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
Vidya Capristyan Pamungkas
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 
Klasifikasi Penerimaan Program Keluarga Harapan (PKH) Menggunakan Metode Learning Vector Quantization (Studi Kasus Desa Kedungjati) Vidya Capristyan Pamungkas; Lailil Muflikhah; Rendi Cahya Wihandika
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (820.531 KB)

Abstract

Poverty is a condition of someone inability to fulfill basic needs for a decent life. The poverty rate is increases, especially in Jombang Regency from year to year until 2017 reaching 131.16 people, various ways have been carried out by the government to reduce poverty, one of which is Program Keluarga Harapan or PKH, Kedungjati Village officer doing survey head of family with manual method by visiting each head of family and recording one by one the criteria. Classification system of Program Keluarga Harapan using Learning vector quantization (LVQ). LVQ is a classification method that has a pattern where the output of each unit is a representation of a class or category. The weight vector of each unit's output is a vector representation to a class. Weight vector have rules during training. As a classification method, LVQ does a lot of training repeatedly process until get maximum results, so LVQ can minimize errors that occur in the process. LVQ method do training and testing process to obtain the classification results. In this case using 5 test parameters with the best results, that is learning rate 0.7, DecAlpha 0.3, Epoch 2, and MinAlpha 0.01, using 2 weight vector to represent class 0 and class 1, get the results of an accuracy of 100%.
Co-Authors Lailil Muflikhah Rendi Cahya Wihandika