RESOLUSI : REKAYASA TEKNIK INFORMATIKA DAN INFORMASI
Vol. 3 No. 4 (2023): RESOLUSI Maret 2023

Metode Conjugate Gradient Beale Powell Restarts Untuk Memprediksi Angka Kecelakaan Berdasarkan Korban Yang Meninggal Di Sumatera Utara

Solikhun (STIKOM Tunas Bangsa, Pematangsiantar)
Hamdani (STIKOM Tunas Bangsa, Pematangsiantar)



Article Info

Publish Date
31 Mar 2023

Abstract

The purpose of this study is to predict the number of traffic accident victims who died in North Sumatra using the Backpropogation Conjugate Gradient Beale Powell Restarts method, as well as calculating using a method based on the level of error and predicting the number of disaster victims and then routes in North Sumatra for the following year. This research was attempted in North Sumatra where the information used in this study was obtained from BPS (Central Bureau of Statistics) of North Sumatra. This information is in the form of information regarding the number of disasters and routes in North Sumatra in 2010–2022 using quantitative analysis using the Conjugate Gradient Beale Powell Restarts method. The results of the analysis of surveillance information on the number of victims of the disaster then using the Conjugate Gradient Beale Powell Restarts method obtained that the best form is the 11-4-1 architectural form with MSE 0.068199165 and an accuracy of 82.14%. Based on the level of confusion, it was found that the Conjugate Gradient Beale Powell Restarts procedure was better than the other architectures, including 11- 5- 1, 11- 6- 1, 11- 7- 1, 11- 3- 1. the number of accident victims for the next 1 year (Year 2023).

Copyrights © 2023






Journal Info

Abbrev

resolusi

Publisher

Subject

Computer Science & IT

Description

Resolusi : Rekayasa Teknik Informatika dan Informasi, membahas ilmu dibidang Informatika, Sistem Informasi, Manajemen Informatika, DSS, AI, ES, Jaringan, sebagai wadah dalam menuangkan hasil penelitian baik secara konseptual maupun teknis yang berkaitan dengan Teknologi Informatika dan Komputer. ...