Dear Professors,
I would like to share our project AirWatch Pro, developed using MATLAB, Raspberry Pi, and a Nova SDS011 PM Sensor, as part of our academic and practical learning activities in IoT, environmental monitoring, and real-time data analytics.
GitHub Repository:
https://github.com/akashlanke/AirWatch-Pro-Air-Quality-Intelligence-Dashboard.git
Projects Slides
airpro project-compressed.pdf
Project Overview
The primary objective of this project was to design and implement an IoT-based environmental monitoring system capable of continuously measuring and analyzing air quality parameters in real time. The system acquires PM2.5 and PM10 particulate matter data using a Nova SDS011 sensor connected to a Raspberry Pi, while MATLAB is used for data acquisition, processing, visualization, and ML model training. Additionally, a React-based web dashboard provides a cross-platform interface for real-time monitoring and AI insights. The project demonstrates the integration of embedded hardware systems with software-based analytical tools to create a real-time AQI monitoring platform.
Implemented Features
Real-time PM2.5 and PM10 monitoring
AQI calculation and visualization with global compliance standards (WHO, US EPA, EU, India NAAQS)
Raspberry Pi UART serial communication with SDS011 sensor (baud rate: 9600)
MATLAB-based live dashboard with graphical plotting and statistical analysis (mean, median, variance)
Client-side AI/ML pipeline:
K-Means Clustering (k=3) for automatic classification into Clean, Moderate, and Polluted zones
Linear Regression for pollution forecasting (predicts next 12 readings)
Z-Score Anomaly Detection for sudden pollution spike alert model for PM2.5 prediction
React + TypeScript web dashboard with Recharts for interactive data visualization
Automated CSV/XLSX data import and live simulation mode
Smart alert system with browser notifications and severity debouncing
AI-powered chatbot for answering plain-language air quality questions
Technologies Used
MATLAB (Data acquisition, , visualization, statistical modeling)
Raspberry Pi 4 (Quad-core ARM Cortex-A72, 4GB RAM, GPIO/UART communication)
Nova SDS011 PM Sensor IoT Communication (UART serial protocol at 9600 baud)
React + TypeScript + Vite (Client-side AI/ML and web dashboard)
Recharts, SheetJS (XLSX) (Data parsing and visualization)
Google Apps Script / Sheets API (Cloud logging – optional extension)
Serial Communication Protocols (Raspberry Pi ↔ SDS011)
Learning Outcomes
Through this project, we gained practical experience in:
IoT system development with Raspberry Pi and sensor integration
Real-time data acquisition and processing via UART serial communication
MATLAB programming for statistical analysis and machine learning
Implementation of client-side AI/ML models (K-Means, Linear Regression,KNN, Z-Score)
Frontend development with React and TypeScript for real-time dashboards
Comparative analysis of global air quality standards (WHO 2021, US EPA, EU, India NAAQS)
Environmental analytics and anomaly detection in time-series data
This project also helped us understand how intelligent monitoring systems can contribute to smart environmental solutions and real-time analytics applications.
Teammates:
AKASH LANKE (@akashlanke),
MUHAMMAD QASEEM (@qaseem97),
ANMOL SUNDRIYAL(@Anmol-dstd)
SNEGA AMBIGAPATHY(@snegaambigapathy)
We sincerely thank @AldoCorbelliniUNIPR , @MarcoRianiUNIPR , @Asadunipr for their valuable guidance, continuous support, and for providing us the opportunity to present and work on this project.
Thank you.
Dear Professors,
I would like to share our project AirWatch Pro, developed using MATLAB, Raspberry Pi, and a Nova SDS011 PM Sensor, as part of our academic and practical learning activities in IoT, environmental monitoring, and real-time data analytics.
GitHub Repository:
https://github.com/akashlanke/AirWatch-Pro-Air-Quality-Intelligence-Dashboard.git
Projects Slides
airpro project-compressed.pdf
Project Overview
The primary objective of this project was to design and implement an IoT-based environmental monitoring system capable of continuously measuring and analyzing air quality parameters in real time. The system acquires PM2.5 and PM10 particulate matter data using a Nova SDS011 sensor connected to a Raspberry Pi, while MATLAB is used for data acquisition, processing, visualization, and ML model training. Additionally, a React-based web dashboard provides a cross-platform interface for real-time monitoring and AI insights. The project demonstrates the integration of embedded hardware systems with software-based analytical tools to create a real-time AQI monitoring platform.
Implemented Features
Real-time PM2.5 and PM10 monitoring
AQI calculation and visualization with global compliance standards (WHO, US EPA, EU, India NAAQS)
Raspberry Pi UART serial communication with SDS011 sensor (baud rate: 9600)
MATLAB-based live dashboard with graphical plotting and statistical analysis (mean, median, variance)
Client-side AI/ML pipeline:
K-Means Clustering (k=3) for automatic classification into Clean, Moderate, and Polluted zones
Linear Regression for pollution forecasting (predicts next 12 readings)
Z-Score Anomaly Detection for sudden pollution spike alert model for PM2.5 prediction
React + TypeScript web dashboard with Recharts for interactive data visualization
Automated CSV/XLSX data import and live simulation mode
Smart alert system with browser notifications and severity debouncing
AI-powered chatbot for answering plain-language air quality questions
Technologies Used
MATLAB (Data acquisition, , visualization, statistical modeling)
Raspberry Pi 4 (Quad-core ARM Cortex-A72, 4GB RAM, GPIO/UART communication)
Nova SDS011 PM Sensor IoT Communication (UART serial protocol at 9600 baud)
React + TypeScript + Vite (Client-side AI/ML and web dashboard)
Recharts, SheetJS (XLSX) (Data parsing and visualization)
Google Apps Script / Sheets API (Cloud logging – optional extension)
Serial Communication Protocols (Raspberry Pi ↔ SDS011)
Learning Outcomes
Through this project, we gained practical experience in:
IoT system development with Raspberry Pi and sensor integration
Real-time data acquisition and processing via UART serial communication
MATLAB programming for statistical analysis and machine learning
Implementation of client-side AI/ML models (K-Means, Linear Regression,KNN, Z-Score)
Frontend development with React and TypeScript for real-time dashboards
Comparative analysis of global air quality standards (WHO 2021, US EPA, EU, India NAAQS)
Environmental analytics and anomaly detection in time-series data
This project also helped us understand how intelligent monitoring systems can contribute to smart environmental solutions and real-time analytics applications.
Teammates:
AKASH LANKE (@akashlanke),
MUHAMMAD QASEEM (@qaseem97),
ANMOL SUNDRIYAL(@Anmol-dstd)
SNEGA AMBIGAPATHY(@snegaambigapathy)
We sincerely thank @AldoCorbelliniUNIPR , @MarcoRianiUNIPR , @Asadunipr for their valuable guidance, continuous support, and for providing us the opportunity to present and work on this project.
Thank you.