Inspiration
We were inspired by the growing pollution levels in cities and the lack of real-time awareness tools for both citizens and government bodies. Our goal was to create a smart system to detect and prevent environmental hazards.
What it does
Smart Urban Guardian is a real-time environmental monitoring system using IoT sensors, ML prediction models, and a citizen-friendly app. It detects air, water, and noise pollution and provides alerts, safety suggestions, and a dashboard for city officials.
How we built it
We used Raspberry Pi and environmental sensors (MQ135, DHT11) for data collection, Python for backend APIs, and React Native for the mobile app. The prediction model was built using Scikit-learn.
Challenges we ran into
We struggled with sensor calibration and real-time data sync. Integrating the prediction model with live input was also challenging due to time constraints.
Accomplishments we’re proud of
We successfully built a working prototype that can detect air quality changes and trigger alerts. The UI is intuitive and the backend handles live data efficiently.
What we learned
We deepened our understanding of IoT integration, API development, and ML for environmental applications. We also learned how to work efficiently as a team under pressure.
What’s next
We plan to integrate crowdsourced reporting, improve the ML model accuracy, and pitch it to municipal bodies for pilot programs.
Built With
- api
- arduino
- dht11-sensor
- firebase
- flask
- maps
- mq135-sensor
- openaq-api
- python
- raspberry-pi
- react-native
- scikit-learn