PREDIKSI JUMLAH FATALITAS DENGAN METODE ARTIFIAL NEURAL NETWORKBERDASARKAN UNDANG-UNDANG LALU LINTAS TAHUN 2009 DAN KARAKTERISTIK WILAYAH

Abstract

Ordinance Number 22 Year 2009 stated that fatality data must be completed with hospitals’ data. However, the data reported by Republic of Indonesia Police has not been in accordance to the law. In many countries, researchers have been using population and motor vehicles numbers as variables to predict fatality victims’ number. Those variables are not fit with Indonesian condition. The main purpose of the study was to develop better fatality prediction model in line with Indonesian condition. This was done by developing multivariable ANN models. The model was built by using population data taken from 26 cities/ in West Java Province. Main results from model validation test are: (1) three variables ANNwith two hidden layer prediction model was the best prediction used for to predict fatality numbers; (2) Fatality number was 90.93% bigger than that fatality data reported by Police RI, that was, 2026 people; ANN3-2HL prediction model was unfit to be used in Indonesia.