Emotion recognition based on EEG (electroencephalography) has been widely used in human-computer interaction, distance education and health care. However, the conventional methods ignore the adjacent and symmetrical characteristics of EEG signals, which also contain salient information related to emotion. In this paper, we present a spatial folding ensemble network (SFENet) for EEG feature extraction and emotion recognition. Firstly, for the undetected area between EEG electrodes, we employ an improved Bicubic-EEG interpolation algorithm for EEG channel information completion, which allows us to extract a wider range of adjacent space features. Then, motivated by the spatial symmetry mechanism of human brain, we fold the input EEG channel data with five different symmetrical strategies: the left-right folds, the right-left folds, the top-bottom folds, the bottom-top folds, and the entire double-sided brain folding, which enable the proposed network to extract the information of space features of EEG signals more effectively. Finally, 3DCNN based spatial and temporal extraction and multi voting strategy of ensemble Learning are employed to model a new neural network. With this network, the spatial features of different symmetric folding signlas can be extracted simultaneously, which greatly improves the robustness and accuracy of feature recognition. The experimental results on DEAP and SEED data sets show that the proposed algorithm has comparable performance in term of recognition accuracy.
翻译:以 EEG (电子感官法) 为基础的内存识别(EEEG (电子感官法)) 被广泛用于 人体-计算机互动、远程教育和医疗保健。然而,常规方法忽视了EEEG信号的相邻和对称特征,这些特征还包含与情感有关的突出信息。在本文中,我们为 EEEG 特征提取和情感识别提供了一个空间折叠连锁网络(SFENet ) 。首先,对于 EEEG 电极之间未探测的区域,我们为 EEEEG 频道完成的信息使用改进的Bicubibic-EEEEG 干涉算法,从而使我们能够提取更广泛的相邻空间特征。随后,在人类大脑空间对称机制的驱动下,我们将EEEEG 频道输入数据与五种不同的对称战略相匹配:左折叠、右折叠、上折叠、下折叠和整个双向大脑折叠,使得拟议的网络能够更有效地提取EEEG信号的空间特征信息。最后,基于空间和时间提取和多表决的3DCD 计算和多表决策略,同时将精度数据化网络的精确化成一个模型的模型,可以改进SEEEEEEEEEEV 学习的模型的模型的模型的模型的模型的模型,可以同时使用。