Investigating the effectiveness of transfer learning in a motor imagery game | |
| Author | Pongkorn Settasompop |
| Call Number | AIT Thesis no.CS-23-02 |
| Subject(s) | Electroencephalography Brain-computer interfaces Transfer learning (Machine learning) |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Computer Science |
| Publisher | Asian Institute of Technology |
| Abstract | This paper investigates the effectiveness of transfer learning in the BCI motor imagery system. In this study, an online EEG-based MI-BCI system with a Unity game as feedback was developed to assess transfer learning. If the participant successfully completes a task, the car is moved. Seven participants participated in the execution and imagery EEG signal recordings. Seven EEG recordings were used to train the 1D-CNN. Seven individuals were requested to participate in an online experiment that required the collection of additional EEG data for transfer learning. Our classifiers are more efficient in both execution and im age classification. In addition, effective classification was supplied for the online system. We conclude that MI-BCI-Unity is the next possible upgrade to the MI-BCI system. |
| Year | 2023 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Chaklam Silpasuwanchai |
| Examination Committee(s) | Dailey, Matthew N.;Mongkol Ekpanyapong |
| Scholarship Donor(s) | Royal Thai Government |
| Degree | Thesis (M. Sc.) - Asian Institute of Technology, 2023 |