Journal
PATTERN RECOGNITION
Volume 110, Issue -, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.patcog.2020.107626
Keywords
EEG; Emotion recognition; Domain adaptation; SPD matrix; Riemannian manifold; Prototype learning
Funding
- National Natural Science Foundation of China [61976209, 81701785]
- CAS International Collaboration Key Project [173211KYSB20190024]
- Strategic Priority Research Program of CAS [XDB32040000]
Ask authors/readers for more resources
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.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available