Jain, Ritik (2023) Exercise and Diet Recommendation System using Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
In a fast growing fitness industry, for almost every gym or fitness enthusiast there is always a challenge for selecting a best suitable exercise and diet from a countless variety of exercises and dietary meals, and due to lack of knowledge of these varieties, people find it very difficult to achieve fitness goals like muscle gain, weight loss. Therefore people give up going to the gym or stop doing any physical exercise since they don’t get results. Skipping fitness routines and not following a healthy diet can seriously impact your well-being, causing issues like obesity, heart disease and overall life span. This research aimed to create a user chatbot for best personalized exercise and diet recommendation using machine learning methods. Many recommendation algorithms of machine learning were used. Many datasets of exercise, nutrition and user history sourced from kaggle were used to train the ML model. Dataset was cleaned, explored and transformed. Chatbot was developed by torch, transformers and tensorflow libraries of python, three recommendation models named Collaborative hybrid, Matrix Factorization with Alternating Least Squares (ALS) algorithm and SVD algorithm were used to predict the output. Finally, there results were compared to find out the most accurate model. The Collaborative hybrid model performed best out of all the model and gave good accuracy of 74% whereas, ALS model’s accuracy was 61%, which is less when compared to other two models. The research was successful in giving the personalized exercise and diet recommendation to the user.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Rifai, Hicham UNSPECIFIED |
Uncontrolled Keywords: | Personalized exercise and diet recommendation; Chatbot; Collaborative hybrid; Matrix Factorization with Alternating Least Square; SVD algorithm |
Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning Q Science > QP Physiology > Nutrition R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine > Personal Health and Hygiene |
Divisions: | School of Computing > Master of Science in Data Analytics |
Depositing User: | Ciara O'Brien |
Date Deposited: | 09 May 2025 08:53 |
Last Modified: | 09 May 2025 08:53 |
URI: | https://norma.ncirl.ie/id/eprint/7532 |
Actions (login required)
![]() |
View Item |