Obesity Guard: Machine Learning for Early Detection and Preventioning

Abstract

Obesity has become a global health concern, with its prevalence reaching alarming levels in recent year. Obesity Guard is an innovative idea aimed at addressing the pressing global issue of obesity through the application of machine learning technology. Obesity poses significant health risks and is a growing concern worldwide, affecting millions of individuals and straining healthcare systems. Early detection and prevention are crucial in combating this epidemic, and Obesity Guard offers a proactive solution leveraging advanced machine learning algorithms. This revolves around the development of a comprehensive system capable of detecting early signs of obesity and providing personalized prevention strategies. Machine learning algorithms are at the core of Obesity Guard, enabling the system to process vast amounts of data efficiently and extract actionable insights. These algorithms utilize predictive analytics to identify patterns and trends indicative of obesity risk factors. By employing techniques such as classification, regression, and clustering, Obesity Guard can generate personalized recommendations tailored to each user's specific needs and goals. The implementation of Obesity Guard has the potential to revolutionize obesity management by shifting the focus from reactive treatments to proactive prevention. By empowering individuals with actionable insights and support, Obesity Guard aims to reduce the burden of obesity-related diseases and improve overall health outcomes. Obesity Guard represents a novel approach to addressing the obesity epidemic through the application of machine learning and personalized healthcare technologies. Obesity Guard represents a significant advancement in the field of preventive healthcare, offering a proactive approach to addressing the global obesity epidemic. By harnessing the power of machine learning and wearable technology, this has the potential to empower individuals to take control of their health, reduce obesity rates, and improve overall well-being. In our proposed work, we compare four supervised ML classifiers i.e. support Vector Machine, Decision Tree, Random Forest, Logistic Regression. Further ensemble learning technique is used to develop a hybrid model for obesity prediction. After analysis, the Random Forest (RF) model has achieved 100% accuracy than other models.