cover
Contact Name
Clara Hetty Primasari
Contact Email
clara.hetty@uajy.ac.id
Phone
-
Journal Mail Official
clara.hetty@uajy.ac.id
Editorial Address
-
Location
Kota yogyakarta,
Daerah istimewa yogyakarta
INDONESIA
Indonesian Journal of Information System
ISSN : 26230119     EISSN : 26232308     DOI : -
Core Subject : Science,
Arjuna Subject : -
Articles 7 Documents
Search results for , issue "Vol. 8 No. 2 (2026): February 2026" : 7 Documents clear
Adaptive Integration of Distributed Deep Q-Networks for Enhancing OLSR Routing in Dynamic Mobile Ad-Hoc Networks Tirta Segara, Alon Jala; Bahtiar, Arief Rais; Firmansyah, Muhammad Raafi'u; Wibowo, Fahrudin Mukti
Indonesian Journal of Information Systems Vol. 8 No. 2 (2026): February 2026
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v8i2.11760

Abstract

Adaptive routing in Mobile Ad-Hoc Networks (MANETs) poses considerable difficulty owing to the network's dynamic characteristics, lack of stable infrastructure, and swift topology alterations. The Optimized Link State Routing (OLSR) protocol provides a proactive routing mechanism via topology dissemination and MultiPoint Relay (MPR) selection. Nevertheless, it exhibits diminished responsiveness to real-time topology alterations, as it depends on periodic updates and does not explicitly account for link quality. This paper suggests the incorporation of the Deep Q-Network (DQN) methodology into OLSR as a reinforcement learning strategy to improve routing adaptability and efficiency. The DQN model employs network metrics like latency, ETX, buffer occupancy, and neighbor count as state inputs, with actions determined by Q-values obtained via environmental interactions. Simulations conducted with NS-3 and PyTorch demonstrate that OLSR-DQN enhances Packet Delivery Ratio (PDR) by as much as 20%, decreases delay by 15–25%, and markedly boosts throughput in dynamic MANET situations. Keywords: MANET, OLSR, Deep Q-Network, adaptive routing, reinforcement learning
Analysis of Risk Assessment Framework Using Agile Methodology and Computer-Aided Software Engineering Tools Monageng, Thapelo; Esiefarienrhe, Bukohwo Michael
Indonesian Journal of Information Systems Vol. 8 No. 2 (2026): February 2026
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v8i2.12359

Abstract

This research paper presents a risk assessment framework developed through the integration of the Scrum process with a Computer-Aided Software Engineering (CASE) tool, specifically Microsoft Excel. The framework aims to automate risk assessment processes, facilitating more accurate calculations of risk based on impact and probability using a matrix system. Initially, data is collected and recorded in the Risk Register, serving as the foundation for risk evaluation. The integration of the CASE tool enhances the efficiency and effectiveness of the process, allowing for real-time updates and tracking of risks. As updates occur within the Risk Register, a real-time dashboard is generated, providing stakeholders with an immediate overview of the risk landscape. The dashboard feature significantly improves decision making capabilities by presenting visual insights into risk levels and potential impacts on the projects. This dynamic monitoring tool is crucial for effective decision-making and timely responses to emerging risks. By leveraging agile methodologies design, this framework not only streamlines the risk management process but also ensures that relevant data is readily accessible to project teams. The findings from this research contribute to the fields of project management and software engineering by demonstrating the benefits of incorporating agile approaches with automated tools in risk assessment. The potential implications of this framework extend beyond individual projects, offering a model that can be adopted by various organizations seeking to enhance their risk management practices in a streamlined and efficient manner. Keywords: Risk Assessment, Scrum, CASE Tool, Risk Register, Dashboard
Exploring Gender-Based Preferences in TikTok Influencer Following Among Students at University of Technology Mthembu , Khulula Blessing; Poyise, Xolisa Philip; Motsilili, Phomolo; Mutanga, Murimo Bethel; Revesai, Zvinodashe
Indonesian Journal of Information Systems Vol. 8 No. 2 (2026): February 2026
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v8i2.12888

Abstract

The rise of short-form video platforms has fundamentally changed patterns of digital communication, with TikTok becoming a dominant influence in youth media consumption. However, gender-specific preferences in influencer choice remain underexamined, especially within African university settings. Based on Uses and Gratifications Theory (UGT), this qualitative exploratory study investigates how gender affects TikTok influencer following behaviours among 103 South African university students who were active TikTok users. Data were gathered via open-ended online questionnaires and analysed through Qualitative Content Analysis with dual-researcher coding to ensure reliability. Significant gender-based differences appeared in influencer preferences and motivational factors: male students (61% of the sample) mainly followed educational, motivational, and entrepreneurial influencers, seeking cognitive gratifications related to skill development and career prospects, while female students (39% of the sample) inclined towards lifestyle, beauty, and fashion influencers, prioritising affective gratifications like emotional resonance, identity exploration, and self-expression. Despite these differences, both groups valued influencer authenticity, relatability, and expertise over follower count or popularity metrics. The findings extend UGT application to algorithm-driven, short-form video platforms and show how gender influences digital media gratification-seeking behaviours, revealing TikTok as a multifaceted tool for identity building, emotional validation, and aspirational learning rather than just entertainment. These results inform gender-sensitive digital marketing, educational technology integration, and culturally relevant content creation for African youth markets, allowing universities to use these insights for more effective student engagement on social media. The study's focus on a single institution and its cross-sectional design limit broad applicability, indicating that future research should explore long-term influencer relationships and cross-cultural comparisons across African educational contexts. Keywords: Gender differences, social media, influencer preferences, TikTok, university students, Uses and Gratifications Theory
Financial Technology Adoption in Public Financial Management of South Africa: a Path Toward Digital Transformation Enwereji, Prince Chukwuneme; Stofile, Regina
Indonesian Journal of Information Systems Vol. 8 No. 2 (2026): February 2026
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v8i2.12959

Abstract

This study examines the adoption of Financial Technology in South African public sector financial management. The study adopted a qualitative research approach and depended on literature reviews for data collection. A total of 260 articles were downloaded for this study while only 11 articles were used after rigorous selection criteria. The findings show that mobile payments and digital banking have significantly improved financial inclusion, especially in urban areas, although adoption in rural regions has been slower due to challenges such as poor infrastructure and low digital literacy. More advanced FinTech solutions, like blockchain and Artificial Intelligence, are still in early stages. The adoption of FinTech has led to greater efficiency in government financial processes, automating tasks like payments and tax filings, which has reduced manual workloads and sped up service delivery. Blockchain technology has improved transparency and accountability and has allowed for better tracking of public funds and reducing the risk of fraud. However, the full potential of FinTech has been limited by barriers like outdated infrastructure, regulatory gaps, and resistance to change within the public sector. To unlock the full potential of FinTech, the study recommends among others, improving digital infrastructure, enhancing digital literacy, and strengthening regulatory frameworks. Keywords: Financial technology, Public financial management, Blockchain technology, Digital transformation, Financial inclusion, Digital financial services
Classification of Medical Complaints: Comparative Analysis of Machine Learning Algorithms with Determination of Dominant Factors Using Information Gain Catherine Santoso Prasetya; Sena, I Gede Wiarta Sena; Matthew Austen Fernando
Indonesian Journal of Information Systems Vol. 8 No. 2 (2026): February 2026
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v8i2.13128

Abstract

This research compares three machine learning algorithms: Random Forest (RF), Decision Tree (DT), and K-Nearest Neighbors (KNN) for classifying illnesses influenced by climate, patient history, and clinical indicators. The dataset obtained from Kaggle contains 5,200 records combining meteorological and symptom data. Two pre-processing scenarios were tested to examine their impact on model performance: (1) normalization using Min-Max, and (2) normalization followed by balancing with the Synthetic Minority Over-sampling Technique (SMOTE). Results show that normalization significantly improves KNN’s performance, increasing its accuracy from 0.324 on raw data to 0.968. In the first scenario, Random Forest achieved the highest accuracy of 0.985, followed by Decision Tree with 0.974 and KNN with 0.968. After applying SMOTE, Random Forest maintained stable accuracy at 0.985, while Decision Tree and KNN slightly decreased to 0.964. These findings indicate that Random Forest is the most robust and consistent algorithm for this classification task. Furthermore, the study reveals that SMOTE does not always enhance accuracy and must be applied selectively. Information gain analysis identifies symptom features as the strongest predictors. Overall, this research provides guidance in selecting the optimal algorithm and pre-processing strategy for building effective weather-related disease classification systems. Keywords: Classification of Diseases, Decision Tree, K-Nearest Neighbors, Random Forest, SMOTE
Design and Implementation of Blockchain in a Website-Based Electronic Medical Record System Using the Prototype Model Chotijah, Umi; Rosyid, Harunur; Sutaji, Deni; Guswanrinandi, Danang Haedar; Nabil , M. Rizaldi Zidan; Akbar , Muhammad Asad Muhibbin
Indonesian Journal of Information Systems Vol. 8 No. 2 (2026): February 2026
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v8i2.13498

Abstract

The security and integrity of medical record data is a crucial issue in the era of healthcare service digitalization. Traditional systems still face risks of manipulation, information leaks, and issues with interoperability between healthcare institutions. Blockchain technology has emerged as a promising solution to address this issue thanks to its features of decentralization, openness, and difficulty in modification. One consensus method that can be applied is Proof of Work (PoW), which has proven to maintain the authenticity of transactions on a distributed network. This research aims to design and evaluate a blockchain-based medical record application using the PoW consensus algorithm to ensure the security, transparency, and reliability of medical data storage. The approach used is experimental, involving the development of a blockchain-based application prototype. The PoW algorithm is applied to ensure the validity of medical record data transactions. The evaluation was conducted by measuring the security aspect (resistance to data changes), performance (time to verify transactions), and scalability (number of transactions that can be handled). The results of the experiment show that implementing PoW in a medical record system can maintain data integrity with a high level of resistance to unauthorized changes. The average time for transaction verification is 2.4 seconds per block, with the ability to handle up to 150 transactions per minute. Although the performance of PoW requires significant computational resources, the level of security it offers suggests potential for implementation in larger healthcare systems. The application of blockchain with the PoW algorithm to medical records has proven to improve the security and transparency of medical information. This research successfully met the established objectives, although computational efficiency issues still need to be addressed. Further research is suggested to explore other consensus algorithms such as Proof of Stake (PoS) or Practical Byzantine Fault Tolerance (PBFT) to improve performance without sacrificing security aspects. Keywords: Blockchain, Electronic Health Records (EHR), Proof of Work (PoW), Smart Contract, Healthcare Information System
Cross-Organizational Transferability of Early Default Prediction Models in Indonesia’s Motorcycle Leasing Industry Kristiawan, Ivan; Destyanto, Twin Yoshua R.; Bañez, Jeremy Laurence
Indonesian Journal of Information Systems Vol. 8 No. 2 (2026): February 2026
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v8i2.13954

Abstract

The motorcycle-leasing sector in Indonesia is critical for consumer financing, yet firms face persistent difficulty in predicting early installment defaults because most credit-risk models are built for single organizations, forcing companies to repeatedly rebuild models when policies or operations change, which increases costs and delays risk detection. This study examines whether early default prediction models developed in one motorcycle-leasing company can be transferred to others by applying a hierarchical framework that integrates feature engineering, behavioral clustering, and supervised classification. The model was trained on 113,222 fiduciary contracts (2011–2025) from a Batam-based firm and tested on two external firms in Batam and Jakarta using Logistic Regression, Random Forest, and LightGBM. Results show substantial performance decline for the second Batam firm but relatively stable performance in Jakarta, indicating that organizational policy differences matter more than regional factors. Fine-tuning with sufficient local data improves performance, while limited data creates instability. The study provides a practical foundation for scalable and transferable credit-risk modeling in emerging markets. Keywords: credit risk prediction; transfer learning; domain adaptation; motorcycle leasing; clustering.

Page 1 of 1 | Total Record : 7