Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 4 No 7 (2020): Juli 2020

Prediksi Persentase Penyelesaian Permohonan Hak Milik menggunakan Metode Extreme Learning Machine (ELM) (Studi Kasus: Badan Pertanahan Nasional Kabupaten Malang)

Meilinda Dwi Puspaningrum (Fakultas Ilmu Komputer, Universitas Brawijaya)
Edy Santoso (Fakultas Ilmu Komputer, Universitas Brawijaya)
Novanto Yudistira (Fakultas Ilmu Komputer, Universitas Brawijaya)



Article Info

Publish Date
18 Aug 2020

Abstract

Certificate of Ownership is a type of certificate where the owner has full claim to the ownership of the land in a certain area that has been mentioned in the certificate. On 2018, the National Land Agency (BPN) established the PTSL program, which is a land registration process. This program is a government innovation through the Ministry of ATR / BPN to meet the basic needs of the community such as clothing, food and shelter. The process of community land certificate services that worked by BPN of Malang Regency has a constraint in which the process takes longer than determined, causing the number of certificates of ownership that can be completed every month to be lower than the number of incoming requests. In this case its cause the work of the staf is pilling up everytime. Several factors that cause this problem is the lack of inadequate human resources, especially measurement staf in the field and data processing staf. Therefore, in order to facilitate the process of servicing the land certificate, a prediction of the percentage of completion of an application using the Extreme Learning Machine (ELM) method is required. Based on the results of testing the parameters that have been carried out using the Extreme Learning Machine (ELM) method with the application for ownership data from 2014 - 2019 the comparison test of training data and testing data is produced the smallest evaluation value 2.878% using the MAPE method. At the comparison testing of training data and testing data the ratio results on the data is 30%: 70% with 2 neurons and activation functions used sigmoid binary.

Copyrights © 2020






Journal Info

Abbrev

j-ptiik

Publisher

Subject

Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Description

Jurnal Pengembangan Teknlogi Informasi dan Ilmu Komputer (J-PTIIK) Universitas Brawijaya merupakan jurnal keilmuan dibidang komputer yang memuat tulisan ilmiah hasil dari penelitian mahasiswa-mahasiswa Fakultas Ilmu Komputer Universitas Brawijaya. Jurnal ini diharapkan dapat mengembangkan penelitian ...