Abstract—Malaria affects over 100 million persons
worldwide with approximately 2,414 deaths a day in average
each year. Indonesia is on the third highest position in the
number of malaria incident in South East Asia, with 229,819
confirmed cases and 432 deaths only at 2010. Previous work has
demonstrated the potential of neural networks in predicting the
behavior of complex, non-linear systems. GMDH Polynomial
Neural Network was applied in a great variety of areas for data
mining and knowledge discovery, forecasting, systems modeling,
optimization, and pattern recognition. Study has also shown the
close relation between Malaria incidence and weather pattern.
This paper proposed a modified GMDH Polynomial Neural
Network to reduce the learning time and computation while
maintaining the accuracy in predicting Malaria incidence by
relating it to weather pattern. Based on the experiments, it was
proven that the modified GMDH PNN was able to reduce the
learning time by 72% and improve the accuracy into 88.02%
compared to the original GMDH PNN.
Index Terms—Malaria, prediction, weather pattern,
polynomial neural network.
The authors are with Graduate School of Informatics Engineering,
Telkom Institute of Technology, Bandung, Indonesia (e-mail:
anditya.arifianto@yahoo.com, mbarmawi@melsa.net.id,
agungtotowibowo@yahoo.com).
[PDF]
Cite:Anditya Arifianto, Ari Moesriami Barmawi, and Agung Toto Wibowo, "Malaria Incidence Forecasting from Incidence Record and
Weather Pattern Using Polynomial Neural Network," International Journal of Future Computer and Communication vol. 2, no. 6, pp. 60-65, 2014.
