重庆大学学报2024，Vol.47Issue(3)：86-95,10.DOI:10.11835/j.issn.1000-582X.2022.207
运动想象脑机接口的判别迁移特征学习与分类
Discriminative transfer feature for motor imagery brain-computer interfaces
摘要
Abstract
To address the cross-sessions variability of motor imagery electroencephalogram (EEG) and eliminate the need for lengthy recalibration step, this study proposes a motor imagery classification method based on discriminative transfer feature learning (DTFL). DTFL aims to reduce domain differences by jointly matching the marginal distribution and class conditional distribution of both domains. Simultaneously, DTFL maximizes inter-class dispersion and minimizes intra-class scatter, preserving class discrimination information and improving classification performance. This method does not require class information for EEG samples in the target domain, effectively avoiding the need for long-term calibration. Experimental results on brain-computer interface competition datasets demonstrate that, compared with some transfer learning methods, the proposed DTFL mitigates cross-session variability and improves the classification accuracy of motor imagery EEG.关键词
脑机接口/运动想象/迁移学习Key words
brain-computer interfaces/motor imagery/transfer learning分类
信息技术与安全科学引用本文复制引用
齐垒,陈民铀,张莉..运动想象脑机接口的判别迁移特征学习与分类[J].重庆大学学报,2024,47(3):86-95,10.基金项目
国家自然科学基金资助项目(51977020).Supported by National Natural Science Foundation of China(51977020). （51977020）
