Design of an Integrated System for Modeling of Functional Air Quality Index Integrated with Health-GIS Using Bayesian Neural Network

Abstract

Air pollution is a major problem, conscious both for health and surroundings. This is a novel approach for the design & development of a system for the monitoring of different air pollutants especially at remote places where it is difficult to install any conventional air quality monitoring stations as well as for the cities. In this research work, a framework of Functional air quality index which is an indicator of susceptibility to respiratory illness has been built using the Bayesian neural network to provide the random real-time data about a location through wireless communication. The monitoring system is integrated with different types of sensors to measure the level of different air pollutants or air quality parameters such as Suspended particulate matters, (PM2.5), Nitrogen dioxide, Sulphur dioxide, Ozone which are directly associated with airways inflammatory diseases such as Asthma, Bronchitis, COPD. Each location in Map (GPS) can be updated automatically with fAQI to the user through mobile computing and satellite commutation. The user gets information about the neighborhood location with health-related information such as- whether a particular location is sensitive to respiratory diseases such as Bronchitis, asthma, COPD etc. due to suspended allergen/pollutants in the ambient air. This novel approach is designed with its’ own prototype and an application of Inter of Things in Health GIS for the benefit of humanity.