Sparsity constrained differential evolution enabled feature-channel-sample hybrid selection for daily-life EEG emotion recognition

Electroencephalography (EEG) reflects the activities of human brain and it can represent different emotional states to provide impersonal scientific evidence for daily-life emotional health monitoring. However, traditional multi-channel EEG sensing contains irrelevant or even interferential features, channels or samples, leading to redundant data and hardware complexity. This paper proposes a feature-channel-sample hybrid selection method to improve the channel selection, feature extraction and classification scheme for daily-life EEG emotion recognition. The features and channels are selected in pair with sparsity constrained differential evolution where the feature-channel pairs are optimized synchronously in the global search. Furthermore, the distance evaluation is carried out to remove abnormal samples to improve the emotion recognition accuracy. Therefore, efficient feature vectors for valence-arousal classification can be obtained by a small number of sparsely distributed channels. The experiments are based on the widely-used emotion recognition database DEAP and generate a feature-channel-sample hybrid selection scheme with optimized parameter settings. It can be derived that the proposed method can reduce the EEG channels sharply and maintain a relatively high accuracy compared with the related work. Furthermore, by applying this optimal scheme in practice, the real-scene daily-life EEG emotion recognition experiments are carried out on a sparsity constrained web-enabled system and a 10-fold cross validation is organized to confirm the performance. In conclusion, this paper provides a practical and efficient hardware configuration and feature-channel-sample optimal selection scheme for daily-life EEG emotion recognition.