STRESS DETECTION USING DEEP LEARNING IN SOFTWARE DEVELOPMENT TEAMS

The study explores an approach to IT stress detection utilizing deep learning, specifically convolutional neural networks (CNNs), as well as traditional machine learning algorithms including decision trees (DT) and support vector machines (SVM). The research focuses on image processing techniques to extract relevant features from facial expressions and physiological signals indicative of stress. The proposed methodology involves data acquisition, preprocessing, and feature extraction to prepare the input data for model training. CNNs are employed to automatically learn discriminative features directly from the images, while DT and SVM models are trained on extracted features to compare their performance against the deep learning approach. Evaluation metrics such as accuracy, precision, recall, and F1 score are utilized to assess the effectiveness of each algorithm in stress detection. Additionally, the study explores the potential for ensemble methods to combine the strengths of multiple algorithms for improved performance. The results demonstrate the efficacy of deep learning CNNs in accurately identifying stress from image data, with insights into the comparative performance and potential synergies with traditional machine learning techniques. This research contributes to advancing the field of stress detection by leveraging state-of-the-art deep learning methodologies within the context of image processing.