Multi-Classifier Fusion Based on MI–SFFS for Cross-Subject Emotion Recognition

• Published in: Entropy (Basel, Switzerland) Vol. 24; no. 5; p. 705
• Main Authors: Yang, Haihui, Huang, Shiguo, Guo, Shengwei, Sun, Guobing
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 16.05.2022; MDPI
• Subjects: Accuracy; Affective computing; Algorithms; Artificial intelligence; Asymmetry; Brain research; Channels; Classification; Classifiers; cross-subject; Datasets; Discriminant analysis; Electroencephalography; Emotion recognition; Emotions; Entropy; Experiments; Feature extraction; Information theory; Machine learning; Multi-Classifier Fusion; mutual information; Physiology; Researchers; SFFS; Splicing; Support vector machines; Multi-Classifier Fusion; mutual information; cross-subject; emotion recognition; SFFS
• DOI: 10.3390/e24050705
• ISSN: 1099-4300

With the widespread use of emotion recognition, cross-subject emotion recognition based on EEG signals has become a hot topic in affective computing. Electroencephalography (EEG) can be used to detect the brain’s electrical activity associated with different emotions. The aim of this research is to improve the accuracy by enhancing the generalization of features. A Multi-Classifier Fusion method based on mutual information with sequential forward floating selection (MI_SFFS) is proposed. The dataset used in this paper is DEAP, which is a multi-modal open dataset containing 32 EEG channels and multiple other physiological signals. First, high-dimensional features are extracted from 15 EEG channels of DEAP after using a 10 s time window for data slicing. Second, MI and SFFS are integrated as a novel feature-selection method. Then, support vector machine (SVM), k-nearest neighbor (KNN) and random forest (RF) are employed to classify positive and negative emotions to obtain the output probabilities of classifiers as weighted features for further classification. To evaluate the model performance, leave-one-out cross-validation is adopted. Finally, cross-subject classification accuracies of 0.7089, 0.7106 and 0.7361 are achieved by the SVM, KNN and RF classifiers, respectively. The results demonstrate the feasibility of the model by splicing different classifiers’ output probabilities as a portion of the weighted features.