A kurtosis-based channel selection method combined with a convolutional neural network achieved classification accuracies of 79.03% for valence and 79.36% for arousal, reducing computational complexity by 89% compared to using all channels.
Does a kurtosis-based channel selection method with a CNN improve the classification accuracy and computational efficiency of self-induced emotion recognition using EEG?
A kurtosis-based channel selection method combined with a CNN effectively classifies self-induced emotions from EEG signals while significantly reducing computational complexity.
Absolute Event Rate: 79.03% vs 72.37%
Emotion recognition from electroencephalogram (EEG) signals requires accurate and efficient signal processing and feature extraction. Deep learning technology has enabled the automatic extraction of raw EEG signal features that contribute to classifying emotions more accurately. Despite such advances, classification of emotions from EEG signals, especially recorded during recalling specific memories or imagining emotional situations has not yet been investigated. In addition, high-density EEG signal classification using deep neural networks faces challenges, such as high computational complexity, redundant channels, and low accuracy. To address these problems, we evaluate the effects of using a simple channel selection method for classifying self-induced emotions based on deep learning. The experiments demonstrate that selecting key channels based on signal statistics can reduce the computational complexity by 89% without decreasing the classification accuracy. The channel selection method with the highest accuracy was the kurtosis-based method, which achieved accuracies of 79.03% and 79.36% for the valence and arousal scales, respectively. The experimental results show that the proposed framework outperforms conventional methods, even though it uses fewer channels. Our proposed method can be beneficial for the effective use of EEG signals in practical applications.
Ji et al. (Fri,) conducted a other in Self-induced emotion (n=29). Kurtosis-based channel selection with Convolutional Neural Network vs. Baseline using all EEG channels (1-50 Hz) was evaluated on Classification accuracy for the valence scale. A kurtosis-based channel selection method combined with a convolutional neural network achieved classification accuracies of 79.03% for valence and 79.36% for arousal, reducing computational complexity by 89% compared to using all channels.