A CSP-based retraining framework for motor imagery based brain-computer interfaces  

作　　者：Xue JIANG Lubin MENG Xinru CHEN Dongrui WU 

机构地区：[1]Key Laboratory of Image Processing and Intelligent Control,School of Artificial Intelligence and Automation,Huazhong University of Science and Technology,Wuhan 430074,China [2]Shenzhen Huazhong University of Science and Technology Research Institute,Shenzhen 518063,China

出　　处：《Science China(Information Sciences)》2024年第8期345-346,共2页中国科学（信息科学）（英文版）

基　　金：supported by Shenzhen Science and Technology Program(Grant No.JCYJ20220818103602004);Fundamental Research Funds for the Central Universities(Grant No.2023BR024).

摘　　要：Motor imagery(MI)is a classic paradigm of electroencephalogram(EEG)-based brain-computer interfaces(BCIs).It entails individuals mentally imagining the movement of a body part without physically performing it.EEG signals from MI are induced by imagination of movement and do not rely on external stimuli.With minimal training,individuals can achieve autonomous control,making MIbased BCI systems highly convenient.During MI,specific regions of the cerebral cortex exhibit changes in sensorymotor rhythms(SMR),which is mainly manifested through event-related desynchronization(ERD)and event-related synchronization(ERS),which are noticeable power decrease and increase at specific frequency bands,respectively.Generally,ERD occurs on the contralateral side of the brain,whereas ERS occurs on the ipsilateral side.Therefore,detecting SMR in specific areas of the cerebral cortex from EEG can be used to decode the subject's motor intentions,and then control external devices to execute the corresponding movements.

关 键 词：COMPUTER IMAGERY AUTONOMOUS 

分 类 号：R318[医药卫生—生物医学工程] TP391.41[医药卫生—基础医学]