Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Sema Yuni Fraticasari
Fakultas Ilmu Komputer , Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

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

Found 1 Documents
Search

 1 
Optimasi Pemodelan Regresi Linier Berganda Pada Prediksi Jumlah Kecelakaan Sepeda Motor Dengan Algoritme Genetika Sema Yuni Fraticasari; Dian Eka Ratnawati; Randy Cahya Wihandika
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 5 (2018): Mei 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (850.75 KB)

Abstract

Traffic accidents are increasing from year to year according to the Badan Pusat Stastistika record from 1992 to 2003. According to the World Health Organization (WHO), it noted that nearly 3,400 people per day died due to traffic accidents. Surabaya is one of the metropolitan cities in Indonesia. Population growth is quite fast because the city of Surabaya is also the capital of East Java province. The system predicts the area of ​​frequent traffic accidents based on the parameters used such as the length of the road, the width of the volume body, the velocity, the number of lanes, the number of directions, the boundary / median, the plot access and the shoulder width by using linear regression optimized with the genetic algorithm. The genetic algorithm uses real numbers with 10 of gene chromosome lengths. The crossover method used by the extended intermediate crossover while the mutation uses random mutation, and the selection uses elitism selection. From the results of the experiments conducted to produce population is 125, the best combination of cr and mr is 0,6:0,4 and the best generation is 700. Comparison of error rate by showing a lower error value of 0,5% compared with regression Which results in an error value is 1,5%.
Co-Authors Dian Eka Ratnawati Randy Cahya Wihandika