Online BCI systems: cross-subject motor imagery classification based on weighted time-domain feature extraction methods

• Published in: Journal of engineering design Vol. 35; no. 6; pp. 685 - 708
• Main Authors: Yang, Cheng, Wang, Shiyu, Peng, Yiteng, Zhang, Zhichao, Kong, Lei, Zhou, Chuyi, Tao, Ye, Chen, Xiaoyu
• Format: Journal Article
• Language: English
• Published: Abingdon Taylor & Francis 02.06.2024; Taylor & Francis Ltd
• Subjects: Accuracy; Brain-computer interface; channel selection; Classification; cross-subject; Electroencephalography; Feature extraction; Feature recognition; Human-computer interface; Image classification; Imagery; motor imagery; online system; Signal classification; Support vector machines; Time domain analysis; Wheelchairs

Motor imagery electroencephalogram (MI-EEG) is becoming increasingly important. This paper solves the problem of online signal recognition for motor imagery across subjects by finding common features across multiple subjects to improve the generality of the classification model. We analysed the EEG...