FURI | Spring 2022
Analyzing the Features and Efficacy of Classification Models for Physiological Stress Prediction
Stress prediction in law enforcement can serve to better prepare officers for the intensity of their work. To further understand the physiological triggers that induce stress, the use of machine learning can determine the patterns in which stress is likely to occur. However, current models should be improved upon to provide more accurate results. This study seeks to evaluate the accuracy of common supervised classification algorithms, discover the features that most impact anxiety, and propose potential new models to better predict future stressful periods given data collected from edge devices.
Hometown: Phoenix, Arizona, United States
Graduation date: Spring 2025