Analysis and Classification for Single-Trial EEG Induced by Sequential Finger Movements

In recent years, motor imagery-based BCIs (MI-BCIs) controlled various external devices successfully, which have great potential in neurological rehabilitation. In this paper, we designed a paradigm of sequential finger movements and utilized spatial filters for feature extraction to classify single-trial electroencephalography (EEG) induced by finger movements of left and right hand. Ten healthy subjects participated the experiment. The analysis of EEG patterns showed significant contralateral dominance. We investigated how data length affected the classification accuracy. The classification accuracy was improved with the increase of the keystrokes in one trial, and the results were 87.42%, 91.21%, 93.08% and 93.59% corresponding to single keystroke, two keystrokes, three keystrokes and four keystrokes. This study would be helpful to improve the decoding efficiency and optimize the encoding method of motor-related EEG information.

I. Introduction

Brain-computer interfaces (BCIs) are the direct communication pathways that users interact with the extern world by means of changes in brain activity. BCIs could replace, restore, enhance, supplement, or improve center nervous system output [1]. With the development of technology in recent decades, BCIs have several mature paradigm systems, such as steady-state visual evoked potential based BCI, P300 potential based BCI, and motor imagery based BCI (MI-BCI) [2]. As a typical paradigm, MI-BCI has received great attention, not only because of its relying on the users’ subjective intention rather than external stimulus but also owe to its immense potential in the neurological rehabilitation and motor assistant [3][4].