Case Study: Jakarta AQI Classification Using Extreme Learning Machine Method with Oversampling Technique

Good air quality is essential in maintaining the continuity of life. Air quality is very influential on the quality of oxygen needed by the human body. Air pollution is one of the components that greatly affects the quality of oxygen. The capital city of Indonesia, Jakarta, is ranked 9th for air quality and urban pollution. Air quality information is certainly needed by humans. People need information about air quality to be more concerned about the effects of air pollution on their health. The air quality information needed is the air quality index. Therefore, in this research, the classification of the air quality index is carried out. The classification process is carried out using a machine learning algorithm with the Extreme Learning Machine (ELM) method. The Extreme Learning Machine (ELM) algorithm was chosen because it has the advantages of faster learning, easy to use for complex problems, and relevant to the real world. The dataset used for this research comes from Jakarta Open Data and Jakarta Low Emission. This research proves that the use of machine learning with the Extreme Learning Machine (ELM) method is effective in performing the classification process. In the classification process, the Extreme Learning Machine (ELM) produces good performance using balanced data and imbalance data. Experiments with imbalance data with a high accuracy of 94% and balanced data with an accuracy of 96%.