Weighted Subject-Semi-Independent Erp-Based Brain-Computer Interface

42ND ANNUAL INTERNATIONAL CONFERENCES OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY: ENABLING INNOVATIVE TECHNOLOGIES FOR GLOBAL HEALTHCARE EMBC'20(2020)

引用 2|浏览21
暂无评分
摘要
Subject-independent brain-computer interfaces (SI-BCIs) which require no calibration process, are increasingly affect researchers in BCI field. The efficiencies (accuracies), however, were not satisfying till now. In this paper, we proposed a weighted subject-semi-independent classification method (WSSICM) for ERP based BCI system in which a few blocks data of target subject were used. 47 participants were attended in this study. We compared the accuracies of proposed method with traditional subject-specific classification method(SSCM) which used 15 blocks data of target subject. The averaged accuracies were 95.2% for the WSSICM at 5 blocks and 95.7% for the SSCM at 15 blocks. The accuracies of two method did not show significant difference (p-value=0.652). The method we proposed in this paper which could reduce the calibration time can be used for future BCI systems.
更多
查看译文
关键词
Brain-Computer Interfaces,Calibration,Data Collection,Humans,Research Design
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要