Intelligent Emotion Detection Method Based on Deep Learning in Medical and Health Data

• Published in: IEEE access 2020, Vol.8, p.3802-3811
• Main Authors: Xu, Jianqiang, Hu, Zhujiao, Zou, Junzhong, Bi, Anqi
• Format: Article
• Language: English
• Subjects: Biological neural networks; Convolution; Convolutional codes; Deep learning; Electrocardiography; Emotion detection model; emotional text features; Emotions; Fatigue; Feature extraction; intelligent data analysis; Machine learning; medical health; Modal data; Model accuracy; multi-channel convolutional aotoencoder (MCAE); Neural networks
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2961139

Emotional abnormality may be brought out by physiological fatigue. In order to solve the problem, an emotion detection method based on deep learning in medical and health data is proposed in this paper. First of all, the related content of emotional fatigue is studied. The concept and the classification of emotional fatigue are introduced. Then, a multi-modal data emotional fatigue detection system is designed. In the system, multi-channel convolutional aotoencoder neural network is used to extract electrocardiograms (ECG) data features and emotional text features for emotional fatigue detection. Secondly, the network structure of learning ECG features by multi-channel convolutional aotoencoder model is introduced in detail. And the network structure of learning emotional text features by convolutional aotoencoder model is also described in detail. Finally, multi-modal data features are combined for emotional detection. It is shown by the experimental results that the proposed model has an average accuracy of more than 85% in predicting emotional fatigue.