🌱 NutriCampusAI
Inspiration
As regular users of our campus dining hall, we noticed a recurring issue: food waste. Many students choose meals quickly between classes without knowing whether the food matches their nutritional needs or personal preferences. As a result, unfinished meals are often thrown away.
We realized that something as routine as selecting lunch could be improved using data and simple health metrics. This inspired us to build NutriCampusAI — a system that connects personal health information with smarter dining decisions to reduce waste and promote healthier choices.
What It Does
NutriCampusAI collects a student’s height (in inches) and weight (in pounds) and calculates their Body Mass Index (BMI). Since we use the imperial system, BMI is calculated using:
$$ BMI = \frac{weight \times 703}{height^2} $$
The result is rounded to two decimal places and categorized (Underweight, Normal, Overweight, etc.).
Based on the BMI category, the system generates personalized meal suggestions aligned with the campus dining hall menu. Students can also rate their meals from 1–5 stars based on taste and preference. All inputs and ratings are securely stored in the database for future optimization.
The goal is to:
- Encourage healthier eating habits
- Reduce unnecessary food waste
- Provide data-driven meal recommendations
- Collect feedback to continuously improve suggestions
How We Built It
We built NutriCampusAI using a modular backend architecture:
- Node.js for server-side development
- RESTful APIs to handle user input, BMI calculation, meal generation, and ratings
- A database to store user data, BMI results, and meal feedback
- A structured folder system to keep controllers, routes, and services organized
System Flow:
- User inputs height and weight
- The backend calculates BMI
- The system categorizes the BMI result
- Meal recommendations are generated based on category
- Users rate meals
- Data is stored for analysis and improvement
We used AI tools to help refactor, debug, and improve efficiency during development, which accelerated our workflow and strengthened our understanding of scalable backend design.
Challenges We Faced
1. Privacy and Sensitivity
Height and weight are personal data. We had to ensure respectful handling and secure storage to build user trust.
2. Menu Alignment
Meal suggestions needed to match the actual campus dining menu. Ensuring accurate mapping between recommendations and available food options required careful data handling.
3. Campus Verification
We needed to confirm that students belonged to the correct campus for security and accuracy in generating meal plans.
4. User Adoption
Convincing students to consistently use the system was challenging. Since BMI is personal, we needed to present the feature in a helpful and non-judgmental way.
What We Learned
- How to structure a scalable backend using Node.js
- How to design RESTful APIs effectively
- The importance of clean architecture and modular code organization
- How to integrate AI tools into the development workflow
- The impact small technical solutions can have on real-world problems
We also learned that solving a real problem requires balancing technology, user psychology, and system design.
Future Improvements
We recognize that BMI alone does not fully represent health, as it does not account for muscle mass or body composition.
In the future, we plan to:
- Include age, gender, activity level, and body fat percentage
- Add a calorie recommendation engine
- Provide personalized exercise suggestions
- Integrate directly with dining hall systems
- Use machine learning to improve meal predictions based on user ratings
- Build a food waste analytics dashboard for campus administrators
Our long-term vision is to create a smarter campus dining ecosystem that promotes both healthier students and more sustainable food consumption.
Log in or sign up for Devpost to join the conversation.