TY - GEN
T1 - Prediction of dengue incidence in DKI Jakarta using adaptive neuro-fuzzy inference system
AU - Hasanah, Hajratul
AU - Hertono, Gatot Fatwanto
AU - Sarwinda, Dewi
N1 - Funding Information:
This research is supported by PUT? 2020 Proceeding Research Grant No: NKB-1011/UN2.RST/HKP.05.00/2020 from Universitas Indonesia.
Publisher Copyright:
© 2020 American Institute of Physics Inc.. All rights reserved.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/11/16
Y1 - 2020/11/16
N2 - Dengue Hemorrhagic Fever (DHF) is one of the virus diseases transmitted by mosquitoes that has spread rapidly in recent years. Based on data, for the last 3 years, 2019 have the highest number of dengue cases, reaching a total of 813 cases in DKI Jakarta. To overcome the widespread DHF, a method is needed to predict the incidence of DHF in DKI Jakarta. In this study, we present an Adaptive Neuro-Fuzzy Inference System (ANFIS) to predict the number of dengue incidence. ANFIS is a Multi-Layer Feed-Forward network using learning algorithms of neural networks and fuzzy logic. The number of dengue incidence data obtained from the DKI Jakarta Health Services website. We used the data from 2009 to 2017 with several clustering methods to find the parameter input in ANFIS. Fuzzy C-Means, Grid Partition, and Subtractive Clustering are chosen as the clustering method. Simulation results show that the ANFIS method is best used to predict the incidence of dengue with the best MSE testing results of 0.000731784 with a correlation value of 0.99104.
AB - Dengue Hemorrhagic Fever (DHF) is one of the virus diseases transmitted by mosquitoes that has spread rapidly in recent years. Based on data, for the last 3 years, 2019 have the highest number of dengue cases, reaching a total of 813 cases in DKI Jakarta. To overcome the widespread DHF, a method is needed to predict the incidence of DHF in DKI Jakarta. In this study, we present an Adaptive Neuro-Fuzzy Inference System (ANFIS) to predict the number of dengue incidence. ANFIS is a Multi-Layer Feed-Forward network using learning algorithms of neural networks and fuzzy logic. The number of dengue incidence data obtained from the DKI Jakarta Health Services website. We used the data from 2009 to 2017 with several clustering methods to find the parameter input in ANFIS. Fuzzy C-Means, Grid Partition, and Subtractive Clustering are chosen as the clustering method. Simulation results show that the ANFIS method is best used to predict the incidence of dengue with the best MSE testing results of 0.000731784 with a correlation value of 0.99104.
UR - http://www.scopus.com/inward/record.url?scp=85096671295&partnerID=8YFLogxK
U2 - 10.1063/5.0030455
DO - 10.1063/5.0030455
M3 - Conference contribution
AN - SCOPUS:85096671295
T3 - AIP Conference Proceedings
BT - International Conference on Science and Applied Science, ICSAS 2020
A2 - Purnama, Budi
A2 - Nugraha, Dewanta Arya
A2 - Anwar, Fuad
PB - American Institute of Physics Inc.
T2 - 2020 International Conference on Science and Applied Science, ICSAS 2020
Y2 - 7 July 2020
ER -
