感知:从EEG获得时间动态和空间对称,以识别情感 (TSception: Capturing Temporal Dynamics and Spatial Asymmetry from EEG for Emotion Recognition)

from arxiv, This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. (Accepted as a regular paper in IEEE Transactions on Affective Computing)

The high temporal resolution and the asymmetric spatial activations are essential attributes of electroencephalogram (EEG) underlying emotional processes in the brain. To learn the temporal dynamics and spatial asymmetry of EEG towards accurate and generalized emotion recognition, we propose TSception, a multi-scale convolutional neural network that can classify emotions from EEG. TSception consists of dynamic temporal, asymmetric spatial, and high-level fusion layers, which learn discriminative representations in the time and channel dimensions simultaneously. The dynamic temporal layer consists of multi-scale 1D convolutional kernels whose lengths are related to the sampling rate of EEG, which learns the dynamic temporal and frequency representations of EEG. The asymmetric spatial layer takes advantage of the asymmetric EEG patterns for emotion, learning the discriminative global and hemisphere representations. The learned spatial representations will be fused by a high-level fusion layer. Using more generalized cross-validation settings, the proposed method is evaluated on two publicly available datasets DEAP and MAHNOB-HCI. The performance of the proposed network is compared with prior reported methods such as SVM, KNN, FBFgMDM, FBTSC, Unsupervised learning, DeepConvNet, ShallowConvNet, and EEGNet. TSception achieves higher classification accuracies and F1 scores than other methods in most of the experiments. The codes are available at https://github.com/yi-ding-cs/TSception

翻译：高时间分辨率和不对称空间激活是大脑情感过程背后电子脑图(EEG)的基本特征。为了了解EEG的时间动态和空间不对称,以准确和普遍的情感识别为目的,我们建议Tsception,这是一个多尺度的进化神经网络,可以对EEG的情感进行分类。Tscion,一个多尺度的进化神经网络,可以对来自EEG的情感进行分类。Tseption由动态的时空、空间不对称和高层次的聚合层组成,同时学习时间和频道层面的歧视性表现。动态时间层由与EGeEG的取样率相关的多尺度1D共进化内核内核组成,其长度与EEEG的取样率相关,了解EEEG的动态时间和频率表现。不对称的空间层利用不对称的EEEGEGS模式, 学习全球和半球的分级。使用更为广泛的交叉校验环境,对两种公开的数据集 DEAP1 和MAHNOB-HI。拟议网络的运行情况与以前报告的方法进行了比较,例如SVBMEVM-SU-NU-CFNU-C-C-CON-CUDR-C-C-SOL-SOL-SOL-SOL-C-SDOL-SOL-SOL-SOL-SDVDR AS-C-SDVDVDR-S-C-C-S-S-SDR-SDVDVDR-SDIS-TIS-TIS-TIS-C-SVDIS-TIS-TIS-TIS-TIS-TIS-TIS-TIS-TIS-TIS-TIS-TIS-TIS-TIS-TIS-TIS-TF-S-TVDVDF-S-S-TVDVG-TVDVDG-TVDV-SV-SVDV-TF-SA-TF-S-S-S-S-S-S-TIS-TIS-TIS-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S