AirWatch Pro – Air Quality Intelligence Dashboard
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 15/100
- Issue type
- Feature
- Clarity
- Needs clarification
- Activity status
- Quiet
- Tech stack
- matlab, raspberry-pi, react, typescript
- Domain
- data-visualization, embedded-iot
Research direction
The issue describes an AirWatch Pro project and links to its repository and slides, but does not specify a change to make in DSwithMATLAB. First check whether the project belongs in this repository and whether a maintainer wants it added; without a defined change or completion criteria, there is no implementation task to start.
Written by the indexing model from the issue text.
Description
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
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.
- Dominant language
- MATLAB
- Stars
- 30
- Forks
- 1
- PR merge metrics
- No merged PRs in 30d
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from UniprJRC/DSwithMATLAB
-
Difficulty 1/5 Under an hour Newbie friendliness 75/100
UniprJRC/DSwithMATLAB#243 ·
-
Difficulty 1/5 Under an hour Newbie friendliness 75/100
UniprJRC/DSwithMATLAB#242 ·
-
Difficulty 1/5 Under an hour Newbie friendliness 78/100
UniprJRC/DSwithMATLAB#241 ·
-
Difficulty 1/5 Under an hour Newbie friendliness 83/100
UniprJRC/DSwithMATLAB#240 ·
-
Suggestion for the next edition
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
UniprJRC/DSwithMATLAB#238 · 2 comments ·
All issues in UniprJRC/DSwithMATLAB
Similar issues
-
bug priority: p3 size: xs
Difficulty 1/5 Under an hour Newbie friendliness 75/100
-
Ax/Atb trim the caller's GpuIds in place, so blocksize-1 solvers run on one GPU after the first anglePossibly taken @AnderBiguri claimed this 1 day ago. Open
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 77/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 63/100
mathworks/MATLAB-Coding-Guidelines#7 · 3 comments ·