基于Otsu的EEG通道选择情绪识别研究  

Otsu⁃based emotion recognition by EEG channel selection

作　　者：钟志文 陈茂洲 ZHONG Zhiwen;CHEN Maozhou(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500

出　　处：《现代电子技术》2023年第17期39-42,共4页Modern Electronics Technique

摘　　要：脑电信号情绪识别是数据人机交互(HCI)技术的一种,实时情感识别对于模型性能要求较高,为实现以较低的运算成本获取较高的识别精度,采用时域滑动窗口的方法扩充样本量,基于Otsu算法筛选出含有最多情绪特征信息的通道,并利用快速傅里叶变换进行脑电信号频段提取,以功率谱密度作为特征,构建了基于支持向量机等分类模型,对高唤醒-低唤醒(HA-LA)和高效价-低效价(HV-LV)两种任务进行分类。实验表明,使用SVM分类器在HA-LA情绪识别任务中得到(82.2±0.4)%的识别准确率,在HV-LV情绪识别任务中得到(83.4±0.3)%的识别准确率。所提出的时域滑动窗口能有效提取含有情绪的脑电信号,在减少数据量的情况下仍获得了不错的情绪识别性能,为实时情感识别的脑机接口提供了一种高效的模型。The emotion recognition with EEG signals is a type of human⁃computer interface(HCI)technology.Real⁃time emotion recognition requires high model performance and aims to achieve high recognition accuracy with low computational cost,so a sliding window method in the time domain is used to expand the sample size.The channel with the most emotional features is selected based on the Otsu algorithm.The Fourier transform is used to extract the frequency band of EEG signals,and the power spectral density is used as the feature to construct a classification model based on support vector machine(SVM).The model is used to classify two kinds of tasks:high arousal⁃low arousal(HA⁃LA)and high valence⁃low valence(HV⁃LV).The experimental results show that the SVM classifier achieves recognition accuracy rates of(82.2±0.4)%in the HA⁃LA emotion recognition task and(83.4±0.3)%in the HV⁃LV emotion recognition task.The proposed sliding window method can extract emotional EEG signals effectively and obtain good emotion recognition performance while reducing the amount of data.It provides an efficient model for the BCI(brain⁃computer interface)with real⁃time emotion recognition.

关 键 词：情绪识别 脑机接口 脑电信号 OTSU算法 通道选择 滑动窗口 数据扩容 支持向量机 

分 类 号：TN919-34[电子电信—通信与信息系统] TP391[电子电信—信息与通信工程]