Stress detection using Convolutional Neural Network and Gramian Angular Field images
The human body is designed to experience stress and react to it and experiencing challenges causes our body to produce physical and mental responses and also helps our body to adjust to new situations. But stress becomes a problem when it continues to remain without a period of relaxation or relief. When a person has long-term stress, continued activation of the stress response causes wear and tear on the body. Chronic stress results in cancer, cardiovascular disease, depression, and diabetes, and thus is deeply detrimental to our health. The experiment is being done on two standard benchmark datasets namely, WESAD(Wearable Stress and Affect Detection) [1] and the SWELL [2]. During the studies, training accuracies of 99% and testing accuracy of over 94.8% and 99.39% are being achieved for both the WESAD and SWELL datasets respectively. For the WESAD dataset, the chest data has been taken for the experiment including the data of sensor modalities like three-axis acceleration (ACC), electrocardiogram (ECG), body temperature (TEMP), respiration (RESP) etc.
Dataset link:
https://archive.ics.uci.edu/ml/datasets/WESAD+%28Wearable+Stress+and+Affect+Detection%29 for WESAD
https://www.kaggle.com/datasets/qiriro/swell-heart-rate-variability-hrv for SWELL