Optimizing Athletic Performance Through Personalized Sleep Monitoring

Recent advances in digital health, particularly the integration of Machine Learning, edge computing, and cloud systems, are revolutionizing healthcare, personal well-being, and athletic performance through continuous, real-time monitoring and personalized recommendations. This study focuses on a cyber-physical system to monitor sleep quality, emphasizing the influence of environmental factors like temperature, humidity, light, and noise. By combining Internet of Things (IoT) and Machine Learning models, the system collects and processes data to provide actionable insights for optimizing the sleep environment. Data were gathered over one month using a custom Arduino-based system and a Garmin wearable device. Statistical analyses revealed significant correlations between environmental conditions and sleep quality, and Machine Learning models were developed to predict sleep scores based on these factors. The system not only offers insights for improving sleep quality but also holds potential for enhancing athletic performance, recovery, and injury prevention. Athletes can use such a system to tailor their environments for optimal rest, essential for peak performance during training and competitions. This work lays the foundation for integrating such systems into smart home environments, offering a scalable, real-time approach to enhancing personal well-being, particularly in sports contexts.