1. Transfer Learning improves MI BCI models classification accuracy in Parkinson's disease patients
- Author
-
Agostino Accardo, Piero Paolo Battaglini, Joanna Jarmolowska, Susanna Mezzarobba, Pierpaolo Busan, Giulia Silveri, Miloš Ajčević, Aleksandar Miladinović, Miladinović, Aleksandar, Ajcevic, Miloš, Busan, Pierpaolo, Jarmolowska, Joanna, Silveri, Giulia, Mezzarobba, Susanna, Battaglini, PIERO PAOLO, and Accardo, Agostino
- Subjects
Signal Processing (eess.SP) ,FOS: Computer and information sciences ,Computer Science - Machine Learning ,medicine.medical_specialty ,Parkinson's disease ,business.industry ,020206 networking & telecommunications ,02 engineering and technology ,transfer learning ,Motor-Imagery Classification ,medicine.disease ,Brain-computer interface ,Machine Learning (cs.LG) ,Physical medicine and rehabilitation ,FOS: Electrical engineering, electronic engineering, information engineering ,0202 electrical engineering, electronic engineering, information engineering ,Medicine ,020201 artificial intelligence & image processing ,Electrical Engineering and Systems Science - Signal Processing ,business ,Transfer of learning ,Neurorehabilitation ,Brain–computer interface - Abstract
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
- Published
- 2021
- Full Text
- View/download PDF