电子测量与仪器学报

黄永庆,周强.基于 CNN 时-空卷积优化的 EM-EEG 识别方法研究[J].电子测量与仪器学报,2022,36(3):231-240

基于 CNN 时-空卷积优化的 EM-EEG 识别方法研究

Research on EM-EEG recognition method based on CNNtime-space convolution optimization

DOI：

中文关键词: EM-EEG 时-空卷积优化粒子群算法 STPS 相关分析 SEED IV 数据集

英文关键词:emotional electroencephalogram(EM-EEG) time-space convolution optimization particle swarm optimization(PSO) STPS correlation analysis SEED IV data set

基金项目:陕西省科技计划项目（2019GY 090）、咸阳市科技计划项目（2017K02 06）资助

作者	单位
黄永庆	1. 陕西科技大学电气与控制工程学院，2. 陕西科技大学陕西省人工智能联合实验室
周强	1. 陕西科技大学电气与控制工程学院，2. 陕西科技大学陕西省人工智能联合实验室

Author	Institution
Huang Yongqing	1. School of Electrical and Control Engineering, Shaanxi University of Science and Technology, 2. Shaanxi Joint Laboratory of Artificial Intelligence, Shaanxi University of Science and Technology
Zhou Qiang	1. School of Electrical and Control Engineering, Shaanxi University of Science and Technology, 2. Shaanxi Joint Laboratory of Artificial Intelligence, Shaanxi University of Science and Technology

摘要点击次数: 1317

全文下载次数: 974

中文摘要:

针对当前情绪脑电信号(emotion electroencephalogram,EM-EEG)识别研究中时间域信息的时间尺度难以把握和空间域信息易被忽视致使辨识率停滞不前,以及采集 EM-EEG 时通道过多导致信息冗余和信息处理成本增加等问题,提出了基于 CNN 的时-空卷积优化融合网络进行 EM-EEG 识别研究。该融合网络由提取 EM-EEG 时域信息的长卷积( long convolution,LConv)CNN 和提取 EM-EEG 空域信息的 CNN 并联组成,在 CNN 模型时-空优化中使用粒子群算法( particle swarm optimization, PSO)对时域 CNN 中的 L-Conv 尺度进行了优化,并使用短时功率谱(short time power spectrum,STPS)的相关分析方法进行空域 CNN 模型通道数目优化,深层且有效地提取了 EEG 中的时间域和空间域特征。结果表明,提出的时-空卷积优化融合 CNN 在 SEED IV 数据集上对平和、悲伤、恐惧、高兴 4 种情绪最终准确率可以达到 90. 13%,相比传统单一 CNN 的识别准确率提高了 4. 76%,并且通道数目由 62 路降低至 33 路,缩减了 46. 77%,证实了本方法的可行性。

英文摘要:

In view of the current emotional electroencephalogram (EM-EEG) identification research on time scales is difficult to grasp the time domain information and the spatial domain information is easy to ignore the recognition rate is stagnant, and collect the EM-EEG with too many channels in the excessive information redundancy and increasing cost of information processing problems, it puts forward the space-time convolution based on CNN optimization study on EM-EEG identification fusion network. The fusion network is composed of a parallel long convolution (L-Conv) CNN that extracts EM-EEG time domain information and a CNN that extracts EM-EEG spatial information. Particle swarm optimization (PSO) is used in the time-space optimization of the CNN model. The L-Conv scale in CNN has been optimized, and use the short time power spectrum ( STPS) correlation analysis method of the spatial CNN channel number optimization model, temporal and spatial domain features in EEG are extracted deeply and effectively. The results show that the proposed optimization of space-time convolution integration CNN on SEED IV data set for peace, sadness, fear, happy four final accuracy can reach 90. 13%, compared with the traditional single CNN recognition accuracy rate increased by 4. 76%, and channel number from 62 to 33 road, shrank by 46. 77%, confirmed the feasibility of this method.

查看全文查看/发表评论下载PDF阅读器