cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Usman Ependi
Contact Email
usmanependi@adsii.or.id
Phone
081271103018
Journal Mail Official
usmanependi@adsii.or.id
Editorial Address
Jl AMD, Lr. Tanjung Harapan, Taman Kavling Mandiri Sejahtera B11, Kel. Talang Jambe, Kec. Sukarami, Palembang, Provinsi Sumatera Selatan, 30151
Location
Unknown,
Unknown
INDONESIA
Journal of Information Systems and Informatics
Published by Asosiasi Doktor Sistem Informasi Indonesia
ISSN : 26565935     EISSN : 26564882     DOI : 10.63158/journalisi
Core Subject : Science,
Computer Science & IT
Journal-ISI is a scientific article journal that is the result of ideas, great and original thoughts about the latest research and technological developments covering the fields of information systems, information technology, informatics engineering, and computer science, and industrial engineering which is summarized in one publisher. Journal-ISI became one of the means for researchers to publish their great works published two times in one year, namely in March and September with e-ISSN: 2656-4882 and p-ISSN: 2656-5935.
Arjuna Subject : -
Articles 832 Documents
 78   79   80   81   82 
Lung X-ray Image Classification for Distinguishing Tuberculosis and Pneumonia Using Pretrained CNN Feature Extractors and Supervised Classifiers Ardian Mohib; Imam Yuadi; Ira Puspitasari; Yusi Dyah Patriani
Journal of Information System and Informatics Vol 8 No 3 (2026): June
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i3.1595

Abstract

Tuberculosis (TB) and pneumonia (PNA) are infectious lung diseases with overlapping chest X-ray (CXR) manifestations, making automated differential classification clinically important and methodologically challenging. This study proposes a supervised CXR classification workflow to distinguish TB from PNA using pretrained convolutional neural network (CNN) feature extractors and supervised classifiers. A publicly available de-identified dataset comprising 390 TB and 390 PNA images was used. Images were screened to exclude duplicates, corrupted files, non-CXR images, unclear labels, and identifiable cases. Preprocessing included format standardization, resizing according to CNN input requirements, and normalization. To reduce augmentation-based leakage risk, no heavy pre-validation augmentation was applied. Image embeddings were extracted using VGG-16, Inception V3, and VGG-19, then classified using Logistic Regression, Support Vector Machine, and Neural Network models. Performance was evaluated using stratified 5-fold cross-validation with AUC, accuracy, F1-score, precision, recall, MCC, and confusion matrix analysis. The Inception V3–Logistic Regression combination achieved the best performance, with AUC of 0.999, accuracy of 0.992, F1-score of 0.992, and MCC of 0.985.
An Explainable AHP with Sensitivity Analysis Approach for Strategic IT Project Prioritization in Higher Education Hilyah Magdalena; Ade Septryanti
Journal of Information System and Informatics Vol 8 No 3 (2026): June
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i3.1597

Abstract

This study addresses the strategic challenges faced by private universities in Indonesia in selecting the most suitable IT project to support digital transformation, comparing a Next-Generation Learning Management System (LMS) and an Integrated University Mobile Super-App. Rather than developing a new method, this study enhances the conventional Analytical Hierarchy Process (AHP) by integrating sensitivity analysis and priority decomposition to improve decision explainability (Explainable MCDM). Expert assessments were collected from five academic stakeholders using pairwise comparisons based on Saaty's scale. Four criteria were assessed: Strategic Alignment, Benefits & Impact, Feasibility & Resources, and Risk Assessment. The results show a narrow preference for the LMS (50.7%) over the Super-App (49.3%), primarily driven by its superiority on the highest-weighted criterion, Strategic Alignment (35.6%), particularly the "Support for Core Educational Goals" sub-criterion. Sensitivity analysis reveals that the ranking would reverse if the Benefits & Impact weight increases from 0.200 to above 0.278. This study provides a transparent, replicable, explainable AHP framework that enables decision-makers to understand not only what is recommended but also why and under what conditions the recommendation changes.
Modeling Generative AI Adoption in Higher Education: The Role of Interface Quality, Algorithmic Transparency, and Trust in Human-AI Interaction Baiq Yulia Fitriyani; Khairul Imtihan; Amrullah; Maulana Ashari; Wire Bagye
Journal of Information System and Informatics Vol 8 No 3 (2026): June
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i3.1598

Abstract

This study examines generative artificial intelligence (AI) adoption in higher education by integrating interface quality, algorithmic transparency, and trust within a Human-AI Interaction framework. The study addresses limitations of traditional technology acceptance models, which often overlook psychological and relational factors in AI-enabled environments. Data were collected through a cross-sectional survey of 195 respondents, including students, lecturers, and administrative staff from higher education institutions in West Nusa Tenggara, Indonesia, within a cross-sectional regional sample, and analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The results show that Trust in AI is the strongest predictor of Behavioral Intention (β = 0.623, p < 0.001), followed by Perceived Usefulness (β = 0.270, p < 0.05). Interface Quality significantly affects Perceived Ease of Use (β = 0.803), while Algorithmic Transparency strongly influences Perceived Control (β = 0.824) and Perceived Usefulness (β = 0.562). AI Anxiety was not found to have a significant direct or moderating effect. The model demonstrates substantial explanatory power (R² = 0.710) and strong predictive relevance. This study proposes an integrated dual-path model combining cognitive and affective mechanisms to explain generative AI adoption in higher education. The findings emphasize that AI systems should be designed not only for functionality, but also for trust, transparency, and user confidence.
Two-Stage Tuning of Machine Learning Models for Heart Disease Classification on Synthetic Data Marini; Tri Sugihartono; Chandra Kirana; Benny Wijaya; Hamidah
Journal of Information System and Informatics Vol 8 No 3 (2026): June
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i3.1599

Abstract

Heart disease remains a leading global cause of mortality, highlighting the need for accurate early risk classification. This study benchmarks Random Forest, XGBoost, and Logistic Regression for heart disease risk classification using a synthetic, perfectly balanced dataset, while addressing performance limitations caused by inadequate hyperparameter configuration. The dataset comprised 70,000 samples with a 50/50 class distribution and 18 clinical and demographic features. Although useful for controlled benchmarking, synthetic balanced data may yield optimistic estimates and may not fully represent real-world clinical variability. Each model was implemented in a scikit-learn Pipeline with median imputation and, where applicable, standard scaling. A two-stage tuning strategy was applied by combining RandomizedSearchCV with GridSearchCV refinement to optimize model configurations systematically. Under these benchmarking conditions, XGBoost achieved the best test performance, with an F1-score of 99.34%, AUC-ROC of 99.97%, and accuracy of 99.34%. Random Forest obtained an F1-score of 99.20% and AUC-ROC of 99.95%, while Logistic Regression achieved an F1-score of 99.12% and AUC-ROC of 99.95%. Age, pain in the arms/jaw/back, and cold sweats/nausea were the most influential predictors. The proposed framework is reproducible, computationally efficient, and suitable for validation on heterogeneous clinical datasets.
Explainable AI for Water Quality Classification Using Ensemble Stacking Windha MP Dhuhita; Hastari Utama; Hartatik; Bayu Setiaji; Haryoko
Journal of Information System and Informatics Vol 8 No 3 (2026): June
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i3.1601

Abstract

This study proposes a robust and interpretable machine learning framework for water quality classification using a publicly available water quality dataset containing 7,996 samples and 20 physicochemical features with an imbalanced class distribution (88.59% majority and 11.41% minority). The study addresses the critical issue of biased classification toward the majority class, which can lead to risk-prone misclassification of unsafe water. An ensemble stacking model combining XGBoost, LightGBM, and CatBoost with a Random Forest meta-learner (passthrough) was developed using an anti-leakage pipeline integrating RobustScaler and SMOTE within stratified 80:20 train–test cross-validation, while hyperparameter tuning was optimized using F1-score to improve minority-class performance; SHAP was further applied for global and local explainability. The proposed model achieved an F1-score of 0.8563 for the minority class and a ROC-AUC of 0.9846, indicating strong discriminative performance, while SHAP analysis identified ammonia as the most influential feature and revealed that False Negative errors were mainly caused by complex feature interactions. The study contributes an integrated framework combining stacking ensemble learning, anti-leakage evaluation, and SHAP-based global–local interpretation to support more reliable and transparent water quality classification; however, the findings are currently limited to a single dataset and and require multi-dataset validation.
Empirical CPU–Memory Benchmarking for Long-Read Genome Assembly Resource Optimization in High-Performance Computing Fatayat; Tisha Melia; Dwipa Amedihardjo
Journal of Information System and Informatics Vol 8 No 3 (2026): June
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i3.1602

Abstract

Efficient resource utilization is a critical challenge in High-Performance Computing (HPC) environments, particularly for long-read genome assembly workflows that require substantial computational resources. This study presents an empirical benchmarking framework to optimize resource allocation for de novo long-read genome assembly of Acacia crassicarpa. Nine experimental scenarios were evaluated by varying CPU cores (32, 48, and 64) and memory allocations (32 GB, 64 GB, and 128 GB) managed via the Slurm workload manager. Performance was assessed based on execution time, assembly continuity (N50), and biological completeness using BUSCO. The results demonstrate that CPU scalability significantly impacts performance, reducing execution time by up to 49% when scaling from 32 to 64 cores. Conversely, increasing memory allocation beyond 64 GB yielded no significant improvements in assembly quality, highlighting the risks of resource over-provisioning. Scenario 2 (64 CPU cores and 64 GB RAM) was selected as the optimal configuration because it balanced runtime, N50 continuity, memory efficiency, and BUSCO completeness, not because it produced the absolute shortest runtime. Under Scenario 2, the workflow achieved an average runtime of 59 hours 39 minutes 40 seconds, an N50 value of 7.8 Mb, and a genome completeness score of 99.8%. These findings provide practical guidance for resource planning and workload scheduling in shared HPC-based genomic workflows.
PCOS Classification Using Random Forest, Recursive Feature Elimination, and Explainable AI Syifa Ayu Salsabila Putri; Rona Nisa Sofia Amriza
Journal of Information System and Informatics Vol 8 No 3 (2026): June
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i3.1603

Abstract

Ovary Syndrome (PCOS) is an endocrine-related condition predominantly affecting women during their childbearing years who experience delayed diagnosis due to the limitations of conventional methods that require laboratory tests and imaging procedures that are relatively costly and time-consuming. This study develops a PCOS classification model based on a clinical dataset of 541 patients with 42 clinical attributes using the random forest algorithm with Recursive Feature Elimination (RFE) feature selection and an Explainable AI (XAI) approach. The research pipeline comprised several sequential stages: problem identification, data collection, preprocessing, data splitting, feature selection, model training and testing, evaluation, and SHAP-based explainability analysis. Performance was evaluated using Accuracy, Precision, Recall, and F1-score, and compared between two models, namely RF+CF and RF+RFE, where RF+RFE was identified as the best-performing model. The XAI approach using SHAP (SHapley Additive exPlanations) was applied to identify and explain the contribution of clinical variables to the classification results. The best model, RF+RFE, achieved an accuracy of 92.66%, precision of 93.75%, recall of 83.33%, and F1-score of 88.24%, demonstrating superior performance compared to RF+CF. As this study relies on a single dataset, broader validation across multiple centers is recommended before clinical deployment. This model is intended as a screening-support approach and has not been validated as a clinical diagnostic tool. The findings are anticipated to serve as a foundation for building data-driven early screening tools and clinical decision-making support systems.
Mapping Sentiment Analysis in Educational Technology: OpenAlex Bibliometrics, Thematic Trends, and Research Gaps (2013-2025) Dany Pratmanto; Fabriyan Fandi Dwi Imaniawan
Journal of Information System and Informatics Vol 8 No 3 (2026): June
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i3.1604

Abstract

This study aims to map the intellectual structure, publication growth, collaboration patterns, thematic evolution, and research gaps of sentiment analysis in educational technology. The study addresses the lack of an open and integrated bibliometric synthesis that connects productivity, collaboration, topic modelling, and gap detection in this field. A bibliometric and science-mapping approach was applied using OpenAlex-indexed publications from 2013 to 2025. After deduplication and eligibility screening, 977 publications were analysed, while 768 papers with sufficient abstract text were used for Non-negative Matrix Factorisation topic modelling. The analysis included publication trend analysis, country and institutional productivity, co-authorship networks, keyword burst analysis, geographic gap analysis, and platform mention analysis. The results show that annual publications increased from 22 papers in 2013 to 123 papers in 2024, with India and China as the most productive countries. Six thematic clusters were identified: Learning Analytics, Social Media Sentiment, Emotion Recognition, MOOCs and E-learning, Transformers/LLMs, and ML Classifier Ensembles. Learning Analytics was the largest cluster, while Transformers/LLMs showed the fastest recent growth. The novelty of this study lies in its reproducible OpenAlex-based bibliometric framework, which integrates performance analysis, science mapping, thematic evolution, and research gap identification for sentiment analysis in educational technology.
Key Scalability Effects on Entropy and Computational Complexity in a GA-SA Hybrid Cryptosystem Naufal Muzakki; Nur Rochmah Dyah Puji Astuti
Journal of Information System and Informatics Vol 8 No 3 (2026): June
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i3.1607

Abstract

Digital data security demands robust encryption systems in which key randomness quality serves as the primary determining factor. Metaheuristic algorithms such as the Genetic Algorithm (GA) and Simulated Annealing (SA) exhibit significant potential for key generation optimization. However, each is individually susceptible to premature convergence and slow computational time, respectively, motivating their sequential hybridization. This study proposes a GA-SA hybrid cryptographic architecture with dynamic population sizing to optimize pseudo-random keystream generation in XOR encryption, evaluated using 15 PDF document datasets across three key configurations: 16 characters (128-bit), 32 characters (256-bit), and 64 characters (512-bit). The hybrid system consistently reduced local optima entrapment across all configurations, with the 64-character key achieving the highest randomness quality at a Shannon Entropy of 7.9288 bits/byte and a mean NIST SP 800-22 Monobit Frequency Test P-Value of 0.2999, though this does not constitute a full NIST SP 800-22 suite evaluation. Runtime analysis showed near-linear empirical growth within the tested range, from 0.0361 seconds to 0.1305 seconds, without exponential bottleneck effects, suggesting the proposed architecture is a promising candidate for pseudo-random keystream generation under tested conditions, with further validation recommended before production deployment.
Designing Smart-Contract-Enabled Liquidity Management for Wholesale Rupiah Digital: A Design Science Research Approach Satria Rana Dityantomo; Made Harta Dwijaksara
Journal of Information System and Informatics Vol 8 No 3 (2026): June
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i3.1609

Abstract

This study proposes a smart-contract-enabled liquidity management reference architecture for Bank Indonesia's Wholesale Rupiah Digital (wRD), addressing a gap in Project Garuda where the Proof-of-Concept adopts a gross settlement model supplemented by decentralized queueing but lacks a liquidity-saving mechanism. Using Design Science Research (DSR), a Multivocal Literature Review (MLR) was conducted to synthesize eight academic and grey literature sources that include central bank reports, BIS publications, and industry white papers. Five key takeaways were extracted and mapped to architectural modules. The resulting architecture operates on a unified ledger and comprises five modules: a Policy & Criteria smart contract for participant eligibility and compliance, a centralized Queue smart contract with configurable release rules, a Liquidity-Saving Mechanism (LSM) for periodic multilateral netting, an Automated Liquidity Provisioning (ALP) module for just-in-time intraday repo against tokenized bonds when netting is insufficient, and a guarded Automated Market Maker (AMM) for cross-currency settlement. The architecture is illustrated through a payment state lifecycle with two scenario transaction walkthroughs and assessed through a criteria-based analytical evaluation that verifies design completeness against requirements. Empirical validation through prototyping, simulation, or expert review is left for future work. The main contribution is a literature-derived reference architecture that integrates global CBDC mechanisms adapted to Indonesia's context.

Page 80 of 84 | Total Record : 832

 78   79   80   81   82 

Filter by Year

2019 2026


Reset
Filter By Issues
All Issue Vol 8 No 3 (2026): June Vol 8 No 2 (2026): April Vol 8 No 1 (2026): February Vol 7 No 4 (2025): December Vol 7 No 3 (2025): September Vol 7 No 2 (2025): June Vol 7 No 1 (2025): March Vol 6 No 4 (2024): December Vol 6 No 3 (2024): September Vol 6 No 2 (2024): June Vol 6 No 1 (2024): March Vol 5 No 4 (2023): Journal of Information Systems and Informatics Vol 5 No 3 (2023): Journal of Information Systems and Informatics Vol 5 No 2 (2023): Journal of Information Systems and Informatics Vol 5 No 1 (2023): Journal of Information Systems and Informatics Vol 4 No 4 (2022): Journal of Information Systems and Informatics Vol 4 No 3 (2022): Journal of Information Systems and Informatics Vol 4 No 2 (2022): Journal of Information Systems and Informatics Vol 4 No 1 (2022): Journal of Information Systems and Informatics Vol 3 No 4 (2021): Journal of Information Systems and Informatics Vol 3 No 3 (2021): Journal of Information Systems and Informatics Vol 3 No 2 (2021): Journal of Information Systems and Informatics Vol 3 No 1 (2021): Journal of Information Systems and Informatics Vol 2 No 2 (2020): Journal of Information Systems and Informatics Vol 2 No 1 (2020): Journal of Information Systems and Informatics Vol 1 No 2 (2019): Journal of Information Systems and Informatics Vol 1 No 1 (2019): Journal of Information Systems and Informatics More Issue