EAI Endorsed Transactions: AI Research

This research provides a thorough review of wearable health monitoring devices and explores their potential in managing individual health. The study emphasizes how wearables can assist in early detection of health issues and empower users to take control of their well-being. It also examines the application of various machine learning algorithms to determine the most suitable approach for different situations. The report suggests that incorporating artificial intelligence in the future could lead to more personalized health insights. Additionally, it stresses the need for continued research to enhance the impact of wearable health monitoring devices on individual health and wellness. The objective of this study is to evaluate the effectiveness of Random Forest, KNN, and Logistic Regression in health monitoring systems. The study compares these algorithms to draw clear conclusions on their suitability and examines how each handles the challenges of high-dimensional health data commonly encountered in monitoring systems. To ensure data quality, the study selects several health monitoring datasets and processes them accordingly. Performance metrics are used to evaluate the execution of the Random Forest, KNN, and Logistic Regression algorithms. The study analyzes how well each algorithm deals with high-dimensional data issues and assesses its ability to deliver clear, actionable insights. While the effectiveness of these algorithms can be improved through parameter tuning, resilience is ensured through cross-validation. Strengths and weaknesses are identified through statistical testing and comparison, with results presented for clarity. The study also addresses the limitations, challenges, and recommendations for selecting the best algorithm for health monitoring systems.