Open AccessThe comparison between extreme learning machine and artificial neural network-back propagation for predicting the dengue incidences number in DKI Jakarta
Author(s) -
Stephen T. Tiffany,
Devvi Sarwinda,
Bevina D. Handari,
Gatot Fatwanto Hertono
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1821/1/012025
Subject(s) - dengue fever , artificial neural network , artificial intelligence , machine learning , christian ministry , backpropagation , extreme learning machine , computer science , incidence (geometry) , support vector machine , medicine , mathematics , virology , philosophy , geometry , theology
The existence of COVID-19 in Indonesia is not the only disease which we must be aware of. The Health Ministry has said that Dengue Hemorrhagic Fever is as dangerous as COVID-19 and must also be treated with caution. Based on data, until July 2020, there are 71,633 dengue cases in Indonesia and DKI Jakarta has the sixth-highest dengue incidence number. One of the factors that affects the spread of dengue vector is weather. It is necessary to predict the number of dengue incidences so that the dengue handling and prevention efforts can be done optimally. In this study, the number of dengue incidences will be predicted by involving weather factors (rainfall, temperature, and humidity) using Extreme Learning Machine and Artificial Neural Network-Back Propagation and also comparing the both of their performance. The result shows that Extreme Learning Machine can give the dengue incidence prediction in DKI Jakarta with the best RMSE testing result of 0.04584, which is more accurate than the dengue incidence prediction that is given by using Artificial Neural Network-Back Propagation with 100 epochs. Moreover, Extreme Learning Machine can do the training process faster than Artificial Neural Network-Back Propagation.