IoT-Based Indoor Air Quality Monitoring with Data Analytics

1. Inspiration

Air pollution is becoming a serious issue, especially in indoor environments where people spend most of their time. We noticed that most systems only display current air quality but do not provide future insights or alerts. This inspired us to build a smart system that not only monitors air quality in real time but also predicts future conditions, helping people stay safe and take preventive actions.

2.What it does

Our project is an IoT-based indoor air quality monitoring system that:

Collects real-time air quality data using sensors Displays data on a user-friendly dashboard Uses machine learning (XGBoost) to predict air quality for the next few days Provides alerts when air quality becomes harmful Helps users make better decisions for their health and environment

1. How we built it Used IoT sensors connected to a microcontroller to capture real-time data Sent the data to a system/database for storage and processing Applied machine learning algorithms like XGBoost for prediction Developed a web dashboard to visualize real-time and predicted data Integrated an alert system for dangerous air quality levels

4.Challenges we ran into Handling noisy and inconsistent sensor data Integrating hardware with software smoothly Ensuring accurate predictions with limited data Maintaining real-time data updates Designing a clean and user-friendly dashboard

5.Accomplishments that we're proud of Successfully built a working IoT + ML integrated system Achieved real-time monitoring and future prediction together Created a simple and effective dashboard for users Implemented an alert system for safety Solved a real-world problem with practical impact

6.What we learned Working with IoT hardware and sensors Real-time data collection and processing Applying machine learning in real-world scenarios Importance of data accuracy and preprocessing Building user-friendly interfaces

7.What's next for IoT-Based Indoor Air Quality Monitoring with Data Analytics Improve prediction accuracy with more advanced models Add mobile app support for better accessibility Integrate more sensors for detailed analysis Enable cloud integration for scalability Expand the system for outdoor and smart city applications

Built With

• css
• frontend:-html
• javascript-(dashboard)-database:-sqlite-data-processing:-pandas
• numpy-communication:-serial-communication-/-http-tools:-vs-code