Islam Monira, Lee Tan
Department of Electrical and Electronic Engineering, Khulna University of Engineering & Technology, Khulna, 9203, Bangladesh.
Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, New Territory, Hong Kong.
Brain Inform. 2025 Aug 2;12(1):19. doi: 10.1186/s40708-025-00265-y.
Emotion is an integral part of human cognitive processes and behaviors. Automatic detection and classification of human emotion has been a goal of applied research. This study presents an approach to detecting emotion from multivariate electroencephalogram (EEG) with signal processing methods applied in the temporal, spectral, and spatial domains. In this work, the noise-assisted multivariate empirical mode decomposition (NA-MEMD) is applied to EEG to extract a set of narrow-band intrinsic mode functions (IMF), upon which spectral analysis and spatial connectivity analysis are performed. Applying Hilbert spectral analysis to those IMFs results in the marginal Hilbert spectrum (MHS). MHS is computed for each EEG channel to obtain the spectral energy of each segment. The spectral energy across multiple EEG channels within the same segment is aggregated while the consecutive frames are stacked to give spectral-temporal feature representation. Again, connectivity analysis is performed at each instant with a non-linear measure named phase locking value (PLV) to construct the connectivity map containing spatial-temporal features. A 2D CNN-BiLSTM is adopted to perform emotion detection with the MHS and the PLV features. On classifying high versus low states in valence, arousal, dominance, and liking, PLV showed better performance than MHS with 97.61%, 96.09%, 96.75%, and 97.23% accuracy, respectively, for DEAP dataset. Meanwhile, the highest accuracy of 94.71% is attained on 4-class task. PLV of high oscillatory IMFs outperforms the reported systems with conventional EEG features.
情感是人类认知过程和行为的一个组成部分。人类情感的自动检测和分类一直是应用研究的一个目标。本研究提出了一种利用在时间、频谱和空间域中应用的信号处理方法从多变量脑电图（EEG）中检测情感的方法。在这项工作中，将噪声辅助多变量经验模式分解（NA-MEMD）应用于EEG，以提取一组窄带固有模式函数（IMF），并在此基础上进行频谱分析和空间连通性分析。对这些IMF应用希尔伯特频谱分析得到边际希尔伯特谱（MHS）。计算每个EEG通道的MHS以获得每个片段的频谱能量。同一片段内多个EEG通道的频谱能量进行聚合，同时将连续的帧堆叠起来以给出频谱-时间特征表示。同样，在每个时刻使用一种名为锁相值（PLV）的非线性度量进行连通性分析，以构建包含时空特征的连通性图。采用二维卷积神经网络-双向长短期记忆网络（2D CNN-BiLSTM）利用MHS和PLV特征进行情感检测。在对效价、唤醒度、优势度和喜爱度的高状态与低状态进行分类时，对于DEAP数据集，PLV分别以97.61%、96.09%、96.75%和97.23%的准确率表现优于MHS。同时，在4类任务上达到了94.71%的最高准确率。高振荡IMF的PLV优于具有传统EEG特征的已报道系统。
