Multichannel EEG-Based Emotion Recognition via Group Sparse Canonical Correlation Analysis
Multichannel EEG-Based Emotion Recognition via Group Sparse Canonical Correlation Analysis
复制标题
通过群体稀疏典型相关分析进行基于多通道脑电图的情绪识别
DOI：
10.1109/tcds.2016.2587290
复制
发表时间：
2017-09-01
影响因子：
5
通讯作者：
Zheng, Wenming
中科院分区：
文献类型：
--
作者：
Zheng, Wenming
本文提出了一种新的群体稀疏典型相关分析（GSCCA）方法，用于同时进行脑电图（EEG）通道选择和情绪识别。GSCCA是传统CCA方法的一种群稀疏扩展，用于对情绪脑电信号分类标签向量与相应脑电信号特征向量之间的线性关系进行建模。与传统的CCA方法或以前的GSCCA方法相比，我们的GSCCA方法的一个主要优点是能够处理原始脑电信号特征的组特征选择问题，这使得它非常适合同时处理脑电信号情感识别和自动通道选择问题，其中每个脑电信号通道与一组原始脑电信号特征相关联。针对脑电信号的情绪识别问题，我们采用常用的频率特征来描述脑电信号，将整个脑电信号频带分成delta、theta、alpha、beta和gamma五个频段，然后从每个频段提取频带特征进行GSCCA模型学习和情绪识别。最后，我们在上海交通大学情绪脑电图数据集上进行了大量基于脑电图的情绪识别实验，实验结果表明，所提出的GSCCA方法优于目前最先进的基于脑电图的情绪识别方法。
In this paper, a novel group sparse canonical correlation analysis (GSCCA) method is proposed for simultaneous electroencephalogram (EEG) channel selection and emotion recognition. GSCCA is a group sparse extension of the conventional CCA method to model the linear correlationship between emotional EEG class label vectors and the corresponding EEG feature vectors. In contrast to conventional CCA method or previous GSCCA methods, a major advantage of our GSCCA method is the ability of handling the group feature selection problem from raw EEG features, which makes it very suitable for simultaneously coping with both EEG emotion recognition and automatic channel selection issues where each EEG channel is associated with a group of raw EEG features. To deal with EEG emotion recognition problem, we adopt the popularly used frequency feature to describe the EEG signal by dividing the full EEG frequency band into five parts, i.e., delta, theta, alpha, beta, and gamma frequency bands, and then extract the frequency band features from each band for GSCCA model learning and emotion recognition. Finally, we conduct extensive experiments on EEG-based emotion recognition based on the SJTU emotion EEG dataset and experimental results demonstrate that the proposed GSCCA method would outperform the state-of-the-art EEG-based emotion recognition approaches.