School of Computer Science and Technology, Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei, Anhui, People's Republic of China.
School of Biological Science and Medical Engineering, Key Laboratory of Child Development and Learning Science, Southeast University, Nanjing 210096, People's Republic of China.
Biomed Phys Eng Express. 2024 May 14;10(4). doi: 10.1088/2057-1976/ad43f1.
In this paper, we propose a novel multi-scale 3D-CRU model, with the goal of extracting more discriminative emotion feature from EEG signals. By concurrently exploiting the relative electrode locations and different frequency subbands of EEG signals, a three-dimensional feature representation is reconstructed wherein the Delta () frequency pattern is included. We employ a multi-scale approach, termed 3D-CRU, to concurrently extract frequency and spatial features at varying levels of granularity within each time segment. In the proposed 3D-CRU, we introduce a multi-scale 3D Convolutional Neural Network (3D-CNN) to effectively capture discriminative information embedded within the 3D feature representation. To model the temporal dynamics across consecutive time segments, we incorporate a Gated Recurrent Unit (GRU) module to extract temporal representations from the time series of combined frequency-spatial features. Ultimately, the 3D-CRU model yields a global feature representation, encompassing comprehensive information across time, frequency, and spatial domains. Numerous experimental assessments conducted on publicly available DEAP and SEED databases provide empirical evidence supporting the enhanced performance of our proposed model in the domain of emotion recognition. These findings underscore the efficacy of the features extracted by the proposed multi-scale 3D-GRU model, particularly with the incorporation of the Delta () frequency pattern. Specifically, on the DEAP dataset, the accuracy of Valence and Arousal are 93.12% and 94.31%, respectively, while on the SEED dataset, the accuracy is 92.25%.
在本文中，我们提出了一种新颖的多尺度 3D-CRU 模型，旨在从 EEG 信号中提取更具判别性的情感特征。通过同时利用 EEG 信号的相对电极位置和不同的频率子带，重建了一个包含 Delta（）频率模式的三维特征表示。我们采用了一种多尺度方法，称为 3D-CRU，在每个时间片段内的不同粒度级别上同时提取频率和空间特征。在提出的 3D-CRU 中，我们引入了一个多尺度 3D 卷积神经网络（3D-CNN），以有效地捕获嵌入在 3D 特征表示中的判别信息。为了对连续时间片段之间的时间动态进行建模，我们引入了一个门控循环单元（GRU）模块，从组合频率-空间特征的时间序列中提取时间表示。最终，3D-CRU 模型产生了一个全局特征表示，涵盖了时间、频率和空间域的全面信息。在公开可用的 DEAP 和 SEED 数据库上进行的大量实验评估提供了实证证据，支持我们提出的模型在情感识别领域的卓越性能。这些发现突出了所提出的多尺度 3D-GRU 模型提取的特征的有效性，特别是在包含 Delta（）频率模式的情况下。具体来说，在 DEAP 数据集上，效价和唤醒度的准确率分别为 93.12%和 94.31%，而在 SEED 数据集上，准确率为 92.25%。
