P3-MSDA: Multi-Source Domain Adaptation Network for Dynamic Visual Target Detection.

Single-trial EEG detection has been widely applied to brain-computer interface (BCI) systems. Moreover, an individual generalized model is significant for applying the dynamic visual target detection BCI system to real life due to the time jitter of the detection latency, the dynamics and complexity of visual background. Hence, we developed an unsupervised multi-source domain adaptation network (P3-MSDA) for the dynamic visual target detection. In this network, a P3 map-clustering method was proposed for the source domain selection. The adversarial domain adaptation was conducted for domain alignment to eliminate individual differences, and prediction probabilities were ranked and returned to guide the input of target samples for the imbalanced data classification. The results showed that individuals with a strong P3 map selected by the proposed P3 map-clustering method perform best on the source domain. Compared with the existing schemes, the proposed P3-MSDA network achieved the highest classification accuracy and F1 score using five labelled individuals with a strong P3 map as the source domain. These findings can have a significant meaning in building an individual generalized model for the dynamic visual target detection.