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

作者：

Highlights：

• Using the SPD matrix as a feature in EEG emotion recognition.

• Using the prototype loss combined with the Riemannian metric to calculate the geometric mean.

• Transferring knowledge by feature adaptation with distribution confusion and sample adaptation with centroid alignment.

摘要

•Using the SPD matrix as a feature in EEG emotion recognition.•Using the prototype loss combined with the Riemannian metric to calculate the geometric mean.•Transferring knowledge by feature adaptation with distribution confusion and sample adaptation with centroid alignment.

论文关键词：EEG,Emotion recognition,Domain adaptation,SPD matrix,Riemannian manifold,Prototype learning

论文评审过程：Received 3 December 2019, Revised 5 August 2020, Accepted 29 August 2020, Available online 30 August 2020, Version of Record 10 September 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107626