Buana Suhurdin Putra
STMIK Mercusuar

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

Found 2 Documents
Search

Identification of Color and Texture of Ripe Passion Fruit with Perceptron Neural Network Method Siswanto; Riefky N. Sungkar; M. Anif; Basuki Hari Prasetyo; Subandi; Ari Saputro; Buana Suhurdin Putra
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 7 No 1 (2023): February 2023
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v7i1.4612

Abstract

Research using artificial neural network methods has been developed as a tool that can help human tasks, one of which is for passion fruit UMKM entrepreneurs. The problem so far that has been faced by UMKM entrepreneurs of passion fruit is that it is difficult to identify ripe passion fruit with sweet and sour taste, because there are 6 colors of passion fruit and the color of passion fruit skin is visually slightly different, as well as the texture of maturity. The main purpose of this study was to identify the color structure and texture of the ripeness of passion fruit, in order to recognize the color and texture of the ripeness of passion fruit which is good for processing into syrup, jam, jelly, juice, passion fruit juice powder by entrepreneurs of UMKM of passion fruit. This study empirically tested the color and texture of the ripeness of 10 passion fruit using the perceptron artificial neural network learning method. The data is obtained from an image that will be entered into the program. The results of the identification process using the perceptron artificial neural network from the tests that have been carried out previously, the highest calculation results obtained with the best results using a learning rate of 0.8 and 500 epoch iterations and producing an accuracy of 80%.
Penerapan Algoritma C4.5 , SVM Dan KNN Untuk Menentukan Rata-Rata Kredit Macet Koperasi Siswanto Siswanto; Riefky Sungkar; Basuki Hari Prasetyo; M.Anif; Subandi Subandi; Gunawan Pria Utama; Raden Sutiadi; Buana Suhurdin Putra
Prosiding SISFOTEK Vol 7 No 1 (2023): SISFOTEK VII 2023
Publisher : Ikatan Ahli Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

problem that often occurs is the difficulty in determining the average bad credit spread across 7,823 savings and loan cooperatives in Indonesia. The main problem faced by savings and loan cooperatives is the difficulty in identifying and mitigating credit risks that can cause bad credit. Bad credit not only harms cooperatives, but can also disrupt the financial stability of cooperative members. The lack of effective tools to measure and predict credit risk makes cooperatives potentially face unnecessary losses. The aim of this research is to apply the C4.5, SVM, and KNN algorithms in determining the average non-performing loans of savings and loan cooperatives, comparing the results and performance of the three such algorithms in the context of credit risk management, and improve understanding of the use of machine learning techniques in identifying credit risk patterns that may be difficult to detect manually. The application of the C4.5 Algorithm, SVM (Support Vector Machine), and KNN (K-Nearest Neighbors) models in determining the average bad credit in the context of savings and credit cooperatives is carried out by considering the appropriate configuration. This research first collects and preprocesses data which includes credit history, income, length of membership, and other related factors from savings and loan cooperatives. Next, factor analysis and feature selection are carried out to identify the factors that most influence credit risk. The results of the three models are evaluated using various evaluation metrics, such as accuracy, precision, recall, F1-score, and AUC-ROC. The results of this research The results show that the SVM model has the highest performance in predicting credit risk, followed by the C4.5 and KNN algorithms. Careful feature selection and robust model validation are also key components in accurate credit risk assessment. Thus, the results of this research can help cooperatives better manage credit risk and make more informed decisions regarding loan approvals.