Calories Burned Prediction Using Machine Learning
Chhakuli Patil∗, Chetan Chaudhari†, Sumit Patil‡, Saurav Patil§, Shivam Patil¶, Mr. Pramod B. Gosavi∥
∗†‡§¶UG Students, ∥Assistant Professor,
Department of Computer Engineering, SSBT’s College of Engineering and Technology, Jalgaon, Maharashtra, India
Abstract—The increasing demand for efficient and personalized health monitoring tools has resulted in the creation of a web-based system aimed at predicting the calories burned during physical activity using machine learning. The system relies on a
predictive model that processes various physiological parameters, including gender, age, exercise duration, heart rate, and body temperature, all of which play a significant role in estimating energy expenditure. After comprehensive data preparation and exploration, the Gradient Boosting Regression algorithm was selected as the primary model due to its strong predictive power and ability to capture complex, nonlinear relationships within the data.
To make the model more accessible, it was integrated into a Flask-based web application, which enables users to input their personal information via a straightforward form. Upon data submission, the system processes the inputs and provides an immediate estimation of the number of calories burned. The design of the interface emphasizes simplicity, user interactivity, and responsive performance, ensuring that it is accessible for both fitness enthusiasts and those new to health monitoring.
This project demonstrates the effective combination of machine learning techniques and web technologies, showcasing their potential in solving practical health-related challenges. Furthermore, the system’s architecture is flexible, with scalability built in to accommodate larger datasets and diverse user needs. The platform also holds significant promise for future enhancements, including mobile applications or integration with wearable fitness trackers to provide automated, real-time calorie tracking. Ultimately, the system represents a key step towards providing users with a data-driven approach to fitness management, and its further development can offer personalized health insights and more tailored recommendations.
Index Terms—Calorie Burn Prediction, Flask Web Application, Machine Learning, Gradient Boosting Regression, Physical Activity Monitoring, Energy Expenditure, Health Informatics,
Real-Time Prediction, Web-Based Interface
