School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, People's Republic of China.
J Neural Eng. 2022 Apr 14;19(2). doi: 10.1088/1741-2552/ac63ec.
. To take full advantage of both labeled data and unlabeled ones, the Graph Convolutional Network (GCN) was introduced in electroencephalography (EEG) based emotion recognition to achieve feature propagation. However, a single feature cannot represent the emotional state entirely and precisely due to the instability of the EEG signal and the complexity of the emotional state. In addition, the noise existing in the graph may affect the performance greatly. To solve these problems, it was necessary to introduce feature/similarity fusion and noise reduction strategies.. A semi-supervised EEG emotion recognition model combining graph fusion, network enhancement, and feature fusion was proposed. Firstly, different features were extracted from EEG and then compacted by Principal Component Analysis (PCA), respectively. Secondly, a Sample-by-sample Similarity Matrix (SSM) was constructed based on each feature, and similarity network fusion (SNF) was adopted to fuse the graphs corresponding to different SSMs to take advantage of their complementarity. Then, Network Enhancement (NE) was performed on the fused graph to reduce the noise in it. Finally, GCN was performed on the concatenated features and the enhanced fused graph to achieve feature propagation.. Experimental results demonstrated that: (a) When 5.30%of SEED and 7.20%of SEED-IV samples were chosen as the labeled samples, respectively, the minimum classification accuracy improvement achieved by the proposed scheme over state-of-the-art schemes were 1.52%on SEED and 13.14%on SEED-IV, respectively. (b) When 8.00%of SEED and 9.60%of SEED-IV samples were chosen as the labeled samples, respectively, the minimum training time reduction achieved by the proposed scheme over state-of-the-art schemes were 46.75 s and 22.55 s, respectively. (c) Graph fusion, network enhancement, and feature fusion all contributed to the performance enhancement. (d) The key hyperparameters that affect the performance were relatively few and easy to set to obtain outstanding performance.. This paper demonstrated that the combination of graph fusion, network enhancement, and feature fusion help to enhance GCN-based EEG emotion recognition.
. 为了充分利用有标签数据和无标签数据，在基于脑电图（EEG）的情绪识别中引入了图卷积网络（GCN）以实现特征传播。然而，由于 EEG 信号的不稳定性和情绪状态的复杂性，单个特征不能完全准确地表示情绪状态。此外，图中存在的噪声可能会极大地影响性能。为了解决这些问题，有必要引入特征/相似性融合和降噪策略。提出了一种结合图融合、网络增强和特征融合的半监督 EEG 情绪识别模型。首先，从 EEG 中提取不同的特征，然后分别通过主成分分析（PCA）进行压缩。其次，基于每个特征构建一个样本对相似性矩阵（SSM），并采用相似性网络融合（SNF）融合对应于不同 SSM 的图，以利用它们的互补性。然后，在融合图上进行网络增强（NE）以减少其中的噪声。最后，在拼接特征和增强融合图上执行 GCN 以实现特征传播。实验结果表明：（a）当选择 SEED 和 SEED-IV 的 5.30%和 7.20%的样本作为有标签样本时，与最先进的方案相比，所提出的方案在 SEED 和 SEED-IV 上的最小分类准确率提高分别为 1.52%和 13.14%。（b）当选择 SEED 和 SEED-IV 的 8.00%和 9.60%的样本作为有标签样本时，与最先进的方案相比，所提出的方案在 SEED 和 SEED-IV 上的最小训练时间减少分别为 46.75s 和 22.55s。（c）图融合、网络增强和特征融合都有助于提高性能。（d）影响性能的关键超参数相对较少，易于设置以获得出色的性能。本文证明了图融合、网络增强和特征融合的结合有助于增强基于 GCN 的 EEG 情绪识别。
