A Study on Stroke Rehabilitation through Task-Oriented Control of a Haptic Device via Near-Infrared Spectroscopy-Based BCI

摘要

This paper presents a study in task-oriented approach to strokerehabilitation by controlling a haptic device via near-infraredspectroscopy-based brain-computer interface (BCI). The task is to command thehaptic device to move in opposing directions of leftward and rightwardmovement. Our study consists of data acquisition, signal preprocessing, andclassification. In data acquisition, we conduct experiments based on twodifferent mental tasks: one on pure motor imagery, and another on combinedmotor imagery and action observation. The experiments were conducted in bothoffline and online modes. In the signal preprocessing, we use localizationmethod to eliminate channels that are irrelevant to the mental task, as well asperform feature extraction for subsequent classification. We propose multiplesupport vector machine classifiers with a majority-voting scheme for improvedclassification results. And lastly, we present test results to demonstrate theefficacy of our proposed approach to possible stroke rehabilitation practice.