PREDICTION OF MALARIA INCIDENCE IN BANGGAI REGENCY USING EVOLVING NEURAL NETWORK

PREDICTION OF MALARIA INCIDENCE IN BANGGAI REGENCY USING EVOLVING NEURAL NETWORK

A THESIS SUBMITTED TO THE GRADUATE SCHOOL

OF TELKOM INSTITUTE OF TECHNOLOGY

BY

RITA RISMALA
First superviser : Prof Dr. The Houw Liong
Second superviser : Arie Ardiyanti

IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR
MASTER DEGREE OF INFORMATICS IN THE INFORMATICS STUDY PROGRAM, FEBRUARY 2013

ABSTRACT

Malaria is an endemic disease in most of Indonesian area, especially in rural and remote areas. Banggai, one of regencies in Central Sulawesi province, is a high endemic area of malaria with Annual Parasite Incidence (API) in 2010 reached 7.88‰. The incidence and spreading of malaria were influenced by environmental and weather factors, particularly rainfall and temperature. Therefore this study would like to developed a malaria incidence prediction system based on environmental and weather factors, so that it may assist Indonesian Ministry of Health to control malaria. The method used to solve the problem was Evolving Neural Network (ENN). This method was a mixture between Artificial Neural Network (ANN) and Genetic Algorithm (GA).
The result of this study shows that the prediction system has acceptable performance for predicting malaria incidence based on weather factors. The best performance while predicting malaria incidence in 2008 was MAPE 21.3%, accuracy 75%, and F-value 84.21%. The best season to predict was dry season with MAPE 13.18%, accuracy 100%, and F-value 100%. As for predicting malaria incidence in 2009, was resulted MAPE 15.29%, accuracy 75%, and F-value 40%. The best season to predict was rainy season with MAPE 3.1%, accuracy 100%, and F-value 100%. These findings proved that there was a sufficient correlation between weather and malaria incidence.
ENN reduced trial-and-error process in constructing ANN architecture very significaltly. The reduction was up to 96%. ENN also improved the performance of ANN up to 14.84% in MAPE, 25% in accuracy, and 40% in F-value.

Keywords: Malaria, Prediction, Evolving Neural Network, Artificial Neural Network, Genetic Algorithm

ABSTRAK

Malaria merupakan penyakit endemis di sebagian besar wilayah Indonesia, terutama di daerah pedesaan dan terpencil. Banggai, salah satu kabupaten di provinsi Sulawesi Tengah, merupakan daerah endemis tinggi malaria, dengan Annual Parasite Incidence (API) pada tahun 2010 mencapai 7.88‰. Kejadian dan penyebaran malaria sangat dipengaruhi oleh sejumlah faktor lingkungan dan cuaca, terutama curah hujan dan suhu. Oleh karena itu pada studi ini dibangun suatu sistem prediksi kejadian malaria yang dikaitkan dengan faktor lingkungan dan cuaca agar bisa membantu Kementerian Kesehatan dalam pengendalian malaria. Adapun metode yang digunakan adalah Evolving Neural Network (ENN). Metode ini menggabungkan Jaringan Syaraf Tiruan (JST) dan Algoritma Genetika (AG).
Sistem prediksi yang dihasilkan dari studi ini menghasilkan performansi yang cukup bagus untuk memprediksi kejadian malaria berdasarkan faktor cuaca. Performansi terbaik saat memprediksi kejadian malaria pada tahun 2008 adalah MAPE 21.3%, akurasi 75%, dan F-value 84.21%, dimana sistem menghasilkan performansi terbaik saat melakukan prediksi di musim kemarau dengan MAPE 13.18%, akurasi 100%, dan F-value 100%. Sedangkan untuk memprediksi kejadian malaria pada tahun 2009, dihasilkan MAPE 15.29%, akurasi 75%, dan F-value 40%, dimana sistem menghasilkan performansi terbaik saat melakukan prediksi di musim hujan dengan MAPE 3.1%, akurasi 100%, dan F-value 100%. Hasil ini membuktikan bahwa ada korelasi yang cukup antara cuaca dan kejadian malaria.
ENN mengurangi proses trial-and-error dalam membangun arsitektur JST secara signifikan hingga 96%, dan memperbaiki performansi hingga 14.84% dalam MAPE, 25% dalam accuracy, dan 40% dalam F-value.

Kata kunci: Malaria, Prediksi, Evolving Neural Network, Jaringan Syaraf Tiruan, Algoritma Genetika

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s