Channel Division Based Multiple Classifiers Fusion for Emotion Recognition Using EEG signals

Abstract

Abstract.With the rapid development of computer technology, pervasive computing and wearable devices, EEG-based emotion recognition has gradually attracted much attention in affecting computing (AC) domain. In this paper, we propose an approach of emotion recognition using EEG signals based on the weighted fusion of multiple base classifiers. These base classifiers based on SVM are constructed using a channel division mechanism according to the neuropsychological theory that different brain areas are differ in processing intensity of emotional information. The outputs of channel base classifiers are integrated by a weighted fusion strategy which is based on the confidence estimation on each emotional label by each base classifier. The evaluation on the DEAP dataset shows that our proposed multiple classifiers fusion method outperforms individual channel base classifiers and the feature fusion method for EEG-based emotion recognition.

A Multimodal Deep Log-Based User Experience (UX) Platform for UX Evaluation

“…In general, biometric sensors can detect emotional arousal and stress, motivation, and visual attention, states that have a direct relationship with user cognitive and affective conditions [ 3 ]. For instance, an eye tracker can detect visual attention [ 19 , 20 , 21 ], electroencephalography (EEG) can detect user motivations and emotional responses [ 22 , 23 , 24 ], the galvanic skin response (GSR) can measure stress and arousal through skin conductivity [ 25 , 26 ], and electrocardiogram (ECG) and electromyogram (EMG) can measure stress levels and muscle-arousing activities [ 27 , 28 ]. However, existing research has focused on limited methods and techniques to uncover the true experience of a user employing a product.…”

Two Stepped Majority Voting for Efficient EEG based Emotion Classification

“…The second-best accuracy score was also produced by the proposed method. Huang et al, Al-Nafjan et al, Zhang et al, and Li et al reported accuracy scores among 80.0% and 85.0% respectively (Huang et al, 2012;Al-Nafjan et al, 2017;Zhang et al, 2013;Li et al, 2017;). Atkinson et al, Tripathi et al, and Zhuang et al reported accuracy scores in the range of 70.0% and 75.0% respectively (Atkinson et al, 2016;Tripathi et al, 2017;Zhu Zhuang et al, 2017).…”

“…2 (b), (c), (d), (e) and (f) shows the alpha, beta, gamma, theta and delta rhythms of the sampled EEG signal, respectively. The alpha, beta, theta and delta rhythms were further used as suggested in (Chao et al, 2019;Li et al, 2017).…”

“…Alzarzi et al produced a second-best accuracy score where the accuracy was 85.8% (Alazrai et al, 2018). Abeer et al, Tripathi et al and Li et al reported 82.0%, 81.4% and 80.7% accuracy scores, respectively (Al-Nafjan et al, 2017;Tripathi et al, 2017;Li et al, 2017). Rozgić et al, Zhang et al, and Atkinson et al reported accuracy scores among 70.0% and 80.0% and Zhuang et al, Huang et al, and Chandra et al reported achievements between 60.0% and 70.0% (Rozgić et al, 2013;Zhang et al, 2013;Atkinson et al, 2016;Zhu Zhuang et al, 2017;Huang et al, 2012;Candra et al, 2015).…”

“…The SVM classifier was used on the DEAP dataset and satisfactory results were reported. Li et al achieved EEG based emotions recognition that was based on an ensemble of SVM classifiers (Li et al, 2017). A weighted fusion scheme was considered to construct the ensemble structure.…”