Prediksi Polusi Udara Menggunakan Algoritma Extreme Learning Machine

Abstract

The problem that has a negative impact on living things is air pollution, especially disorders of the respiratory tract. One of the causes of increased air pollution is the increasing use of motorized or private vehicles. Air Quality Index (AQI) is a value that is used as a benchmark for the community to find out whether the air in an area is good or not. The Air Quality Index (AQI) is calculated based on several components such as Carbon Monoxide (CO), Nitrogen Dioxide (NO2), Ozone (O3), Particulate Levels (PM10) and Sulfur Dioxide (SO2). The method used in this research is the Extreme Learning Algorithm. This study uses 2171 data with 1736 training data and 435 Testing data. This Extreme Learning Machine Algorithm has several activations that can be used to test the model. The test uses a sigmoid which produces air pollution predictions with an accuracy of 93,3%.