Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal JUITA : Jurnal Informatika International Journal of Cyber and IT Service Management (IJCITSM)
Tuga Mauritsius
Bina Nusantara University
Computer Science & IT Decision Sciences, Operations Research & Management

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

Found 2 Documents
Search

 1 
Creation of RAG Chatbot in Answering Queries Related to Banking Terms Using Microsoft Azure Cindy Aurora; Tuga Mauritsius
International Journal of Cyber ​​and IT Service Management (IJCITSM) Vol. 5 No. 2 (2025): October
Publisher : International Institute for Advanced Science & Technology (IIAST)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34306/ijcitsm.v5i2.209

Abstract

This study investigates the use of Natural Language Processing (NLP), specifically Large Language Models (LLM), to implement technology intelligence as a solution for supporting developers in understanding information-related terms, abbreviations, and business processes in the banking sector. The aim is to explore the effectiveness of integrating AI-powered chatbots, particularly through Retrieval Augmented Generation (RAG), to enhance software development in banking by providing fast, accurate responses. The methodology involves profiling data analysis and the development of a RAG based AI chatbot using the Microsoft Azure platform, integrating advanced NLP and LLM techniques to assist developers in navigating complex banking terms and processes efficiently. The results demonstrate that the RAG chatbot significantly improves operational efficiency by offering real-time, context-aware responses, enabling faster decision-making and reducing time spent on manual searches for information, which leads to faster software development cycles. This study contributes to the fields of NLP and LLM, particularly in the banking sector, by showcasing the benefits of RAG chatbots in improving operational efficiency and software development quality. The use of AI technologies provides substantial improvements in the development process, leading to enhanced productivity in the banking industry.
Optimizing Diabetic Retinopathy Classification Using EfficientNet-B3 with Data Augmentation and Oversampling A A JE Veggy Priyangka; Tuga Mauritsius
JUITA: Jurnal Informatika JUITA Vol. 14 Issue 2, July 2026
Publisher : Department of Informatics Engineering, Universitas Muhammadiyah Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30595/juita.v14i2.30410

Abstract

Diabetic retinopathy (DR) is a leading cause of preventable blindness among diabetes patients. This study optimizes DR severity classification using EfficientNet-B3 with transfer learning combined with data handling strategies. Using the APTOS 2019 dataset containing 3,662 retinal fundus images across five severity classes, three experimental scenarios were evaluated: (1) baseline CNN, (2) CNN with data augmentation, and (3) CNN with data augmentation and random oversampling. Performance was measured using Quadratic Weighted Kappa (QWK), accuracy, precision, recall, F1-score, and ROC-AUC. Results demonstrate that Scenario III achieves the best performance with QWK of 0.8496 and accuracy of 77.00%, representing significant improvement over baseline (QWK: 0.4998) and augmentation-only models (QWK: 0.5728). The combination of data augmentation and random oversampling effectively addresses class imbalance in medical image datasets. This study provides empirical evidence on combining transfer learning with data balancing strategies for automated DR screening systems.
Co-Authors A A JE Veggy Priyangka Cindy Aurora