Emotional Stress Detection Using the Variance of Deep Convolutional Neural Network (DCNN) Analysis Using Facial Images

Abstract

Emotional stress is a common issue that can have negative impacts on an individual's health, productivity, and overall well-being. Detecting emotional stress in real-time can help provide timely interventions to alleviate its negative effects. This study aims to explore the effectiveness of using the variance of deep convolutional neural network (DCNN) for analysis of facial images for emotional stress detection. Four DCNN models, namely VGG16, ResNet50, AlexNet, and VGG19, were used to analyze facial images and measure their variance to detect emotional stress. The results showed that the variance of DCNN analysis of facial images is an effective method for detecting emotional stress. The study highlights the potential of using DCNN models for real-time emotional stress detection and can be applied in various fields, such as healthcare, education, and security, to detect emotional stress and provide timely interventions.