People suffering from complete motor paralysis with no severe deficiency in cognitive abilities, syndrome called Completely Locked in State (CLIS), remain aware of their surroundings without being able to interact and communicate in any way. In this context, the only possibility of communicating is by the techniques of Brain-Computer Interface. In this work, the focus is on the features extraction and selection on EEG and fNIRS signals and, finally, on the combination of the two to develop a system capable of classifying affirmative and negative answers from users in CLIS. The analysis considers the data collected in 4 visits to one patient. The choice to focus on a single case was made because the psychophysical considerations on the state of the patient are fundamental interpreting the results and the author of this work had the opportunity to participate directly in some acquisition. Offline analysis led to good results in the classification of fNIRS signals. Once again, using EEG signals it was not possible to successfully classify yes/no answers. Finally, the combination of EEG and fNIRS features did not improve the performance of the system.
Classification of EEG and fNIRS signals from Completely Locked-in State Patients for a Brain-Computer Interface communication system
Corniani, Giulia
2018/2019
Abstract
People suffering from complete motor paralysis with no severe deficiency in cognitive abilities, syndrome called Completely Locked in State (CLIS), remain aware of their surroundings without being able to interact and communicate in any way. In this context, the only possibility of communicating is by the techniques of Brain-Computer Interface. In this work, the focus is on the features extraction and selection on EEG and fNIRS signals and, finally, on the combination of the two to develop a system capable of classifying affirmative and negative answers from users in CLIS. The analysis considers the data collected in 4 visits to one patient. The choice to focus on a single case was made because the psychophysical considerations on the state of the patient are fundamental interpreting the results and the author of this work had the opportunity to participate directly in some acquisition. Offline analysis led to good results in the classification of fNIRS signals. Once again, using EEG signals it was not possible to successfully classify yes/no answers. Finally, the combination of EEG and fNIRS features did not improve the performance of the system.File | Dimensione | Formato | |
---|---|---|---|
Corniani_thesisFINAL.pdf
accesso aperto
Dimensione
3 MB
Formato
Adobe PDF
|
3 MB | Adobe PDF | Visualizza/Apri |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
https://hdl.handle.net/20.500.12608/24540