MGFKD: A semi-supervised multi-source domain adaptation algorithm for cross-subject EEG emotion recognition

• Published in: Brain research bulletin Vol. 208; p. 110901
• Main Authors: Zhang, Rui, Guo, Huifeng, Xu, Zongxin, Hu, Yuxia, Chen, Mingming, Zhang, Lipeng
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.03.2024; Elsevier
• Subjects: Algorithms; Electroencephalography; Emotion recognition; Emotions; Golden subjects; Humans; Negative transfer; Recognition, Psychology; Semi-supervised domain adaptation algorithm; Transfer learning; Emotion recognition; Golden subjects; Negative transfer; Semi-supervised domain adaptation algorithm; Transfer learning
• DOI: 10.1016/j.brainresbull.2024.110901
• ISSN: 0361-9230; 1873-2747

Currently, most models rarely consider the negative transfer problem in the research field of cross-subject EEG emotion recognition. To solve this problem, this paper proposes a semi-supervised domain adaptive algorithm based on few labeled samples of target subject, which called multi-domain geodesic flow kernel dynamic distribution alignment (MGFKD). It consists of three modules: 1) GFK common feature extractor: projects the feature distribution of source and target subjects to the Grassmann manifold space, and obtains the latent common features of the two feature distributions through GFK method. 2) Source domain selector: obtains pseudo-labels of the target subject through weak classifier, finds "golden source subjects" by using few known labels of target subjects. 3) Label corrector: uses a dynamic distribution balance strategy to correct the pseudo-labels of the target subject. We conducted comparison experiments on the SEED and SEED-IV datasets, and the results show that MGFKD outperforms unsupervised and semi-supervised domain adaptation algorithms, achieving an average accuracy of 87.51±7.68% and 68.79±8.25% on the SEED and SEED-IV datasets with only one labeled sample per video for target subject. Especially when the number of source domains is set as 6 and the number of known labels is set as 5, the accuracy increase to 90.20±7.57% and 69.99±7.38%, respectively. The above results prove that our proposed algorithm can efficiently and quickly improve the cross-subject EEG emotion classification performance. Since it only need a small number of labeled samples of new subjects, making it has strong application value in future EEG-based emotion recognition applications. •A semi-supervised DA algorithm for cross-subject emotion recognition is proposed.•The proposed algorithm achieves higher accuracy in SEED and SEED-IV datasets.•It is a non-deep learning method with strong interpretability and short running time.•It could build efficient emotion decoding model for new subject quickly in real-life.