An Inter- and Intra-Subject Transfer Calibration Scheme for Improving Feedback Performance of Sensorimotor Rhythm-Based BCI Rehabilitation

Lei Cao; Shugeng Chen; Jie Jia; Chunjiang Fan; Haoran Wang; Zhixiong Xu

doi:10.3389/fnins.2020.629572

An Inter- and Intra-Subject Transfer Calibration Scheme for Improving Feedback Performance of Sensorimotor Rhythm-Based BCI Rehabilitation

Front Neurosci. 2021 Jan 28:14:629572. doi: 10.3389/fnins.2020.629572. eCollection 2020.

Authors

Lei Cao¹, Shugeng Chen², Jie Jia², Chunjiang Fan³, Haoran Wang⁴, Zhixiong Xu¹

Affiliations

¹ Department of Artificial Intelligence, Shanghai Maritime University, Shanghai, China.
² Department of Rehabilitation Medicine, Huashan Hospital, Fudan University, Shanghai, China.
³ Wuxi Rehabilitation Hospital, Wuxi, China.
⁴ Department of Computer Science and Technology, Tongji University, Shanghai, China.

Abstract

The Brain Computer Interface (BCI) system is a typical neurophysiological application which helps paralyzed patients with human-machine communication. Stroke patients with motor disabilities are able to perform BCI tasks for clinical rehabilitation. This paper proposes an effective scheme of transfer calibration for BCI rehabilitation. The inter- and intra-subject transfer learning approaches can improve the low-precision classification performance for experimental feedback. The results imply that the systematical scheme is positive in increasing the confidence of voluntary training for stroke patients. In addition, it also reduces the time consumption of classifier calibration.

Keywords: BCI; classifier calibration; rehabilitation; stroke; transfer learning.