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
Khairul Rizal
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 
Penentuan Waktu Terakhir Penggunaan Ganja Menggunakan Multidimensional Hierarchical Classification Khairul Rizal; Sigit Adinugroho; Bayu Rahayudi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 10 (2019): Oktober 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (765.369 KB)

Abstract

Drug abuse in Indonesia increases every year. One type of narcotics that often consumed freely without obtaining permission from the pharmaceutical industry is cannabis which can make the user experience euphoria (excessive joy without cause). The handling of drug addicts can be done through government rehabilitation services and one of the services is giving medical rehabilitation to aburses based on their level of dependency. Therefore, classification of determining last time use of cannabis is carried out which can help in determining the right type of rehabilitation service for abusers. The method that used by researcher is Multidimensional Hierarchical Classification (MHC) because this method focuses on determining the best path in the classification process and using the Naive Bayes Classifier to find probabilities that have high values ​​from the data. Data that used were 1885 secondary data form UCI Machine Learning with the title Drug Consumption which is divided into 7 classes based on the last time use of cannabis. Steps of this research conducting MHC training process and testing process using MHC. Testing process were carried out using 3 testing process, K-Fold Cross Validation with k = 5, testing with overall data and with balanced data. Testing results shows that the highest accuracy value is 42,86% using testing with balanced data.
Co-Authors Adinugroho, Sigit Bayu Rahayudi