Skip to content

AI-powered optimization & safety control for a low-cost ozone generator using ML

Notifications You must be signed in to change notification settings

hriday-goyal/ozone-ai-ml

Repository files navigation

🌿 AirGuard – Accessible AI-Powered Ozone Dashboard

A machine learning-based air purification and accessibility-focused dashboard that predicts ozone output, classifies safety levels, and estimates indoor air purification efficiency — built to support individuals with respiratory conditions like asthma or COPD.

📌 Overview

This project combines IoT-inspired data with software intelligence to improve indoor air quality using AI-enabled analysis. It features a multi-module ML model deployed as a Streamlit web app, optimized for accessibility and ease of use.

🔧 Technologies Used

  • Python
  • Streamlit
  • scikit-learn
  • NumPy
  • Pandas

🚀 Features

  • Predict ozone output (g/hr) using regression
  • Classify air safety levels for respiratory health
  • Estimate purification efficiency based on input factors
  • Clean, accessible UI with real-time ML inference
  • Hosted online via Streamlit Cloud

🧪 ML Models Implemented

  • Regression model for ozone output
  • Classification model for air safety
  • Efficiency estimation based on calculated metrics

🔗 Live Demo

👉 Launch AirGuard

📂 Project Structure

ozone-generator-ml/
├── ozone_predictor.py
├── classifier.py
├── efficiency_model.py
├── app.py
├── data.csv
└── requirements.txt

📥 Installation & Usage

To run locally:

pip install -r requirements.txt
streamlit run app.py

🧠 What I Learned

  • Integrating multiple ML models into a single interactive tool
  • Designing with accessibility-first UI principles
  • Applying AI to social-impact problems like air quality and public health

📝 Research Paper

This project was published in the IRJMETS Journal.
📄 Link to publication

📎 License

MIT License


👤 Author: Hriday Goyal
🔗 GitHub

About

AI-powered optimization & safety control for a low-cost ozone generator using ML

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published