Project Update: Calories Burnt Prediction AI
I'm excited to share the progress of our Calories Burnt Prediction AI – ML + DL Based Fitness Prediction and Analytics System!
Our project aims to make fitness analysis smarter by using Artificial Intelligence to estimate calories burned based on personal and workout-related parameters such as age, weight, workout duration, heart rate, and body temperature.
What we've built:
- Data preprocessing and preparation for model training
- Machine Learning and Deep Learning-based calorie prediction
- Model evaluation using RMSE, MAE, and R²
- An interactive web application developed with Streamlit
- Online deployment for easy access
What's next?
We're exploring opportunities to improve prediction performance, introduce personalized fitness insights, and investigate cloud-based AI inference using Nebius and NVIDIA Nemotron.
This journey has helped us strengthen our skills in AI, data science, model development, deployment, and problem-solving. We're also proud that our project was selected for our college expo!
Try our live application: https://calories-brunt-prediction.streamlit.app/
Every step brings us closer to making fitness analytics more accessible through AI.
Log in or sign up for Devpost to join the conversation.