AUTHOR=Dan Yufang , Tao Jianwen , Fu Jianjing , Zhou Di 

TITLE=Possibilistic Clustering-Promoting Semi-Supervised Learning for EEG-Based Emotion Recognition

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 15 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2021.690044

DOI=10.3389/fnins.2021.690044

ISSN=1662-453X

ABSTRACT=The purpose of the latest brain computer interface(BCI) is to perform accurate emotion recognition through the customized their recognizers to each subject. In the field of machine learning, graph-based semi-supervised learning has attracted more and more attention due to its intuitive and good learning performance for emotion recognition. However, each individual subject may present noise or outlier EEG patterns in the same scenario, the existing GSSL methods are sensitive or not enough robust to noise or outlier EEG-based data. To address the problem, in this paper, we invent a Possibilistic Clustering-Promoting semi-supervised learning for EEG-based Emotion Recognition (PCP-ER). Specifically, it constrains each instance to have the same label membership value with its local weighted mean (LWM), so as to improve the reliability of the recognition method. In addition, a regularization term about fuzzy entropy is introduced into the objective function, and the generalization ability of membership function is enhanced by increasing the amount of sample discrimination information, which improves the robustness of the method to noise and outlier. A large number of experimental results on the three real datasets (i.e., DEAP, SEED and SEED-IV) show that the proposed method improves the reliability and robustness of the EEG emotion recognition.