Linda Purnama Muri
Jurusan Teknik Informatika, Fakultas Teknik, Universitas Halu Oleo, Kendari

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

PREDIKSI TINGKAT PENYAKIT DEMAM BERDARAH DI KOTA KENDARI MENGGUNAKAN METODE MODIFIED K-NEAREST NEIGHBOR Linda Purnama Muri; Bambang Pramono; Jayanti Yusmah Sari
semanTIK Vol 4, No 1 (2018): semanTIK
Publisher : Informatics Engineering Department of Halu Oleo University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (400.125 KB) | DOI: 10.55679/semantik.v4i1.4036

Abstract

Kendari city is still a dengue endemic area. It is viewed from the topography of Kendari City which has a height between 0-472 m above sea level (DPL). The low ability to anticipate the occurrence of Dengue Fever is caused, among others, because the time, place and incidence rate has not been well predicted, the unavailability of index and vulnerability maps of the area based on the time of the incident, and the unavailability of predictive prediction model of DHF incidence. This underlies the need for DHF Prediction in Kendari City.The method used to predict dengue fever rate in Kendari city that is Modified K-Nearest Neighbor method. MKNN consists of two processing, the first data validation training that aims to validate training data and the second is to apply the weighting of KNN.Based on the results of testing conducted, application prediction of dengue fever (DHF) in kendari city using Modified K-Nearest Neighbor (MKNN) method is able to predict with the smallest error value 0,04%, for value k = 4 biggest error value 1 , 58 for the value of k = 4 and the smallest error rate of 0.28% for the value of k = 3.Keywords— Dengue Fever, Forecasting, Modified K-Nearst NeighborDOI :10.5281/zenodo.1402838