Inspiration

Many passengers face difficulties during peak hours because buses become overcrowded. People often spend a lot of time waiting for buses without knowing the crowd level. This inspired us to build CrowdSense AI, a smart system that predicts bus crowd levels before travel.

What it does

CrowdSense AI predicts the expected crowd level in a bus based on factors such as time, day, and historical travel patterns. The system helps passengers choose less crowded buses, reduce waiting time, and improve travel comfort.

Key Features:

  • Bus crowd prediction
  • Crowd percentage estimation
  • Crowd status (Low, Medium, High)
  • User-friendly web interface
  • Smart public transport assistance

How we built it

Frontend:

  • HTML
  • CSS
  • JavaScript

Backend:

  • Python Flask

Machine Learning:

  • Scikit-learn

Dataset:

  • CSV-based historical bus occupancy data

The machine learning model is trained using historical crowd information and predicts future crowd levels based on user inputs.

Challenges we ran into

  • Finding suitable public transport datasets
  • Preparing and cleaning data
  • Building an accurate prediction model
  • Integrating the machine learning model with the web application

Accomplishments that we're proud of

  • Successfully developed a working AI-based crowd prediction system
  • Created a simple and user-friendly web application
  • Applied machine learning to solve a real-world smart city problem

What we learned

  • Machine Learning model development
  • Flask web development
  • Data preprocessing and analysis
  • Team collaboration and project management

What's next for CrowdSense AI

  • Real-time GPS integration
  • Live bus tracking
  • Weather-based prediction
  • Mobile application support
  • Smart city transport dashboard

Built With

Share this project:

Updates

Submission history