Home / Current Issue / Paper 1716884
Smart IOT Based Air Quality Monitoring and Respiratory Disease prediction using Machine Learning
Subject area: Science,Engineering and Technology · Area of research: IoT and Machine Learning
DOI: https://doi.org/10.64388/IREV9I10-1716884
Abstract
Rising levels of air pollution have significantly contributed to respiratory diseases such as asthma, chronic obstructive pulmonary disease (COPD), and bronchitis. This paper presents a Smart IoT-based air quality monitoring and respiratory disease prediction system that combines low-cost environmental sensing with machine learning techniques. An ESP32 microcontroller integrated with MQ-135 (CO₂), MQ-7 (CO), MQ-3 (alcohol), and DHT11 sensors collects real-time atmospheric data and transmits it to the ThingSpeak cloud platform via Wi-Fi. Raw sensor values are pre-processed and converted into parts per million (PPM) before being merged with additional pollutant parameters (PM2.5, PM10, SO₂, NO₂, O₃), along with personal attributes such as age and smoking habits. The Air Quality Index (AQI) is computed and used as an input feature for predictive modelling. Logistic Regression, XGBoost, and RandomForest algorithms are implemented to predict the likelihood of asthma, COPD, and bronchitis. The system categorizes health risk into four levels—Low, Medium, High, and Severe—and provides personalized feedback through a web-based platform with automated email alerts for critical cases. The proposed framework demonstrates a scalable and affordable approach for real-time environmental health monitoring.
Keywords
IOT, ThingSpeak, Sensors, ESP32, Machine Learning, Logistic Regression, XGBoost, Random Forest, Respiratory Diseases Prediction.
How to cite this paper
@article{1716884,
author = {S Anuhya, Santhwana Rajeevan, Sushmitha T R, Dr. Sharmila G},
title = {Smart IOT Based Air Quality Monitoring and Respiratory Disease prediction using Machine Learning},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {10},
pages = {3366-3373},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1716884.pdf},
abstract = {Rising levels of air pollution have significantly contributed to respiratory diseases such as asthma, chronic obstructive pulmonary disease (COPD), and bronchitis. This paper presents a Smart IoT-based air quality monitoring and respiratory disease prediction system that combines low-cost environmental sensing with machine learning techniques. An ESP32 microcontroller integrated with MQ-135 (CO₂), MQ-7 (CO), MQ-3 (alcohol), and DHT11 sensors collects real-time atmospheric data and transmits it to the ThingSpeak cloud platform via Wi-Fi. Raw sensor values are pre-processed and converted into parts per million (PPM) before being merged with additional pollutant parameters (PM2.5, PM10, SO₂, NO₂, O₃), along with personal attributes such as age and smoking habits. The Air Quality Index (AQI) is computed and used as an input feature for predictive modelling. Logistic Regression, XGBoost, and RandomForest algorithms are implemented to predict the likelihood of asthma, COPD, and bronchitis. The system categorizes health risk into four levels—Low, Medium, High, and Severe—and provides personalized feedback through a web-based platform with automated email alerts for critical cases. The proposed framework demonstrates a scalable and affordable approach for real-time environmental health monitoring.},
keywords = {IOT, ThingSpeak, Sensors, ESP32, Machine Learning, Logistic Regression, XGBoost, Random Forest, Respiratory Diseases Prediction.},
month = {April},
doi = {https://doi.org/10.64388/IREV9I10-1716884}
}