Stress Assessment with Convolutional Neural Network Using PPG Signals

TL;DR

This paper presents a novel CNN-MLP based model that uses raw PPG signals from wearable sensors to accurately detect stress, achieving 96.7% accuracy in distinguishing stressful from normal events.

Contribution

The study introduces an adaptive CNN combined with MLP for stress detection using raw PPG signals, demonstrating high accuracy on a public dataset.

Findings

Achieved 96.7% accuracy in stress detection.

Utilized raw PPG signals from wearable sensors.

Validated model on the publicly available WESAD dataset.

Abstract

Stress is one of the main issues of nowadays lifestyle. If it becomes chronic it can have adverse effects on the human body. Thus, the early detection of stress is crucial to prevent its hurting effects on the human body and have a healthier life. Stress can be assessed using physiological signals. To this end, Photoplethysmography (PPG) is one of the most favorable physiological signals for stress assessment. This research is focused on developing a novel technique to assess stressful events using raw PPG signals recorded by Empatica E4 sensor. To achieve this goal, an adaptive convolutional neural network (CNN) combined with Multilayer Perceptron (MLP) has been utilized to realize the detection of stressful events. This research will use a dataset that is publicly available and named wearable stress and effect detection (WESAD). This dataset will be used to simulate the proposed model and to examine the advantages of the proposed developed model. The proposed model in this research will be able to distinguish between normal events and stressful events. This model will be able to detect stressful events with an accuracy of 96.7%.