Analyzing Sleep Quality through Digital Data Insights and Soft Computing Methods for Enhanced Evaluation

The primary objective of the research is to evaluate the quantity of sleep by using actigraphy along with information generated from various devices. It defines typical sleep quality measurement instruments, such as survey forms, and discusses their benefits and downsides. Using soft computing methods and data acquired by commercialized smartwatches, this study starts by developing a novel way for measuring the quality of sleep without self-answered assessments. We offer three new sleep indices: SleepQualD for daily sleep quality, SleepQualWeek for weekly sleep quality, and SleepCons for consistency in sleep. These markers are generated from sleep characteristics measured by clinical actigraph devices and smartwatches, which provide a far more precise evaluation. Additionally, the purpose of this chapter is to comprehend the role of physical exercise and technological usage in assessing the quality of sleep. Additionally, the article discusses CNN and MLP, two deep learning and supervised machine learning methods, that were used to build the model that could predict the quality of sleep based on these variables. The results also back up the claim that wearable electronics and ML methods are crucial for improving the accuracy rate of CNN models and making objective predictions about sleep quality.