Panic detection through facial recognition paradigm using deep learning tools

Abstract

Recently, panic detection has become essential in security, healthcare, and human-computer interaction. Automatic panic detection (APD) systems are designed to monitor physiological signals and behavioral patterns in real-time to detect stress responses. APD is increasingly adopted across many sectors, including disaster preparedness, COVID-19, and terror attacks. Their integration with various applications reduces human efforts and saves costs. However, most studies rely on existing models with fewer new ones or techniques. This study proposes a vision-based panic detection model using MobileNet, ResNet, and convolutional neural network (CNN). The FER2013 dataset is used for the model training and testing. The results indicate that MobileNet is the most effective model for image-based panic detection across ten folds with an accuracy of 90%, recall of 96.9%, and mean accuracy of 0.032. MobileNet also showed a mean absolute error (MAE) between 0.02 and 0.04. This study has been to confirm MobileNet's suitability for image-based panic detection. The findings contribute to developing more reliable and accurate image-based panic detection systems in real-world applications. It offers valuable insights and lays the groundwork for future deep-leaning-based panic detection studies.