Predicting human's stress level while sleeping using XGBoost

Monitoring stress levels during sleep provides valuable insights into an individual’s mental and physical well-being. In this study, we present a machine learning-based approach to classify human stress levels while sleeping using the XGBoost algorithm. The dataset used includes physiological and behavioral features collected during sleep sessions, such as heart rate, movement, and other biometric indicators. After preprocessing and feature extraction, the XGBoost model was trained to classify discrete levels of stress, achieving promising results in terms of accuracy and robustness. The performance of the model was evaluated using cross-validation and key metrics including accuracy, precision, recall, and F۱-score. The results demonstrate that XGBoost is highly effective in capturing complex, non-linear relationships in the data, enabling reliable stress detection. This research highlights the potential of integrating machine learning models into wearable or bedside sleep monitoring systems for real-time stress analysis. Future work may include expanding the dataset, incorporating additional physiological signals, and comparing with deep learning approaches.

کلیدواژه ها:

Stress detection ، XGBoost ، Sleep monitoring ، Machine learning ، Physiological signals ، Mental health