Two Stepped Majority Voting for Efficient EEG based Emotion Classification

Abstract

In this paper, a novel approach that is based on two-stepped majority voting is proposed for efficient EEG based emotion classification. Emotion recognition is important for human-machine interactions. Facial-features and body-gestures based approaches have been generally proposed for emotion recognition. Recently, EEG based approaches become more popular in emotion recognition. In the proposed approach, the raw EEG signals are initially low-pass filtered for noise removal and band-pass filters are used for rhythms extraction. For each rhythm, the best performed EEG channels are determined based on wavelet-based entropy features and fractal dimension based features. The k-nearest neighbor (KNN) classifier is used in classification. The best five EEG channels are used in majority voting for getting the final predictions for each EEG rhythm. In the second majority voting step, the predictions from all rhythms are used to get a final prediction. The DEAP dataset is used in experiments and classification accuracy, sensitivity and specificity are used for performance evaluation metrics. The experiments are carried out to classify the emotions into two binary classes such as high valence (HV) vs low valence (LV) and high arousal (HA) vs low arousal (LA). The experiments show that 86.3% HV vs LV discrimination accuracy and 85.0% HA vs LA discrimination accuracy is obtained. The obtained results are also compared with some of the existing methods. The comparisons show that the proposed method has potential in the use of EEG based emotion classification.

Efficient approach for EEG‐based emotion recognition

“…Tripathi et al [7 ], and Zhu Zhuang et al [14 ] reported accuracy scores in the range of 70.0 and 75.0%, respectively. The worst accuracy score was also reported by Ismael et al [13 ].…”

“…Rozgić et al [11 ] and Zhang et al [8 ] reported accuracy scores among 76.9 and 75.2% and Zhu Zhuang et al [14 ] and Candra et al [10 ] reported achievements between 60.0 and 70.0%. The worst score 57.6% was reported by Ismael et al [13 ].…”

“…The EEG signals contain five rhythms namely, alpha, beta gamma, theta and delta, respectively. The ‘F3’ EEG channel and the delta rhythm was further considering [13 ]. The extracted EEG rhythm signals were converted to the EEG rhythm images by using the CWT method.…”

Sentiment recognition model of EEG signals combined with one-dimensional convolution and BiBASRU-AT

“…Many studies have shown that there is a certain emotional dependence between each channel [11][12], while the traditional recurrent network can only capture the characteristics of the timing of EEG signals, and lacks the modeling of the relationship between channels, resulting in Feature learning ability is limited. This paper combines self-attention and simple recurrent unit module [13] (Simple Recurrent Unit, SRU), and proposes a built-in self-attention simple recurrent unit (BASRU).…”