MECAM: A Novel Multi-Axis EEG Channel Attention Model for Emotion Recognition

With the constant evolution of information technology, the paradigm of human-computer interaction has progressively transitioned from emphasizing command behavior to a novel approach that prioritizes natural language and emotional communication. In response to this trend, the development of an effective model for emotion recognition has become imperative. Consequently, this article introduces a novel multi-axis EEG channel attention model (MECAM) designed for emotion recognition. To enhance the model’s capabilities, we employ a split depth-wise convolution with a larger convolutional kernel, resulting in the creation of four parallel branches. This not only reduces the computational complexity but also expands the receptive field of the model. The incorporation of a multi-axis attention mechanism, capturing both global and local information from the output features of parallel branches, further elevates the network’s receptive field through the MBConv block. The primary objective of MECAM is to adeptly extract discriminative features from electroencephalogram (EEG) data, thereby enhancing the performance of emotion recognition. The model underwent rigorous validation using multiple datasets, including database for emission analysis using physical signals (DEAPs), SJTU emission EEG dataset (SEED), and SJTU emission EEG dataset with four emission (SEED-IV). In subject-dependent experiments, the accuracy of binary and ternary emotion classification tasks exceeded 95%, while the accuracy of the quaternary classification task surpassed 93%. In subject-independent experiments, the accuracy of most emotion classification tasks also exceeded 90%, with the exception of quaternary classification on DEAP, achieving an accuracy of 86.64%. The experimental results unequivocally underscore the superior performance of MECAM in EEG-based emotion recognition tasks.