Research on EEG emotion recognition based on CNN+BiLSTM+self-attention model
CSTR:
Author:
Affiliation:

1. School of Integrated Circuit Science and Engineering, Tianjin University of Technology, Tianjin 300384, China;2. China France BOHAI Geoservices Co., Ltd., Tianjin 300457, China;3. China Electronics Cloud Brain (Tianjin) Technology Co., Ltd., Tianjin, China;4. Institute of Motion Analysis and Research, University of Dundee, Scotland DD14HN, UK

  • Article
  • | |
  • Metrics
  • |
  • Reference [5]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    To address the problems of insufficient dimensionality of electroencephalogram (EEG) feature extraction, the tendency to ignore the importance of different sequential data segments, and the poor generalization ability of the model in EEG based emotion recognition, the model of convolutional neural network and bi-directional long short-term memory and self-attention (CNN+BiLSTM+self-attention) is proposed. This model uses convolutional neural network (CNN) to extract more distinctive features from both spatial and temporal dimensions. The bi-directional long short-term memory (BiLSTM) is used to further preserve the long-term dependencies between the temporal phases of sequential data. The self-attention mechanism can change the weights of different channels to extract and highlight important information and address the often-ignored importance of different channels and samples when extracting EEG features. The subject-dependent experiment and subject-independent experiment are performed on the database for emotion analysis using physiological signals (DEAP) and collected datasets to verify the recognition performance. The experimental results show that the model proposed in this paper has excellent recognition performance and generalization ability.

    Reference
    [1] IBRAHIM A, ELIJAH O, OMOBOLAJI F O. Performance evaluation of different support vector machine kernels for face emotion recognition[C]//2015 SAI Intelligent Systems Conference (IntelliSys), November 10-11, 2015, London, UK. New York:IEEE, 2015:15670349.
    [2] WEI C, CHEN L L, SONG Z Z, et al. EEG-based emotion recognition using simple recurrent units network and ensemble learning[J]. Biomedical signal processing and control, 2020, 58(3):101756.
    [3] SORAIA M A, MANUE J F. Emotions recognition using EEG signals:a survey[J]. IEEE transactions on affective computing, 2019, 10(3):374-393.
    [4] GAO Y Y, SUN X Y, MENG M, et al. EEG emotion recognition based on enhanced SPD matrix and manifold dimensionality reduction[J]. Computers in biology and medicine, 2022, 146(3):105606.
    [5] RAHUL S, RAM B P, PRADIP S. Automated emotion recognition based on higher order statistics and deep learning algorithm[J]. Biomedical signal processing and
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

LI Xueqing, LI Penghai, FANG Zhendong, CHENG Longlong, WANG Zhiyong, WANG Weijie. Research on EEG emotion recognition based on CNN+BiLSTM+self-attention model[J]. Optoelectronics Letters,2023,19(8):506-512

Copy
Share
Article Metrics
  • Abstract:568
  • PDF: 487
  • HTML: 0
  • Cited by: 0
History
  • Received:December 05,2022
  • Revised:January 13,2023
  • Online: August 22,2023
Article QR Code