Cross-Subject EEG-Based Emotion Recognition via Semisupervised Multisource Joint Distribution Adaptation

Most emotion recognition systems still present limited applicability to new users due to the inter-subject variability of electroencephalography (EEG) signals. Although domain adaptation methods have been adopted to tackle this problem, most methodologies deal with unlabeled data from a target subject. However, a few labeled samples from a target subject could also be included to boost cross-subject emotion recognition. In this paper, we present a semi-supervised domain adaptation framework to align the joint distributions of subjects, assuming that fine-grained structures must be aligned to perform a greater knowledge transfer. To achieve this, the proposed framework performs a multi-source alignment of features at subject level, while predictions are aligned over the global feature space. To support joint distribution alignment, inter-class separation and consistent predictions are ensured on the target subject. We perform experiments using two public benchmark datasets, SEED and SEED-IV, with two different sampling strategies to incorporate a few labeled samples from a target subject. Our proposal achieves an average accuracy of 93.55% and 87.96% on SEED and SEED-IV, using three labeled target samples of each class. Moreover, we obtained an average accuracy of 91.79% and 85.45% on SEED and SEED-IV by incorporating 10 labeled samples from the first EEG trial of each class.