Inspiration
Whenever New Years came around and I suddenly felt inspired to follow a fitness plan, I knew that it would quickly die out. I always started to lose motivation because I didn't see results quickly enough. But what if there were a way to predict what I would look like in the future if I were to follow a work-out/nutrition plan? That's exactly what this web application provides; a way for anybody to become motivated to become fit by seeing results in the future.
What it does
This application takes various user input values such as general information (gender, height, weight), nutritional information (daily calorie intake, protein, etc.), and cardiovascular information (running times and frequency) and creates predictions of future weight loss in a year's span. Also, it gives user's feedback on how they could change their diet/work-out plan.
How we built it
The web application itself and the back-end was built using R and various packages such as rshiny and ggplot2. The machine learning model was built using built-in functions of R. Connection to our SQLite database was done by using the package rsqlite. The rest of the website was built using HTML, Javascript and CSS.
Challenges we ran into
Learning the rshiny package was tricky because there are many possibilities for the layout of the web app. Many functions had to be made within R to calculate various numbers pertaining to fitness. The biggest problem was finding a way to create human models to make our predictions.
Accomplishments that we're proud of
We were able to come together from different backgrounds to make a product that we are proud of.
What we learned
We learned how to work together as a team under such an intense time constraint.
What's next for Fitness Prophet
We plan to further Fitness Prophet by providing a cleaner user interface and human models for prediction. We also plan to incorporate more work-out plans than just running, such as strength training to see future muscle progression. The user login system will also be fully incorporated.
Log in or sign up for Devpost to join the conversation.