A prototype-based SPD matrix network for domain adaptation EEG emotion recognition

Emotion plays a vital role in human daily life, and EEG signals are widely used in emotion recognition. Due to individual variability, training a generic emotion recognition model across different subjects is difficult. The conventional method involves the collection of a large amount of calibration data to build subject-specific models. Recently, developing an effective brain-computer interface with a short calibra-tion time has become a challenge. To solve this problem, we propose a domain adaptation SPD matrix network (daSPDnet) that can successfully capture an intrinsic emotional representation shared between different subjects. Our method jointly exploits feature adaptation with distribution confusion and sample adaptation with centroid alignment. We compute the SPD matrix based on the covariance as a feature and make a novel attempt to combine prototype learning with the Riemannian metric. Extensive experiments are conducted on the DREAMER and DEAP datasets, and the results show the superiority of our proposed method. (c) 2020 Elsevier Ltd. All rights reserved.

Automated summary

Emotion is crucial in human daily life, with EEG signals widely used in emotion recognition. However, training a generic emotion recognition model across different subjects is challenging due to individual variability. To address this, a domain adaptation SPD matrix network was proposed to capture shared emotional representations between subjects.