AI-Based Fake Media Detection Using Machine Learning and Natural Language Processing

Abstract

In recent years, maintaining a healthy lifestyle has become a major concern due to increasing sedentary habits and lifestyle-related diseases. Monitoring calorie expenditure during physical activities plays a vital role in fitness management, weight control, and overall well-being. This project presents an Intelligent Calorie Burn Prediction System that utilizes machine learning techniques to estimate the number of calories burned during various physical activities.The system is developed using Python and integrates a graphical user interface (GUI) built with Tkinter to provide an interactive user experience. It incorporates the XGBoost regression algorithm, a powerful ensemble learning technique known for its high accuracy and efficiency in predictive modeling tasks. The system predicts calorie expenditure based on multiple physiological and activity-related parameters, including age, gender, height, weight, workout type, exercise duration, heart rate, and body temperature.A synthetic dataset of 10,000 records is generated to simulate real-world conditions. The dataset includes diverse combinations of user attributes and activity patterns, ensuring robustness in model training. The categorical variables such as gender and workout type are encoded using Label Encoding, and the dataset is split into training and testing sets for model evaluation. The performance of the model is assessed using the R² (coefficient of determination) metric, providing a measure of prediction accuracy.The system also includes a BMI (Body Mass Index) calculator, allowing users to assess their health status. Based on user input, the system predicts calorie burn and visually represents the results using graphical plots. Additionally, dataset visualization helps users understand the relationship between exercise duration and calorie expenditure.This project demonstrates the practical application of machine learning in fitness and health monitoring. It provides a user-friendly platform for individuals to estimate calorie burn and make informed decisions about their physical activities. The system can be further enhanced by integrating real-world datasets, wearable device data, and mobile applications.