Transfer Learning for Motor Imagery Based Brain-Computer Interfaces: A Complete Pipeline
This work addresses the challenge of high calibration effort for new users in motor imagery BCIs, offering an incremental improvement by integrating existing transfer learning approaches into a more comprehensive pipeline.
The paper tackles the problem of reducing calibration effort for motor imagery brain-computer interfaces by proposing a complete transfer learning pipeline that includes data alignment and applies transfer learning across all three components (spatial filtering, feature engineering, and classification). The result is significantly improved classification performance, greatly reducing calibration effort as verified on two datasets.
Transfer learning (TL) has been widely used in motor imagery (MI) based brain-computer interfaces (BCIs) to reduce the calibration effort for a new subject, and demonstrated promising performance. While a closed-loop MI-based BCI system, after electroencephalogram (EEG) signal acquisition and temporal filtering, includes spatial filtering, feature engineering, and classification blocks before sending out the control signal to an external device, previous approaches only considered TL in one or two such components. This paper proposes that TL could be considered in all three components (spatial filtering, feature engineering, and classification) of MI-based BCIs. Furthermore, it is also very important to specifically add a data alignment component before spatial filtering to make the data from different subjects more consistent, and hence to facilitate subsequential TL. Offline calibration experiments on two MI datasets verified our proposal. Especially, integrating data alignment and sophisticated TL approaches can significantly improve the classification performance, and hence greatly reduces the calibration effort.