A Novel Deep-Learning based Framework for Multi-Subject Emotion Recognition

作者：Qiao, Rui; Qing, Chunmei; Zhang, Tong; Xing, Xiaofen; Xu, Xiangmin^*

来源：4th International Conference on Information, Cybernetics and Computational Social Systems (ICCSS), 2017-07-24 To 2017-07-26.

DOI：10.1109/ICCSS.2017.8091408

• Affective Computing
• Electroencephalogram signals
• Emotion classification
• Emotion recognition
• Generalization ability
• High-level features
• Subject recognition
• Traditional approaches

Electroencephalogram (EEG) signal based emotion recognition, as a challenging pattern recognition task, has attracted more and more attention in recent years and widely used in medical, Affective Computing and other fields. Traditional approaches often lack of the high-level features and the generalization ability is poor, which are difficult to apply to the practical application. In this paper, we proposed a novel model for multi-subject emotion classification. The basic idea is to extract the high-level features through the deep learning model and transform traditional subject-independent recognition tasks into multi-subject recognition tasks. Experiments are carried out on the DEAP dataset, and our results demonstrate the effectiveness of the proposed method.

• 出版日期2017
• 单位华南理工大学