Zhong Qinghua, Zhu Yongsheng, Cai Dongli, Xiao Luwei, Zhang Han
School of Physics and Telecommunication Engineering, South China Normal University, Guangzhou, China.
South China Academy of Advanced Optoelectronics, South China Normal University, Guangzhou, China.
Front Hum Neurosci. 2020 Dec 16;14:589001. doi: 10.3389/fnhum.2020.589001. eCollection 2020.
In the human-computer interaction (HCI), electroencephalogram (EEG) access for automatic emotion recognition is an effective way for robot brains to perceive human behavior. In order to improve the accuracy of the emotion recognition, a method of EEG access for emotion recognition based on a deep hybrid network was proposed in this paper. Firstly, the collected EEG was decomposed into four frequency band signals, and the multiscale sample entropy (MSE) features of each frequency band were extracted. Secondly, the constructed 3D MSE feature matrices were fed into a deep hybrid network for autonomous learning. The deep hybrid network was composed of a continuous convolutional neural network (CNN) and hidden Markov models (HMMs). Lastly, HMMs trained with multiple observation sequences were used to replace the artificial neural network classifier in the CNN, and the emotion recognition task was completed by HMM classifiers. The proposed method was applied to the DEAP dataset for emotion recognition experiments, and the average accuracy could achieve 79.77% on arousal, 83.09% on valence, and 81.83% on dominance. Compared with the latest related methods, the accuracy was improved by 0.99% on valence and 14.58% on dominance, which verified the effectiveness of the proposed method.
在人机交互（HCI）中，通过脑电图（EEG）进行自动情绪识别是机器人大脑感知人类行为的一种有效方式。为了提高情绪识别的准确率，本文提出了一种基于深度混合网络的脑电图情绪识别方法。首先，将采集到的脑电图分解为四个频段信号，并提取每个频段的多尺度样本熵（MSE）特征。其次，将构建的三维MSE特征矩阵输入到深度混合网络中进行自主学习。深度混合网络由连续卷积神经网络（CNN）和隐马尔可夫模型（HMM）组成。最后，使用经过多个观测序列训练的HMM替代CNN中的人工神经网络分类器，由HMM分类器完成情绪识别任务。将所提方法应用于DEAP数据集进行情绪识别实验，在唤醒度方面平均准确率可达79.77%，效价方面为83.09%，优势度方面为81.83%。与最新的相关方法相比，效价方面准确率提高了0.99%，优势度方面提高了14.58%，验证了所提方法的有效性。
