Active transfer learning and selective instance transfer with active learning for motor imagery based BCI

Abstract

Non-invasive EEG signal based brain computer interface (BCI) for motor imagery task - classification requires large number of subject specific training samples for each user session that reduces the user feasibility of BCI. A generalized classifier using few subject specific sample will ease the real world implementation of motor imagery based BCI. At first, this paper applies an improved active transfer learning (ATL) on motor imagery based BCI. Then, it proposes a noble method of transferring selective instances (selected by few new subject specific data) from other subjects to new subject combining with selecting most informative subject specific data determined by active learning. Experimental results on BCI competition IV 2B dataset show that improved ATL works well on six out of nine subjects and proposed SIITAL method overcomes ATL limitation for other subjects. This means, it can achieve similar or better accuracy with a lower quantity of subject specific training data. Thus, it reduces the calibration effort.