Emotion Recognition Based on Dynamic Energy Features Using a Bi-LSTM Network

• Published in: Frontiers in computational neuroscience Vol. 15; p. 741086
• Main Authors: Zhu, Meili, Wang, Qingqing, Luo, Jianglin
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 21.02.2022; Frontiers Media S.A
• Subjects: Bi-LSTM; Datasets; Deep learning; dynamic energy feature; EEG; Electroencephalography; emotion recognition; Emotions; Energy; energy sequence; Long short-term memory; Neural networks; Neuroscience; Noise reduction; Switzerland; Bi-LSTM; energy sequence; emotion recognition; EEG; dynamic energy feature
• ISSN: 1662-5188; 1662-5188
• DOI: 10.3389/fncom.2021.741086

Among electroencephalogram (EEG) signal emotion recognition methods based on deep learning, most methods have difficulty in using a high-quality model due to the low resolution and the small sample size of EEG images. To solve this problem, this study proposes a deep network model based on dynamic e...