Tuberculosis (TB) is the highest cause of death in the world. This disease attacks the respiratory system and included in infectious diseases. In 2019, Indonesia occupies the third highest position for the number of TB disease case namely as many as 842.000 cases. The increase in TB cases from year to year is due to people with insufficient information about the dangers as well as the treatment and prevention of this disease. Therefore, it is necessary to do the classification of tuberculosis for the community in order to determine the risk of developing TB disease based on symptoms experienced. From these problems, it is necessary to classify TB disease as an effort to increase public awareness of the TB disease. This study aims to obtain the result of the TB classification using the Extreme Learning Machine (ELM) method. Based on the result of testing and analysis using confusion matrix using TB data from Dinoyo Puskesmas in 2018-2019, the highest accuracy value is 99.33% with the number of hidden neurons 20, the percentage of training data and testing data is 70% : 30%, and uses the sigmoid biner function activation.
Copyrights © 2020