Article Per Year (5 Year)
p-Index From 2020 - 2025
0.92
P-Index
This Author published in this journals
All Journal Journal of Intelligent Decision Support System (IDSS) Jurnal Bumigora Information Technology (BITe) Jurnal Mandiri IT
Rimbawa, H.A Danang
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Library & Information Science Mathematics

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Improving Large Language Model’s Ability to Find the Words Relationship Alam, Sirojul; Abdul Jabar, Jaka; Abdurrachman, Fauzi; Suharjo, Bambang; Rimbawa, H.A Danang
Jurnal Bumigora Information Technology (BITe) Vol 6 No 2 (2024)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/bite.v6i2.4127

Abstract

Background: It is still possible to enhance the capabilities of popular and widely used large language models (LLMs) such as Generative Pre-trained Transformer (GPT). Using the Retrieval-Augmented Generation (RAG) architecture is one method of achieving enhancement. This architectural approach incorporates outside data into the model to improve LLM capabilities. Objective: The aim of this research is to prove that the RAG can help LLMs respond with greater precision and rationale. Method: The method used in this work is utilizing Huggingface Application Programming Interface (API) for word embedding, store and find the relationship of the words. Result: The results show how well RAG performs, as the attractively rendered graph makes clear. The knowledge that has been obtained is logical and understandable, such as the word Logistic Regression that related to accuracy, F1 score, and defined as a simple and the best model compared to Naïve Bayes and Support Vector Machine (SVM) model. Conclusion: The conclusion is RAG helps LLMs to improve its capability well.
Redefining hash functions for quantum security with SHA 256 Riswantoro, Dadan Shavkat; Rimbawa, H.A Danang
Journal of Intelligent Decision Support System (IDSS) Vol 8 No 2 (2025): June: Intelligent Decision Support System (IDSS)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/idss.v8i2.301

Abstract

The rapid advancement of quantum computing technology presents a significant challenge to the field of cryptography, particularly affecting the security of hash functions that form the foundation of many cryptographic protocols. Hash functions are widely used to ensure data integrity, generate digital signatures, and securely store passwords. However, the emergence of quantum algorithms—such as Grover’s algorithm—threatens to undermine the security assumptions on which these hash functions are based by significantly reducing their effective security levels.  This paper aims to provide a comprehensive analysis of the vulnerabilities introduced by quantum computing to traditional hash functions, detailing how these weaknesses can be exploited by quantum adversaries. We explore the fundamental properties of hash functions, including pre-image resistance, second pre-image resistance, and collision resistance, and assess how these properties are affected in a quantum context. Furthermore, we examine the implications of these vulnerabilities for existing cryptographic systems and emphasize the urgent need for the development of post-quantum cryptographic standards. In response to these challenges, we review ongoing research efforts focused on designing hash functions that are resilient to quantum attacks. We evaluate several promising candidates for post-quantum hash functions, considering their security properties, performance metrics, and practical applicability. The findings of this paper highlight the necessity of transitioning to post-quantum cryptographic solutions to safeguard sensitive information in an increasingly quantum-capable world. Ultimately, we advocate for proactive measures within the cryptographic community to adopt and implement these new standards, thereby ensuring robust data security in the age of quantum computing.
Artificial intelligence-based hand gesture recognition for sign language interpretation Rais, M. Fazil; AlFatrah, M. Ilham; Noorta, Chadafa Zulti; Rimbawa, H.A Danang; Atturoybi, Abdurrosyid
Jurnal Mandiri IT Vol. 14 No. 1 (2025): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i1.395

Abstract

This paper presents an artificial intelligence-based system for real-time hand gesture recognition to support sign language interpretation for the deaf and hard-of-hearing community. The proposed system integrates computer vision techniques with deep learning models to accurately identify static hand gestures representing alphabetic signs. The MediaPipe framework is employed to detect and track hand landmarks from live video input, which are then processed and classified using a Convolutional Neural Network (CNN) model. The model is trained on a publicly available BISINDO (Bahasa Isyarat Indonesia) gesture dataset retrieved from Kaggle, comprising 312 images across 26 hand gestures captured under multiple background conditions. Preprocessing includes resizing, grayscale conversion, data augmentation, and landmark extraction with specific innovations in preprocessing techniques, such as the use of advanced data augmentation methods and landmark normalization, which significantly enhance gesture identification accuracy and model robustness. Experimental results show that the system achieves an average classification accuracy of 88.03% and maintains stable performance in real-time applications. Despite these promising results, the system exhibits limitations, including challenges with dynamic gesture recognition, background interference, and limited handling of complex hand movements, all of which can be explored in future research to improve the system’s accuracy and generalization. These findings highlight the system’s potential as an inclusive communication tool to bridge language barriers between deaf individuals and non-signers. This research contributes to the development of accessible assistive technologies by demonstrating a non-intrusive, vision-based approach to sign language interpretation. Future development may involve dynamic gesture translation, sentence-level recognition, and deployment on mobile platforms.
Design and development of an IoT-based archive room security system integrating RFID and fingerprint authentication for military document protection Tidar, R Haryo; Madramsyah, Adam; Rimbawa, H.A Danang; Sembali, Tryas Putranto
Jurnal Mandiri IT Vol. 14 No. 1 (2025): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i1.440

Abstract

The objective of this research is to design and implement a secure, IoT-based dual-authentication system for protecting classified military archive rooms, in response to the growing urgency of safeguarding sensitive documents against real threats such as espionage, unauthorized access, and data tampering. Military archives store critical information essential for national defense operations, yet many facilities continue to rely on outdated physical security systems vulnerable to intrusion and lacking auditability. This research presents the design and implementation of a dual-authentication archive security system based on Internet of Things (IoT), integrating Radio Frequency Identification (RFID) and fingerprint biometrics. The system is developed using the Waterfall model, involving sequential stages of requirement analysis, system design, implementation, testing, and evaluation. The NodeMCU ESP32 microcontroller serves as the central controller, enabling real-time data transmission via Wi-Fi and notification delivery through the Telegram API. The RFID module performs initial identification, while the fingerprint sensor confirms biometric authentication. A solenoid lock mechanism provides physical access control, activated only upon successful dual verification. System testing under simulated military archive conditions yielded an average response time of 4.59 seconds and an authentication accuracy of 90.6%. Additionally, the real-time notification feature enhanced situational awareness by informing administrators of all access events—both valid and unauthorized. The results indicate that combining RFID and fingerprint authentication significantly improves system security, auditability, and operational efficiency compared to single-factor or conventional methods. This system demonstrates the potential for scalable, adaptable application in high-security institutional environments. Future development may include integration of backup power supplies, encrypted communication protocols, and expansion toward a more comprehensive digital security architecture. This research contributes to the advancement of smart security systems in military infrastructure, promoting proactive threat mitigation and enhanced document protection.
Improving Large Language Model’s Ability to Find the Words Relationship Alam, Sirojul; Abdul Jabar, Jaka; Abdurrachman, Fauzi; Suharjo, Bambang; Rimbawa, H.A Danang
Jurnal Bumigora Information Technology (BITe) Vol. 6 No. 2 (2024)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/bite.v6i2.4127

Abstract

Background: It is still possible to enhance the capabilities of popular and widely used large language models (LLMs) such as Generative Pre-trained Transformer (GPT). Using the Retrieval-Augmented Generation (RAG) architecture is one method of achieving enhancement. This architectural approach incorporates outside data into the model to improve LLM capabilities. Objective: The aim of this research is to prove that the RAG can help LLMs respond with greater precision and rationale. Method: The method used in this work is utilizing Huggingface Application Programming Interface (API) for word embedding, store and find the relationship of the words. Result: The results show how well RAG performs, as the attractively rendered graph makes clear. The knowledge that has been obtained is logical and understandable, such as the word Logistic Regression that related to accuracy, F1 score, and defined as a simple and the best model compared to Naïve Bayes and Support Vector Machine (SVM) model. Conclusion: The conclusion is RAG helps LLMs to improve its capability well.
Co-Authors Abdul Jabar, Jaka Abdurrachman, Fauzi Alam, Sirojul AlFatrah, M. Ilham Atturoybi, Abdurrosyid Madramsyah, Adam Noorta, Chadafa Zulti Rais, M. Fazil Riswantoro, Dadan Shavkat Sembali, Tryas Putranto Suharjo, Bambang Tidar, R Haryo