Article Per Year (5 Year)
p-Index From 2019 - 2024
0.444
P-Index
This Author published in this journals
All Journal Jurnal Komputer Terapan PREDATECS: Public Research Journal of Engineering, Data Technology and Computer Science
Devy Safira
UNIVERSITAS ISLAM NEGERI SULTAN SYARIF KASIM RIAU
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Perbandingan Algoritma C4.5 dengan C4.5+Particle Swarm Optimization untuk Klasifikasi Angkatan Kerja Devy Safira; Mustakim
Jurnal Komputer Terapan  Vol. 7 No. 2 (2021): Jurnal Komputer Terapan
Publisher : Politeknik Caltex Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (300.395 KB) | DOI: 10.35143/jkt.v7i2.5143

Abstract

In a large dataset, data mining is a solution to arrange new models into useful information. The algorithm is often used in machine learning is C4.5. This algorithm is known to be very strong in classifying, but has several weaknesses, such as overlapping and overfitting of data. To handle this, it is necessary to select an attribute that can identify the relevant attribute without reducing the accuracy of the algorithm itself. The Particle Swarm Optimization (PSO) is an optimization algorithm which one can be used as an attribute selection. The PSO benefit is that to easy to use, efficient and has a simple concept when to compared of data mining algorithms and other optimization techniques. In this study, the precision of C4.5 which is optimized by Particle Swarm Optimization (PSO) algorithm is proven to be higher than using the C4.5 algorithm alone. Where the algorithm C4.5+PSO has an precision of 66.80% while the algorithm of C4.5 has an precision of 76.32%.
Implementation of Naïve Bayes Classifier for Classifying Alzheimer’s Disease Using the K-Means Clustering Data Sharing Technique Wildani Putri; Delvi Hastari; Kunni Umatal Faizah; Siti Rohimah; Devy Safira
Public Research Journal of Engineering, Data Technology and Computer Science Vol. 1 No. 1: PREDATECS July 2023
Publisher : Institute of Research and Publication Indonesia (IRPI).

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/predatecs.v1i1.803

Abstract

Alzheimer's disease is a neurodegenerative disease that is very universal and characterized by memory loss and cognitive function decline which ultimately leads to dementia. In 2015, it is estimated that around million people worldwide will suffer from Alzheimer's disease or dementia. Globally, the number of Alzheimer's diseases will increase from 26.6 million in 2006 to 106.8 million cases in 2050. Due to the large number of people with Alzheimer's disease, it is necessary to classify symptoms that lead to indicators of Alzheimer's disease, so that data mining methods are used for data processing. Alzheimer's data taken from Kaggle amounted to 373 records, through the stages of data preprocessing, data sharing using the Hold-Out method and clustering with AK-Means algorithm. The data is processed using data mining techniques using NBC algorithms. Validation testing the accuracy value obtained the result that the NBC algorithm with K-Means Clustering data sharing has relatively better accuracy than the hold-Out method of 91.89%.
Co-Authors Delvi Hastari Kunni Umatal Faizah Mustakim Siti Rohimah Wildani Putri