Evaluation of Machine Learning Classifiers for Stress Detection Using Multimodal Physiological Data

Stress detection using physiological signals has gained significant attention in recent years due to its applications in healthcare, workplace monitoring, and human–computer interaction. This study investigates and compares the performance of two widely used machine learning approaches—Support Vector Machines (SVM) and Artificial Neural Networks (ANN)—for stress recognition from multimodal physiological data. Relevant features such as heart rate, heart rate variability, galvanic skin response, respiration rate, skin temperature, and physical activity levels were extracted from secondary datasets. The data were preprocessed and standardized before model training. Both classifiers were evaluated using metrics including accuracy, precision, recall, F1-score, and the area under the ROC curve (AUC). Experimental results indicate that both SVM and ANN achieve high classification performance, with the SVM model demonstrating slightly higher precision and AUC, while the ANN exhibited stronger recall. The comparative analysis highlights the potential of both techniques for reliable stress detection, providing valuable insights for selecting appropriate algorithms in real-world applications.

Hali tarjima qilinmagan