Two Hybrid Expert System for Diagnosis Air Quality Index (AQI)

Abstract

Air pollution is a common problem in areas with high population density such as big cities. The mega city of Tehran which is capital city of Iran is suffering from poor air quality. In Tehran, Traditional air quality assessment is realized using air quality indices which are determined as max values of selected air pollutants which is mostly base on PM2.5. Thus, air quality assessment depends on strictly describe without taking into account specific other Environmental parameters. In this paper, To demonstrate the application, common air pollutants like CO, O3, NO2, SO2, PM10 and PM2.5 are used as air pollutant parameters, also we were studied over an 2-year period (2015–2017) on daily data of the air quality index (AQI) in Tehran. The artificial intelligence based on neural network and fuzzy inferences methods allows assessing air quality parameters, providing a partial solution to this problem. Accordingly, this study proposes two fuzzy logic system for assessing accurate air quality evaluations, also proposed Seven score stages: Good, Moderate, Unhealthy for Sensitive Group, Unhealthy, Very Unhealthy, Hazardous for evaluating air quality index. Our experimental results show a good performance of the proposed air quality index against other system that those in literature.