Case-Based Classifier for Air Pollution Monitoring and Forecasting

Abstract

Global energy production and consumption around the world have changed dramatically over the years with concern over the air quality. Pollution can be of various forms, and each of these types can have different effects on different people. Increased pollution levels are capable of causing mass destruction to the earth as well as to the species residing in it. Data analytics with air pollution monitoring can be one of key areas that provide insights into different levels of particles for air pollution. Air pollution can be defined as the presence of pollutants, such as sulfur dioxide (SO2), particle substance, nitrogen oxides (NOX) and ozone (O3). These pollutants are present in the air that we inhale at levels which can create some negative effects on the health and environment. With the increasingly severe air pollution, how to effectively process and analyze air quality data has become a hot issue. This paper aims to propose a system that intends to predict different pollutant levels using case-based reasoning method for future time frames. The cases are determined using the linear regression and polynomial regression with their respective graphical representation. The results of the case-based classifier show that the prediction levels are accurate enough for reasoning in the future.