Stress Prediction in Working Employees using Artificial Intelligence of Things

Abstract

Stress issues are a common issue among today's working IT professionals. As people's lifestyles and workplace cultures change, employees are more prone to encounter stress. In this project, we will use IoT and machine learning approach like supervised learning to examine stress in working employees. After proper data cleaning and preprocessing, we used a variety of Machine Learning approaches like KNN, Decision Tree and Naïve Bayes algorithm to train our model. The accuracy of the above-mentioned models was determined and compared. Among the models used, KNN Algorithm had the best accuracy. Significant factors that affect stress were found using KNN, Decision Tree, and Naive Bayes algorithms. With these findings, organizations can set their sights on reducing stress and providing a much more comfortable working environment for their employees.