, during the programming phase two subjects present a pronounced theta peak in the EEG power spectrum, while other two maintain an alpha peak, even if less pronounced with respect to the baseline condition. These results suggest the need for further investigations. This research is part of the Biofeedback Augmented Software Engineering (BASE) project, which aims at studying programmer’s central and autonomic nervous systems response during the software development activity.

Physiological responses related to pleasant and unpleasant sounds

Paola De Stefano - Politecnico di Milano, Italy

PREVIEW e-BADGE PRESENTATION

Physiological responses related to pleasant and unpleasant sounds

ABSTRACT

Sound is a crucial factor in everyday life, since it impacts on people feelings and reactions to circumstances. Therefore, classifying sounds based on experiential, physiological, and behavioral responses becomes a key factor in the understanding of the relationship between sound and emotions. As reported in the literature, since using a single type of analysis results to be only partially reliable, there is an increasing demand of integration among the various kind of analyses. The aim of this study is to integrate both physiological and self-reported outcomes, in order to provide a more accurate information about the emotions induced by pleasant and unpleasant audio stimuli. In particular, several indices were extracted from physiological signals, which were matched with self-reported outcomes. The results of this study show that cardiac response in terms of sympathetic activation is significantly different for the two types of acoustic artefacts. To further support the physiological responses results, statistical analysis of Loudness, Roughness and Sharpness values was performed. The two types of stimuli seemed to be characterized by significantly different levels of Loudness and Roughness, which were found higher for unpleasant stimuli. Therefore, it is possible to conclude that only one type of measure is not always sufficient to characterize the emotional response to sounds and more than one measure is needed as indicator of listener emotions.

Design and Implementation of Steady State Visual Evoked Potential Based Brain Computer Interface Video Game

Elifsu Filiz - Istanbul Bilgi University, Turkey

PREVIEW e-BADGE PRESENTATION

Design and Implementation of Steady State Visual Evoked Potential Based Brain Computer Interface Video Game

ABSTRACT

Brain Computer Interface (BCI) is a system that enables device control by processing EEG signals acquired from scalp. This system can be used as a communication channel for severely disabled patients as well as other applications for healthy people. In this study, a BCI game was implemented based on classifying steady state visual evoked potentials (SSVEP) that occur in occipital lobe when a subject is exposed to a visual stimulus flickering at a certain frequency using canonical correlation analysis (CCA). In the experiment, the subjects were expected to move a square to specific locations using four visual stimuli with different frequencies. This task could be completed at 1.4 seconds in the best case scenario. The subjects completed this task at 1.4 seconds in the best run, 36.22 seconds in the worst run, and 8.57 seconds in average. The ratio of moves towards target to all moves were calculated as 66.72%. Index Terms—brain computer interface, steady state visual evoked potential, EEG, canonical correlation analysis.

CogAR: an augmented reality App to improve quality of life of the people with cognitive impairment

Mirko Rossi - Sapienza University of Rome, Italy

PREVIEW e-BADGE PRESENTATION

CogAR: an augmented reality App to improve quality of life of the people with cognitive impairment

ABSTRACT

The number of people affected by dementia in the world is growing up due to the shift of the population age profile. This paper presents a tool to help and support people who suffer from both cognitive decline age-related and cognitive impairments. Cognitive impairment refers to a person who has trouble remembering, learning, concentrating, or making decisions that affect their daily life. Cognitive impairment varies from mild to severe. With mild impairment, people may begin to notice changes in cognitive functions, while still be able to do their everyday activities; on the other hand, severe levels of impairment can lead to losing the ability to understand the meaning or importance of something in addition to the ability to talk or write, resulting in the inability to live independently. We developed an augmented reality home-made App, CogAR, designed for smart glasses. The App can be a useful tool able to provide more independence to patients during actual daily living activities and in navigating their home, providing cues for memory integration in real time. In this way, elderly people, could stay at home longer without the need to move into a care home environment.

Neonatal Seizures Detection using Stationary Wavelet Transform and Deep Neural Networks: Preliminary Results

Lorenzo Frassineti - University of Florence, Italy

PREVIEW e-BADGE PRESENTATION

Neonatal Seizures Detection using Stationary Wavelet Transform and Deep Neural Networks: Preliminary Results

ABSTRACT

The increasing use of Electroencephalography (EEG) in the field of pediatric neurology allows more accurate and precise diagnosis of several cerebral pathologies, mainly in Neonatal Intensive Care Units (NICUs), where it represents the gold-standard for the diagnosis of neonatal epileptic seizures. However, EEG interpretation is time consuming and requires highly specialized staff. For this reason, in the last years there was a growing interest in the development of systems for automatic and fast detection of neonatal epileptic seizures. To this aim, we propose here hybrid systems that combines techniques related to the Stationary Wavelet Transform (SWT) as a support to deep-learning algorithms such as Convolutional Neural Networks and Fully Convolutional Networks. The proposed methods are validated on a public dataset of NICUs seizures recorded at the Helsinki University Hospital. Results are encouraging both in terms of Area Under the receiveroperating Curve, AUC (81%), Good Detection Rate, GDR (77%) and False Detection per hour, FD/h (1.6). Actually, the SWT step increases the performance of the proposed methods of about 5% for the AUC as compared to considering the raw EEG time-series only. These results, though preliminary, represent a significant step forward in solving the problem of neonatal seizure detection.

Technical Solution for Burnout, the Modern Age Health Issue

Simona Riurean - University of Petrosani, Romania

PREVIEW e-BADGE PRESENTATION

Technical Solution for Burnout, the Modern Age Health Issue

ABSTRACT

This world, the way we know it, dramatically changes every day due to unexpected technological developments with high influence on human wellbeing and health. Today, more than ever, the employees experience high demanding regarding their performance at work with direct consequences on personal comfort, leading, in most of cases, to an undesired burnout state. Early detection of the burnout state with the support of a wearable device is presented in this work. Based on data acquisition followed by local and remote optical wireless communication (OWC) technology, the Heart Rate (HR), the peripheral capillary oxygen saturation (SpO2) as well as Galvanic Skin (GS) values are analyzed and a fast estimation of burnout state is obtained due to artificial neuronal network (ANN). Burnout state early detection allows to increase individual, both body and mind health condition. The solution from this paper has two main advantages. The first is related to the correlation between the results of the quantitative research through questionnaires and of the qualitative research through physiological parameters measurement done by an ANN. The second is related to real-time burnout state estimation based only on measurements and without any outside communication of data, the only protocol for device setup is OWC, that ensures safety and privacy of data.

SESSION CHAIRS

Anna Maria Bianchi

Politecnico di Milano, Italy

e-BADGE

Kleanthis Neokleous

RISE Research Center on Interactive Media Smart Systems and Emerging Technologies

e-BADGE

Technical Session

IEEE Mediterranean Eletrotechnical Conference 2020

IEEE MELECON 2020

Session 3.3 - Neural and Cognitive Engineering: Methods and Technological Solutions

EEG monitoring during software development

Physiological responses related to pleasant and unpleasant sounds

Design and Implementation of Steady State Visual Evoked Potential Based Brain Computer Interface Video Game

CogAR: an augmented reality App to improve quality of life of the people with cognitive impairment

Neonatal Seizures Detection using Stationary Wavelet Transform and Deep Neural Networks: Preliminary Results

Technical Solution for Burnout, the Modern Age Health Issue

SESSION CHAIRS

Anna Maria Bianchi

Kleanthis Neokleous