The overarching idea of this research project is to make a comparative study of machine learning algorithms to predict the calories burn during the workout. In this paper we first build a machine learning systems that can predict the amount of calories burnt during exercise. In today’s world many people are inquisitive about the workout that they do and the weight loss plan that they take and how much calorie do they burn once they workout. To solve this problem we can use ML alggoirthms such as XGBoost regressor and Linear Regression.
he body temperature and the heartbeat will rise when we exercise or workout. The variables that we take here such as time scale for which the individual carrying out the workout training and what is the average beats per minute and then the temperature. Then we additionally take the height, weight, gender and age of the person to predict how tons energy the person may be burning. A machine learning XGBoost regressor algorithm and linear regression algorithms are used to predict calories burned depends on the workout duration,body temperature, height,weight and age of the person.
- Document your code that supports mathematical equations
- Create,Upload,Share notebooks
- Import and save notebook from or to Google Drive
- Import or Publish notebooks from GitHub
- Import external datasets e.g. from Kaggle
- Integrate PyTorch, TensorFlow, Keras, OpenCV
- Free Cloud service with free
From the analysis we met with a conclusion that the XGB Regressor has more accurate results than the Linear regression model. Mean absolute error imply absolute error ought to be as low as viable.. it is not anything but the difference between the actual and predicted values through the models. The mean absolute error value that is getting in XGB Regressor is 2.71 which is a good value.The error values is very less. Therefore we can conclude that the best model for the calorie burn prediction is XGBoost Regressor.