Calibrating EEG features in motor imagery classification tasks with a small amount of current data using multisource fusion transfer learning. (September 2020)

• Record Type: Journal Article
• Authors: Liang, Yong; Ma, Yu
• Is Part Of: Biomedical signal processing and control. Volume 62(2020)
• Publication Date: 2020-09
• Subjects: Brain-computer interface -- Transfer learning -- Source selection -- Balanced distribution adaptation; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2020.102101
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A novel transfer learning algorithm for calibrating EEG features in motor imagery classification tasks. A two-step calibration based on transfer learning, which works on the levels of both subjects and features. Only need a small amount of new training data from the current user. Superior performance compared to state-of-the-art works. Abstract: Background and objective: The identification of motor intention by analyzing electroencephalogram (EEG) signals has become an important issue in brain-computer interface (BCI) applications. Since the individual differences of EEG are large, it's hard to design a universal BCI system, which means the labeled data from current user have to be collected for calibration. We propose a multi-source fusion transfer learning algorithm for this calibration, which only needs a small amount of new data from the current user. Methods: The core idea of proposed algorithm is a two-step calibration based on transfer learning, which works on the levels of both subjects and features. The spatial covariance matrices represented in the Riemannian space are used to characterize the multi-channel EEG signals. Source subjects whose features are similar to the current user are selected as the transfer source via a Riemannian geometry alignment algorithm. Their features obtained from the Riemannian tangent space, as well as the ones of the current user, are fused and calibrated by a balanced distribution adaptation algorithm. Finally, a classification model could be trained for the current user with only a few new training data. Results: Validated on both the online ERD-BCI database and the BCI Competition IV 2a database for motor imagery tasks, experimental results show that our method outperforms the state-of-the-art methods. When the new training data from current user is insufficient, the classification accuracy and kappa values compared with the outstanding counterparts have advantages of 3.30 % and 0.05 respectively on the online ERD-BCI database, 3.95 % and 0.03 respectively on the BCI Competition IV 2a database. Even when the new training data from current user is sufficient, the classification accuracy and kappa values of our proposed method also outperforms the counterparts with highest performance by 2.37 % and 0.05 respectively on the online ERD-BCI database, 2.25 % and 0.03 respectively on the BCI Competition IV 2a database. Conclusions: The algorithm provides a new idea of solution for calibrating EEG features. It is expected to contribute to the practical applications of BCI.