Abstract :

Air Pollution Has Emerged As One Of The Most Critical Environmental And Public Health Challenges, Causing Severe Respiratory And Cardiovascular Diseases Due To Prolonged Exposure To Pollutants Such As PM2.5, PM10, NO₂, CO, SO₂, And O₃. Existing Air Quality Index (AQI) Monitoring Platforms Primarily Provide Generalized Information And Often Lack Real-time Localized Prediction, Personalized Health Recommendations, And Intelligent Decision Support. This Paper Presents Respirify, An AI-powered Air Quality Monitoring And Health Advisory System Designed To Provide Accurate AQI Prediction And Personalized Health Guidance Based On Environmental Conditions And Individual Health Profiles. The Proposed System Integrates Machine Learning Models, Including XGBoost And Random Forest, To Analyze Historical And Real-time Air Quality Data Collected From Trusted Public Sources Such As CPCB And OpenAQ. The Architecture Adopts A Modular Full-stack Design Comprising A React.js Frontend For Interactive Visualization, A FastAPI Backend For Data Processing And Prediction Services, And ChromaDB For Efficient Storage And Retrieval Of Contextual Information. The System Incorporates Explainable Artificial Intelligence Techniques To Improve The Transparency Of Health Risk Assessment While Generating Dynamic Recommendations Based On Pollutant Concentration, User Age, And Existing Medical Conditions. Experimental Evaluation Using Standard Regression Metrics Demonstrates The Effectiveness Of The Proposed Prediction Model In Providing Reliable AQI Forecasts While Supporting Timely Health Advisories. By Combining Intelligent Prediction, Personalized Recommendations, And User-friendly Visualization, Respirify Offers A Scalable And Practical Solution For Enhancing Environmental Awareness, Reducing Pollution-related Health Risks, And Promoting Informed Decision-making For Individuals And Communities.

Published:

11-7-2026

Issue:

Vol. 26 No. 7 (2026)

Page Nos:

510-523

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite