Scholarlink

The integration of IoT technology for disease prediction using machine learning and real-time air quality monitoring marks a significant advancement in public health management. This project employs IoT devices to continuously collect air quality data, including pollutants like C6H6, NH3, CO, NO2, and CO2, all linked to respiratory issues. An affordable IoT prototype was built using gas sensors to measure various air pollutants and determine the Air Quality Index. Real-time data is analyzed by advanced machine learning algorithms, predicting potential disease outbreaks such as heart disease, asthma, stroke, and COPD. The model uses Random Forest and XG Boost algorithms for multi-label classification on stored data. Findings based on real-time data from MQ135 sensors predict diseases like COPD, asthma, lung cancer, heart disease, and stroke. Additionally, a user interface provides preventative advice through warning signals. Studies indicate that IoT and machine learning enhance the accuracy of disease prediction, facilitating proactive public health measures. Experimental results demonstrate the effectiveness of this approach in predicting diseases based on air quality.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Integrating IoT and Machine Learning for Real-Time Disease Prediction Through Air Quality Monitoring

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Fahima Hossain,
  • Palash Saha,
  • Moshiur Rahman,
  • Mumtahina Mehjabin

摘要

The integration of IoT technology for disease prediction using machine learning and real-time air quality monitoring marks a significant advancement in public health management. This project employs IoT devices to continuously collect air quality data, including pollutants like C6H6, NH3, CO, NO2, and CO2, all linked to respiratory issues. An affordable IoT prototype was built using gas sensors to measure various air pollutants and determine the Air Quality Index. Real-time data is analyzed by advanced machine learning algorithms, predicting potential disease outbreaks such as heart disease, asthma, stroke, and COPD. The model uses Random Forest and XG Boost algorithms for multi-label classification on stored data. Findings based on real-time data from MQ135 sensors predict diseases like COPD, asthma, lung cancer, heart disease, and stroke. Additionally, a user interface provides preventative advice through warning signals. Studies indicate that IoT and machine learning enhance the accuracy of disease prediction, facilitating proactive public health measures. Experimental results demonstrate the effectiveness of this approach in predicting diseases based on air quality.