Abstract
To satisfy the need to accurately monitor emotional stress, this paper explores the effectiveness of the attention mechanism based on the deep learning model CNN (Convolutional Neural Networks)-BiLSTM (Bi-directional Long Short-Term Memory) As different attention mechanisms can cause the framework to focus on different positions of the feature map, this discussion adds attention mechanisms to the CNN layer and the BiLSTM layer separately, and to both the CNN layer and BiLSTM layer simultaneously to generate different CNN–BiLSTM networks with attention mechanisms. ECG (electrocardiogram) data from 34 subjects were collected on the server platform created by the Institute of Psychology of the Chinese Academy of Science and the researches. It verifies that the average accuracy of CNN–BiLSTM is up to 0.865 without any attention mechanism, while the highest average accuracy of 0.868 is achieved using the CNN–attention–based BiLSTM.
Highlights
In today’s society, as greater psychological stress is experienced, people are more prone to suffer harm caused by that high stress
On the basis of proposing a network using CNN [14] and BiLSTM(Bi-directional Long Short-Term Memory), we added different attention mechanisms to the CNN and BiLSTM layers separately and to the whole network to explore the effectiveness of the attention mechanism for the task of identifying emotional stress based on ECG signals
To satisfy the need to accurately monitor emotional stress based on the ECG signal, we tried to add different attention mechanisms to the CNN and BiLSTM layers of a CNNBiLSTM network separately and to the whole network to explore the effectiveness of the attention mechanism
Summary
In today’s society, as greater psychological stress is experienced, people are more prone to suffer harm caused by that high stress. When humans suffer from stress, the sympathetic nervous system become excited and generates adrenal hormones, which cause the heart to beat faster and breathing to shorten. There is a lack of research on how to applicate attention mechanism in the subject of monitoring emotional stress based on physiological parameters. On the basis of proposing a network using CNN [14] and BiLSTM(Bi-directional Long Short-Term Memory), we added different attention mechanisms to the CNN and BiLSTM layers separately and to the whole network to explore the effectiveness of the attention mechanism for the task of identifying emotional stress based on ECG signals. To the best of our knowledge, this effort is the first where deep learning models were combined with attention mechanisms to detect psychological stress using ECG signals
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
