Fang Yinfeng, Yang Haiyang, Zhang Xuguang, Liu Han, Tao Bo
School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, China.
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China.
Front Neurorobot. 2021 Jan 11;14:617531. doi: 10.3389/fnbot.2020.617531. eCollection 2020.
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.
由于人机交互的快速发展，情感计算近年来受到了越来越多的关注。在情感识别中，脑电图（EEG）信号比其他生理实验更容易记录，并且不容易被伪装。由于EEG数据的高维性质和人类情感的多样性，提取有效的EEG特征并识别情感模式具有一定难度。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EEG信号划分为几个EEG频段，然后从每个频段以及原始信号中提取功率谱密度（PSD）和微分熵（DE）作为特征。使用一个五类情感模型来标记五种情感，包括中性、愤怒、悲伤、快乐和愉悦。以原始特征或降维后的特征作为输入，构建深度森林对这五种情感进行分类。这些实验在一个用于使用生理信号进行情感分析的公共数据集（DEAP）上进行。将实验结果与传统分类器进行比较，包括K近邻（KNN）、随机森林（RF）和支持向量机（SVM）。MFDF实现了71.05%的平均识别准确率，分别比RF、KNN和SVM高3.40%、8.54%和19.53%。此外，以降维后的特征和原始EEG信号作为输入时的准确率分别仅为51.30%和26.71%。本研究结果表明，该方法能够有效地为基于EEG的情感分类任务做出贡献。
