Emotion Classification Using EEG Brain Signals and the Broad Learning System
Sali Issa, Qinmu Peng and You Xinge
Abstract—This paper presents a new user-independent emotion classification method that classifies four distinct emotions using EEG brain signals and the Broad Learning System (BLS). The public DEAP and MAHNOB-HCI databases are used. Just one EEG electrode channel is selected for the feature extraction process, Continuous Wavelet Transform (CWT) is then utilized to extract the proposed Gray-Scale Image (GSI) feature which describes the EEG brain activation in both time and frequency domains. Finally, the new Broad Learning System (BLS) is constructed for the emotion classification process, which successfully upgrades the efficiency of emotion classification based on EEG brain signals. Experiment results show that the proposed work produces a robust system with high accuracy of approximately 94.12% and training process time of approximately 0.66 s for DEAP database, as well as, high accuracy of approximately 93.05% and training process time of approximately 0.5 s for MAHNOB-HCI database.
For any questions, suggestions or cooperations, please feel free to contact ours,
Sali Issa : I201622211@hust.edu.cn
Qinmu Peng : email@example.com