College Life essentials

AI-powered insights for better health and lifestyle decisions.

Comment

Inspiration

University life is exciting but often challenging, especially when it comes to maintaining a healthy lifestyle. Many students struggle with poor sleep quality, irregular eating habits, and lack of physical activity due to their busy schedules. We wanted to create an AI-powered tool that helps students analyze their habits and make informed lifestyle improvements with data-driven insights.

What it does

College Life Essentials is an interactive health companion that provides:

  • 🏃 Obesity Prediction: Predicts BMI changes based on user inputs like eating habits and physical activity.
  • 🌙 Sleep Quality Prediction: Analyzes lifestyle patterns and estimates sleep quality.
  • 📍 Fitness Center Locator: Helps students find nearby fitness facilities for a healthier routine.
  • 📚 Health Insights: Educates users on common health issues and ways to improve well-being.

How we built it

  • Data Collection: We used real-world health datasets related to obesity and sleep quality.
  • Machine Learning: Trained models using Random Forest and MLPRegressor to make accurate predictions.
  • Web Application: Implemented an intuitive UI using Streamlit for real-time user interaction.
  • Data Visualization: Utilized Matplotlib, Seaborn, Folium and API to present insights effectively.

Challenges we ran into

  • Feature Selection & Data Preprocessing: Cleaning and normalizing datasets to ensure accurate predictions.
  • Model Optimization: Fine-tuning hyperparameters for better performance.
  • Deployment Issues: Handling large datasets and integrating Streamlit Cloud for smooth functionality.

Accomplishments that we're proud of

  • 🏥 AI-Driven Health Assistant for College Students

    • We successfully built an AI-powered tool designed to assist students in managing their health, fitness, and sleep habits. Our platform leverages machine learning models to provide personalized insights and actionable recommendations.

  • 📊 BMI Predictor: Understanding & Managing Weight

    • Using MLPRegressor, we developed an interactive BMI prediction model that allows students to adjust lifestyle variables (e.g., diet, exercise frequency, and screen time) to predict changes in their BMI.
    • The model is trained on real-world health datasets and incorporates insights from peer-reviewed studies on obesity risk factors and metabolic health to provide scientifically backed recommendations tailored to the user's lifestyle.

  • 🏋️ UW Madison Fitness Center Map: Encouraging an Active Lifestyle

    • We integrated a map-based fitness center locator to help students find nearby gyms, fitness studios, and wellness facilities on and around the UW Madison campus.
    • By using Folium for interactive mapping, students can explore fitness locations, check operational hours, and plan their workouts efficiently.

  • 🥗 Health & Wellness Courses: Learning for a Healthier Lifestyle

    • Recognizing the importance of education in maintaining health, we compiled a comprehensive database of university courses related to nutrition, exercise science, and wellness.
    • Students can browse categorized course offerings in Dance, Kinesiology, and Food Science to make informed decisions about academic paths that align with their health goals.

  • Using API integration, we automated the retrieval of course data, ensuring up-to-date and accurate information.

  • 🌙 Predict Your Sleep Quality: Data-Driven Sleep Insights

    • We built a sleep quality predictor using Random Forest model trained on sleep habit datasets.
    • This feature allows users to enter their daily habits (stress levels, activity, heart rate, etc.) and receive a predicted sleep quality score (0-10) based on AI-driven analysis.
    • To enhance reliability, our insights are supported by findings from scientific literature on circadian rhythms, sleep hygiene, and the impact of digital device usage on rest patterns.

  • 📖 Expert-Backed Health & Lifestyle Recommendations

    • Each health module provides recommendations derived from scientific studies, medical research, and academic publications on obesity prevention, sleep improvement, and physical fitness.
    • Our system offers practical, research-based strategies such as reducing technology use before sleep, optimizing meal frequency for metabolic health, and incorporating low-intensity exercise for sustainable weight management.

What we learned

  • The importance of data preprocessing in improving ML model accuracy.
  • How to optimize Random Forest and MLPRegressor for different prediction tasks.
  • The power of visualization in making complex data easy to understand.
  • The value of deploying AI models in an accessible web application.

Built With

Share this project:

Updates