Machine Learning based Human Stress Detection through Sleep Patterns

Stress is a critical factor in overall wellbeing, and understanding its patterns during sleep can provide valuable insights into improving sleep quality and managing stress-related health issues. Stress has become an increasingly prevalent issue in modern society, impacting both mental and physical well-being. The ability to accurately detect stress levels in individuals is crucial for timely intervention and management. Sleep patterns serve as a valuable indicator of stress, as disruptions in sleep quality and duration often correlate with heightened stress levels. Leveraging advancements in machine learning techniques, this study proposes a novel linaer regression based approach to detect human stress by analyzing sleep patterns extracted from wearable devices. The proposed system consists of several key components. Firstly, data collection involves the continuous monitoring of sleep parameters such as sleep stages, heart rate variability, and movement using wearable sensors. Next, feature extraction techniques are applied to transform raw sleep data into informative features that capture relevant aspects of sleep patterns indicative of stress.