Multi-Feature Input Deep Forest for EEG-Based Emotion Recognition.
Multi-Feature Input Deep Forest for EEG-Based Emotion Recognition.
复制标题
用于基于脑电图的情绪识别的多特征输入深度森林
DOI：
10.3389/fnbot.2020.617531
复制
发表时间：
2020
影响因子：
3.1
通讯作者：
Tao B
中科院分区：
文献类型：
--
作者：
Fang Y;Yang H;Zhang X;Liu H;Tao B
随着人机交互的快速发展，情感计算近年来受到越来越多的关注。在情绪识别中，脑电图信号比其他生理实验更容易被记录，而且不易被伪装。由于脑电数据的高维性和人类情绪的多样性，很难提取有效的脑电特征和识别情绪模式。本文提出了一种多特征深度森林（MFDF）模型来识别人类情感。首先将脑电信号划分为多个脑电信号频带，然后从每个频带和原始信号中提取功率谱密度（PSD）和微分熵（DE）作为特征。用一个五级情绪模型来标记五种情绪，包括中性、愤怒、悲伤、快乐和愉快。以原始特征或降维特征作为输入，构建深度森林对五种情绪进行分类。这些实验是在使用生理信号（DEAP）进行情绪分析的公共数据集上进行的。实验结果与传统分类器，包括K近邻（KNN）、随机森林（RF）和支持向量机（SVM）进行了比较。MFDF的平均识别准确率为71.05%，比RF、KNN和SVM分别提高3.40%、8.54%和19.53%。降维后特征输入和原始脑电信号输入的准确率分别只有51.30%和26.71%。研究结果表明，该方法能够有效地完成基于脑电图的情绪分类任务。
Due to the rapid development of human–computer interaction, affective computing has attracted more and more attention in recent years. In emotion recognition, Electroencephalogram (EEG) signals are easier to be recorded than other physiological experiments and are not easily camouflaged. Because of the high dimensional nature of EEG data and the diversity of human emotions, it is difficult to extract effective EEG features and recognize the emotion patterns. This paper proposes a multi-feature deep forest (MFDF) model to identify human emotions. The EEG signals are firstly divided into several EEG frequency bands and then extract the power spectral density (PSD) and differential entropy (DE) from each frequency band and the original signal as features. A five-class emotion model is used to mark five emotions, including neutral, angry, sad, happy, and pleasant. With either original features or dimension reduced features as input, the deep forest is constructed to classify the five emotions. These experiments are conducted on a public dataset for emotion analysis using physiological signals (DEAP). The experimental results are compared with traditional classifiers, including K Nearest Neighbors (KNN), Random Forest (RF), and Support Vector Machine (SVM). The MFDF achieves the average recognition accuracy of 71.05%, which is 3.40%, 8.54%, and 19.53% higher than RF, KNN, and SVM, respectively. Besides, the accuracies with the input of features after dimension reduction and raw EEG signal are only 51.30 and 26.71%, respectively. The result of this study shows that the method can effectively contribute to EEG-based emotion classification tasks.
登录
查看更多内容
影响因子：
11.2
作者：
Koelstra, Sander;Muhl, Christian;Patras, Ioannis (Yiannis)
通讯作者：
Patras, Ioannis (Yiannis)
通过深森林的多通道脑电图进行情绪识别
DOI：
10.1109/jbhi.2020.2995767
发表时间：
2021-02-01
影响因子：
7.7
作者：
Cheng, Juan;Chen, Meiyao;Chen, Xun
通讯作者：
Chen, Xun
影响因子：
3.4
作者：
Cao, Xianghai;Li, Renjie;Jiao, Licheng
通讯作者：
Jiao, Licheng
DOI：
10.1109/tnsre.2017.2776149
发表时间：
2018-01-01
影响因子：
4.9
作者：
Memar, Pejman;Faradji, Farhad
通讯作者：
Faradji, Farhad
人脑脑电图传感器情绪识别的最优特征选择和深度学习集成方法
影响因子：
3.9
作者：
Mehmood, Raja Majid;Du, Ruoyu;Lee, Hyo Jong
通讯作者：
Lee, Hyo Jong