TY - GEN
T1 - Transfer learning improves MI BCI models classification accuracy in Parkinson's disease patients
AU - Miladinovic, Aleksandar
AU - Ajcevic, Miloš
AU - Busan, Pierpaolo
AU - Jarmolowska, Joanna
AU - Silveri, Giulia
AU - Mezzarobba, Susanna
AU - Battaglini, Piero Paolo
AU - Accardo, Agostino
N1 - Funding Information:
A. Miladinović is supported by the European Social Fund (ESF) and Autonomous Region of Friuli Venezia Giulia (FVG). Work partially supported by the master programme in Clinical Engineering of the University of Trieste.
Publisher Copyright:
© 2021 European Signal Processing Conference, EUSIPCO. All rights reserved.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2021/1/24
Y1 - 2021/1/24
N2 - Motor-Imagery based BCI (MI-BCI) neurorehabilitation can improve locomotor ability and reduce the deficit symptoms in Parkinson's Disease patients. Advanced Motor-Imagery BCI methods are needed to overcome the accuracy and time-related MI BCI calibration challenges in such patients. In this study, we proposed a Multi-session FBCSP (msFBCSP) based on inter-session transfer learning and we investigated its performance compared to the single-session based FBSCP. The main result of this study is the significantly improved accuracy obtained by proposed msFBCSP compared to single-session FBCSP in PD patients (median 81.3%, range 41.2-100.0% vs median 61.1%, range 25.0-100.0%, respectively; p<0.001). In conclusion, this study proposes a transfer learning-based multi-session based FBCSP approach which allowed to significantly improve calibration accuracy in MI BCI performed on PD patients.
AB - Motor-Imagery based BCI (MI-BCI) neurorehabilitation can improve locomotor ability and reduce the deficit symptoms in Parkinson's Disease patients. Advanced Motor-Imagery BCI methods are needed to overcome the accuracy and time-related MI BCI calibration challenges in such patients. In this study, we proposed a Multi-session FBCSP (msFBCSP) based on inter-session transfer learning and we investigated its performance compared to the single-session based FBSCP. The main result of this study is the significantly improved accuracy obtained by proposed msFBCSP compared to single-session FBCSP in PD patients (median 81.3%, range 41.2-100.0% vs median 61.1%, range 25.0-100.0%, respectively; p<0.001). In conclusion, this study proposes a transfer learning-based multi-session based FBCSP approach which allowed to significantly improve calibration accuracy in MI BCI performed on PD patients.
KW - Brain-computer interface
KW - Motor-Imagery Classification
KW - Parkinson's disease
KW - Transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85099312431&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85099312431&partnerID=8YFLogxK
U2 - 10.23919/Eusipco47968.2020.9287391
DO - 10.23919/Eusipco47968.2020.9287391
M3 - Conference contribution
AN - SCOPUS:85099312431
T3 - European Signal Processing Conference
SP - 1353
EP - 1356
BT - 28th European Signal Processing Conference, EUSIPCO 2020 - Proceedings
PB - European Signal Processing Conference, EUSIPCO
T2 - 28th European Signal Processing Conference, EUSIPCO 2020
Y2 - 24 August 2020 through 28 August 2020
ER -