ARTIFICIAL INTELLIGENCE APPLIED TO THE STUDY OF CONSCIOUS PERCEPTIVE STATES

Dove e quando

2019-03-11 | Conference Room (3rd floor) DIBRIS Via Dodecaneso 35, Ore 16.00

SERIES: AUK READINGS IN WELL-BEING TECHNOLOGIES TITLE: ARTIFICIAL INTELLIGENCE APPLIED TO THE STUDY OF CONSCIOUS PERCEPTIVE STATES SPEAKER: Dr. Marialessia Musumeci (Computer Science Department of Milan University, Italy) EMAIL: marialessia.musumeci@gmail.com DATE: Monday March 11th,2019 - time 4:00 pm VENUE: Conference Room (3rd floor) DIBRIS Via Dodecaneso 35 - Genoa (Italy) ABSTRACT: This research consists of the processing of signals from the 14 electrodes of the EMOTIV system, connected to immersive glasses that allow a realistic visual experience and investigate the brain network in order to identify the signals features corresponding to different perceptive and cognitive stimuli. A Matlab-Simulink procedure synchronizes the acquired signals with various sensory experiences presented in a video. Aim of the research is to test the interconnections among brain areas in presence of sensory and emotional stimuli, and show how similar stimuli give rise to chaotic attractors identified with identical or similar codes. The chaotic attractors can be definite as a trajectory of the dynamical system, contained in a finite volume of phase space. A dynamical system can have chaotic behavior, i.e. an organized (but not periodic) behavior sensitive to the initial conditions. In this work a custom ANN (ITSOM) processes individual signals or many signals simultaneously. The sequence of the ITSOM winning nodes tends to repeat itself creating a time series of chaotic attractors. The ITSOM attributes similar codes attractors emerging from similar brain states, perceptions and emotions. Such attractors are isomorphic to the attractors in which the corresponding dynamic system (the signal time series) is evolving and characterize univocally the input element that produces them. If the attractors are chaotic, this means that the signals are individually self-organized or, examining more signals together, there is a form of coherence between signals. The ITSOM network memorizes the time series of the winning nodes. The cumulative scores for each input are normalized following the z standardized variable distribution. Attractors are labelled with a binary code that identifies them univocally, and the flexibility of the ANN allows attributing the same codes to similar dynamic events. During the experiment, the subject is looking at the screen when different nuances of colours (yellow, red and blue) are displayed. Each stimulation lasts five seconds, between stimuli there is a black screen (the black is used to reset the previous colour stimuli). The collected results show, as forecast, many correspondences among binary codes coming from similar stimuli. BIO: Marialessia Musumeci was born in Genoa, Italy, on September 11, 1985. She received the Bachelor's degree in Neurophysiology Techniques in November 2008 from Universita' degli Studi di Genova, Italy, discussing the thesis âThe Technique Of Digital Recording and Quantification€. From January 2009 to September 2009, she collaborated for the different Hospitals, Genoa and Milan, Italy, performing research activities in the context of the Neurological Surgery and Sleep Recording of neural signals. She received the Master' s degree in Cognitive Science and Decision Making in March 2011 from Universita' degli Studi di Milano, Italy, discussing the thesis €Communication for Learning Mediated by BCI in cases of Dyslexia and ADHD (Attention Deficit Hyperactivity Disorder)€. From January 2015 to July 2015, she perceived a research grant from Department of Information Technologies, Universita' degli Studi di Milano, Italy, performing research activities neuroscience and signals processing techniques. From October 2015 to November 2018, she has been a PhD student at the Computer Science Doctorate School of Universita' degli Studi di Milano (XXXI cycle), performing research activities at the Department of Computer Science, with the supervision of Prof. Rita Maria Rosa Pizzi. In the first year of the doctorate she took part in the European project entitled NANO x COMP, bringing his neuroscientific skills. She has obtained the PhD in February 2019, discussing the thesis Artificial Intelligence Applied To The Study Of Conscious Perceptive States€. Resulting the only woman to obtain the title of research doctor for the XXXI cycle. His research interests include neuroconding, neuroscience, neurophysiology, cognitive science, signal and image processing, computational intelligence. Author of several publications on these topics.
Ultimo aggiornamento 28 Febbraio 2019