Article Per Year (5 Year)
p-Index From 2019 - 2024
0
P-Index
This Author published in this journals
All Journal Paradigma
Amrin Amrin
AMIK BSI JAKARTA
Computer Science & IT

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Perbandingan Metode Neural Network Model Radial Basis Function Dan Multilayer Perceptron Untuk Analisa Risiko Kredit Mobil Amrin Amrin
Paradigma Vol 20, No 1 (2018): Periode Maret 2018
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (670.692 KB) | DOI: 10.31294/p.v20i1.2783

Abstract

Problems are often encountered in the provision of credit is to determine lending decisions to someone, while other issues are not all credit payments can run well. Among the causes are errors of judgment in making credit decisions. In this study will be used  neural network with radial basis function method and neural network with multilayer perceptron method to analyze the risk of car credit,  then compare which method is the better. From the test results to measure the performance of the method is to use testing methods confusion matrix and ROC curve, it is known that the method of  neural network with multilayer perceptron is better than method of neural network with radial basis function where has  a value of accuracy is 96,1%  and value of AUC is 0.999. This shows that the model produced, including the classification is Exellent Clasification because it has the value of AUC  between 0.90- 1.00.
Aplikasi Diagnosa Penyakit Tuberculosis Menggunakan Algoritma Data Mining Amrin Amrin; Hafdiarsya Saiyar
Paradigma Vol 20, No 2 (2018): Periode September 2018
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (531.95 KB) | DOI: 10.31294/p.v20i2.3932

Abstract

It is important for doctors to make an early diagnosis of tuberculosis in order to reduce the transmission of the disease to the wider community. In this study, the authors will apply and compare several methods of data mining classification, including AlgoritmaC4.5, Naïve Bayes, and Neural Network to diagnose tuberculosis disease, then compare which of the three methods are the most accurate. Based on the performance measurement results of the three models using Cross Validation, Confusion Matrix and ROC Curve methods, it is known that Naïve Bayes method is the best method with accuracy of 94.18% and under the curva (AUC) value of 0.977 , then neural network method with accuracy 89,89% and under the curva value (AUC) 0,975, and then C4.5 method with accuracy level equal to 84,56% and under the curva value (AUC) equal to 0,938. This shows that the three models that are produced including the category of classification is very good because it has an AUC value between 0.90-1.00.
DATA MINING DENGAN ALGORITMA APRIORI UNTUK PENENTUAN ATURAN ASOSIASI POLA PEMBELIAN PUPUK Amrin Amrin
Paradigma Vol 19, No 1 (2017): Periode Maret
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (761.458 KB) | DOI: 10.31294/p.v19i1.1836

Abstract

In order to find out what fertilizer purchased by consumers, can be done with analytical techniques that is the analysis of consumer buying habits. Detection of fertilizers often purchased simultaneously is done using association rules. In this research will be used a priori algorithm for determining the rules of association of fertilizer purchases. From the results of the discussion and analysis of data can be concluded that with the application of a priori algorithm in determining the combination between itemsets with minimum support of 20% and minimum confidence 75% found 6 association rules, which has the highest value of support and confidence is if the consumer made a purchase transaction of fertilizer Organic and urea fertilizers simultaneously with the value of 60% support and 86% confidence value. Thus, if there are consumers buying organic fertilizers, then the possibility of consumers buying urea fertilizer is 86%.
Analisa Kelayakan Pemberian Kredit Mobil Dengan Menggunakan Metode Neural Network Model Radial Basis Function Amrin Amrin
Paradigma Vol 19, No 2 (2017): Periode September 2017
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (556.771 KB) | DOI: 10.31294/p.v19i2.2283

Abstract

Problems are often encountered in the provision of credit is to determine lending decisions to someone, while other issues are not all credit payments can run well. Among the causes are errors of judgment in making credit decisions. In this study will be used  neural network with radial basis function method to analyze the feasibility of providing car loans. From the test results to measure the performance of the method is to use testing methods confusion matrix and ROC curve, it is known that the method of back neural network radial basis function has a value of 89,2% accuracy and AUC value of 0.9471. This shows that the model produced, including the classification is Exellent Clasification because it has the AUC values between 0.90- 1.00.
Co-Authors Hafdiarsya Saiyar