Article Per Year (5 Year)
p-Index From 2021 - 2026
1.407
P-Index
This Author published in this journals
All Journal Building of Informatics, Technology and Science MEANS (Media Informasi Analisa dan Sistem) Jurnal Pengabdian Masyarakat (ABDIRA) Journal Global Technology Computer Jurnal Sains dan Teknologi Informasi Jurnal Ilmu Pengetahuan dan Teknologi Bagi Masyarakat Journal Of Computer Engineering And Information Technology
Asprina Br Surbakti, Asprina Br
STT Poliprofesi Medan
Aerospace Engineering Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Mechanical Engineering Nursing Social Sciences Other

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Journal Global Technology Computer

 1 
Penerapan Sistem Pakar dengan Metode Naive Bayes pada Kerusakan Motor Injeksi Sinaga, Marito Romaida; Sianipar, Lilin; Laia, Naomita; Bawamenewi, Nelis Sastraman; Surbakti, Asprina Br; Danur, Surizar Rahmi
Journal Global Technology Computer Vol 4 No 3 (2025): Agustus 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jogtc.v4i3.8190

Abstract

An injection engine is a motorized vehicle that uses a fuel injection system directly into the combustion chamber through an injector that is electronically controlled by the ECU. However, mechanics often encounter obstacles and difficulties in checking for damage to the injection engine, so that checks are still carried out manually on the injection engine. To overcome this problem, one solution is to utilize an analysis method that can help and facilitate mechanics in determining damage to the injection engine. This method was chosen with the aim of being able to identify the type of damage and provide solutions related to existing problems. The purpose of this study is to analyze and identify the types of damage to the injection engine using the Naïve Bayes method, as well as to determine the probability level of each damage so that it can provide more accurate information for the repair process. The results of the calculation test using the Naïve Bayes method show that problematic injection sensor damage is the damage with the highest value of 72.8%.
Penerapan Metode MAUT dalam Penentuan Kelayakan Tenaga Kerja Indonesia Keluar Negeri dengan Pembobotan ROC Ginting, Leonardo; Edelweis, Edelweis; Irpanto, Irpanto; Hulu, Zulima Berkat; Sembiring, David JM; Surbakti, Asprina Br
Journal Global Technology Computer Vol 4 No 3 (2025): Agustus 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jogtc.v4i3.8292

Abstract

Determining the eligibility of Indonesian Migrant Workers (TKI) to travel abroad is a complex process because it involves many criteria that must be considered objectively. This study proposes the application of the Multi-Attribute Utility Theory (MAUT) method in decision-making by weighting criteria using the Rank Order Centroid (ROC) method. The ROC method is used to generate criteria weights based on priority levels, thus providing a fairer proportion in the calculation. Furthermore, the MAUT method is used to normalize the data, calculate utility values, and determine the final score of each alternative. The purpose of this study is to develop a Decision Support System model that can help determine the eligibility of Indonesian Migrant Workers (TKI) to travel abroad more objectively, measurably, and systematically, so that the selection process does not only rely on subjective considerations, but also uses a quantitative approach to improve the accuracy of the decision results. This study uses five assessment criteria with ten alternatives as data samples. The calculation results show that criteria with higher priorities have a significant influence on the final result. From the data processing process, it was obtained that Alternative A7 had the highest preference value of 0.945 and was recommended as the best alternative, followed by A3 with a value of 0.926 and A9 with a value of 0.865, while the alternative with the lowest score was A8 with a value of 0.608. The results of this study prove that the integration of the ROC and MAUT methods can produce an objective, transparent, and systematic decision support system in determining the feasibility of alternatives, as well as assisting decision makers in a more accurate and measurable selection process.
Penerapan Algoritma Decision Tree Data Mining untuk Prediksi Pola Pemberian Kredit pada Koperasi Simpan Pinjam Ginting, Winda Widia Br; Sitepu, Harun Rivaldo; Nainggolan, Laksono; Purba, Andrean Saputra; Surbakti, Asprina Br; Utomo, Dito Putro
Journal Global Technology Computer Vol 4 No 3 (2025): Agustus 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jogtc.v4i3.8336

Abstract

Savings and Loan Cooperatives (KSP) play a crucial role in providing access to financing for the public, particularly in underbanked areas. However, lending through KSPs often faces challenges related to the accuracy of creditworthiness assessments, which largely rely on subjective assessments and manual procedures, resulting in the risk of non-performing loans. This study aims to develop a creditworthiness prediction model using the Decision Tree algorithm to improve the accuracy and efficiency of the credit decision-making process. The Decision Tree algorithm was chosen for its ability to classify customers based on historical data in a manner that is easy to understand and interpret. In this study, customer data, including attributes such as Borrower Credit History, Financial Status, Income Amount, Employment Status, and Loan Amount, was used to construct a decision tree. The results showed that the Decision Tree model achieved an accuracy of 86.67%, indicating its effectiveness in predicting creditworthiness and its reliability in supporting credit granting decisions in savings and loan cooperatives. This research contributes to reducing the risk of non-performing loans and improving the efficiency of decision-making in savings and loan cooperatives through the application of data mining techniques based on historical customer data analysis.
Co-Authors Agnesia, Mella Ashari, Runi Bangun, Zuriah Rezky Br Bawamenewi, Nelis Sastraman Br Ginting, Lastri Marsely Danur, Surizar Rahmi Dini Lestari, Dini Dito Putro Utomo Edelweis, Edelweis Ginting, Clusilla Via Mia Dalmatia Br Ginting, Jenni Veronika Br Ginting, Leonardo Ginting, Rahelya Br Ginting, Winda Widia Br Hulu, Zulima Berkat Ilham, Safarul Irpanto, Irpanto Kaban, Debi Yolanda Kaban, Roberto Laia, Naomita Mehuli Br PA, Sinek Meiliyani Br Ginting, Meiliyani Br Naim, Muhammad Akmal Nainggolan, Laksono Nasution, Vikram Taufik Purba, Andrean Saputra Rahayu, Cici Raheliya Br Ginting, Raheliya Br Sari , Sri Novida Sembiring, David JM Sianipar, Lilin Sinaga, Marito Romaida Sitepu, Harun Rivaldo