基于迁移学习和残差网络的SSVEP信号识别
SSVEP Signal Recognition Based on Transfer Learning and Residual Networks
尹菁 1王贤敏 1王力哲 2郭海湘3
作者信息
- 1. 中国地质大学(武汉)地球物理与空间信息学院,湖北 武汉 430074;中国地质大学(武汉)地质探测与评估教育部重点实验室,湖北 武汉 430074
- 2. 中国地质大学(武汉)地质探测与评估教育部重点实验室,湖北 武汉 430074
- 3. 中国地质大学(武汉)地质探测与评估教育部重点实验室,湖北 武汉 430074;中国地质大学(武汉)经济管理学院,湖北 武汉 430074
- 折叠
摘要
针对脑电信号中的稳态视觉诱发电位(SSVEP)信号目标识别难以适应个体差异、识别稳定性差、精度低的难题,提出了一种参数共享迁移学习的残差网络SSVEP信号识别方法.首先,利用离散小波变换将多通道 SSVEP信号转化为小波系数,并与变换前信号构成特征矩阵作为输入特征集,提升特征提取的丰富性;其次,建立融合空间注意力机制的残差网络,利用清华大学脑—机接口提供的两个SSVEP信号数据集,包括105 名被试,进行跨任务的迁移训练,把源域上训练完成的网络逐模块迁移至目标网络以获取合适的迁移模块,迁移后连接2 层残差块和模式识别单元得到跨个体差异识别结果.实验结果显示,在1s时间窗口,训练与测试使用被试无交集情况下,测试集的总识别率达到84.2％,提升了脑电信号识别的个体适应性,验证了提出的方法在提高SSVEP信号识别的稳健性和准确性上具有优势.
Abstract
A residual network SSVEP signal recognition method based on parameter sharing transfer learning is proposed to address the challenges of adapting to individual differences,poor recognition stability,and low accuracy in target recognition of steady-state visual evoked potential(SSVEP)signals in EEG signals.Firstly,the multi-channel SSVEP signals are transformed into wavelet coefficients using discrete wavelet transform as the input feature set to-gether with the pre-transformed signals;thus,the extracted features are more abundant.Secondly,a residual network fused with a spatial attention mechanism is established,and two SSVEP signal datasets,including 105 individuals,provided by the Tsinghua University brain-computer interface are used to achieve a cross-task and cross-individual transfer.The network trained on the source domain is migrated to the target network block by block to obtain the ap-propriate transfer block,and the recognition results are obtained by connecting the 2 residual blocks and pattern rec-ognition units after the transfer.The total recognition rate in the test set reaches 84.2％ under a 1s time-window with no intersection between training and test individuals.Thus,the proposed method is characterized by relatively high in-dividual adaptability,accuracy,and robustness in SSVEP signal recognition.
关键词
稳态视觉诱发电位/残差网络/迁移学习/注意力机制Key words
Steady-state visual evoked potentials/Residual networks/Transfer learning/Attentional mechanism引用本文复制引用
基金项目
国家自然科学基金(U21A2013)
国家自然科学基金(71874165)
地质探测与评估教育部重点实验室主任基金(GLAB2020ZR02)
地质探测与评估教育部重点实验室主任基金(GLAB2022ZR02)
出版年
2024
NETL
NSTL
万方数据