cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Teguh Wiyono
Contact Email
indexsasi@apji.org
Phone
+6285700037105
Journal Mail Official
indexsasi@apji.org
Editorial Address
Jalan Watunganten 1 No 1-6, Batursari, Mranggen Kab. Demak Jawa Tengah 59567
Location
Kab. demak,
Jawa tengah
INDONESIA
Global Science: Journal of Information Technology and Computer Science
Published by International Forum of Researchers and Lecturers
ISSN : 31089976     EISSN : 31089968     DOI : 10.70062
Core Subject : Science,
Computer Science & IT
Global Science: Journal of Information Technology and Computer Science; This a journal intended for the publication of scientific articles published by International Forum of Researchers and Lecturers This journal contains studies in the fields of Information Technology and Computer Science, both theoretical and empirical. This journal is published 1 year 4 times (March, June, September and December)
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 30 Documents
 1   2   3 
Interpretable Feature Interaction Mining in High-Dimensional Clinical Data Using Hybrid Tree–Neural Models Widiastuti, Tiwuk; Richard , Berlien; Maryo Indra, Manjaruni
Global Science: Journal of Information Technology and Computer Science Vol. 2 No. 1 (2026): March: Global Science: Journal of Information Technology and Computer Science
Publisher : International Forum of Researchers and Lecturers

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70062/globalscience.v2i1.182

Abstract

High-dimensional clinical data exhibit complex and non-linear relationships among patient attributes, where outcomes are often influenced by feature interactions rather than isolated variables. However, many existing machine learning models prioritize predictive performance while providing limited interpretability and insufficient insight into interaction structures. This study aims to address this limitation by developing an interpretable and robust framework for feature interaction mining in clinical data. We propose a hybrid tree–neural modeling framework that explicitly captures and ranks feature interactions while maintaining stable predictive performance. Tree-based ensemble models are employed to identify non-linear interaction patterns, while neural representations enhance learning flexibility and generalization. The framework integrates interaction importance analysis, cross-validation–based stability assessment, and evaluation across multiple data splits to ensure robustness and interpretability. Experiments conducted on a real-world high-dimensional clinical dataset demonstrate that the proposed approach achieves consistent predictive performance, with AUC values ranging from 0.628 to 0.641 across five cross-validation folds (mean AUC ≈ 0.633). Performance remains stable under varying train–test splits, indicating strong generalizability. Interaction analysis reveals that a small number of dominant feature interactions—such as age combined with length of hospital stay and medication count combined with diagnostic information—consistently contribute to model predictions, appearing in over 80% of validation folds. Ablation studies further confirm that removing interaction-aware components leads to noticeable performance degradation, highlighting their importance. In conclusion, this study demonstrates that explicit feature interaction modeling enhances interpretability, stability, and generalization in clinical prediction tasks. The proposed hybrid framework provides a reliable foundation for developing trustworthy and transparent clinical decision-support systems
Transparent AI for Welfare Programs: Explainable Fraud Detection Using Publicly Available Administrative Data Sutrisno, Sutrisno; Winny, Purbaratri
Global Science: Journal of Information Technology and Computer Science Vol. 2 No. 1 (2026): March: Global Science: Journal of Information Technology and Computer Science
Publisher : International Forum of Researchers and Lecturers

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70062/globalscience.v2i1.184

Abstract

This study examines the application of Transparent Artificial Intelligence (AI) for fraud detection in public welfare programs using publicly available administrative data. Persistent challenges in welfare governance such as misallocation, fraud, and data inaccuracy necessitate analytical frameworks that are both effective and explainable. The research aims to design and evaluate an interpretable anomaly detection system capable of identifying irregularities in welfare distribution while maintaining transparency and accountability. Methodologically, the study employs two unsupervised models Isolation Forest and Local Outlier Factor (LOF) to detect anomalies in sub-district-level welfare data, incorporating features such as population size, number of beneficiaries, and coverage ratio. An Explainable AI (XAI) framework integrating surrogate Random Forests, Permutation Feature Importance (PFI), and local linear surrogates (LIME-like) is applied to ensure interpretability of both global and local model behaviors. Findings reveal that receivers per 1000 population and percentage coverage are dominant determinants of anomaly scores. Fifteen administrative units were flagged for potential inconsistencies suggesting over- or under-reporting of beneficiaries. Cross-validation between IF and LOF models confirmed consistency in identifying anomalous regions. The integrated XAI explanations enhance transparency, enabling policymakers and auditors to trace the rationale behind detected anomalies. In conclusion, the proposed Transparent AI framework demonstrates that combining anomaly detection with interpretability tools can strengthen accountability and fairness in welfare administration. It offers a reproducible, ethical, and data-driven approach to social program monitoring, reinforcing public trust and supporting responsible AI governance.
Toward Explainable AI for Cybersecurity: A NIST-Based Knowledge Graph for Transparent Semantic Reasoning Pratama, Firman; Dahil, Irlon; Dien, Marion Erwin; Lase, Dewantoro
Global Science: Journal of Information Technology and Computer Science Vol. 2 No. 1 (2026): March: Global Science: Journal of Information Technology and Computer Science
Publisher : International Forum of Researchers and Lecturers

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70062/globalscience.v2i1.186

Abstract

Explainable artificial intelligence (XAI) has become a critical requirement in cybersecurity due to the high-stakes nature of security decision-making and the limitations of black-box learning models. This study investigates the construction of an explainable cybersecurity knowledge representation by leveraging standardized terminology from the NIST cybersecurity glossary. The primary problem addressed is the lack of transparent and semantically grounded reasoning mechanisms in existing AI-driven cybersecurity systems, which limits trust, accountability, and analyst adoption. To address this challenge, we propose a NIST-based semantic knowledge graph that embeds explainability directly into its ontology structure and reasoning process. The proposed framework systematically extracts definitional entities and relations from NIST glossary entries to construct a domain ontology and a multi-relational knowledge graph. A rule-based semantic relation extraction method is employed to ensure faithful, interpretable, and reproducible reasoning paths. The resulting knowledge graph contains over 3,000 cybersecurity concepts and approximately 27,000 semantic relations, covering hierarchical, associative, dependency, and mitigation semantics. Experimental evaluation demonstrates that the proposed approach achieves a high level of explainability, with 92.4% of reasoning outcomes being fully traceable and only 1.4% classified as non-traceable. Most explainable reasoning paths are limited to two or three hops, indicating an effective balance between inferential depth and human interpretability. Structural analysis further confirms the presence of meaningful hub concepts that support multi-hop semantic inference. These results confirm that ontology-driven, standard-based knowledge graphs provide a robust foundation for explainable cybersecurity intelligence. The study concludes that explainability-by-design, grounded in authoritative standards, offers a viable and trustworthy alternative to opaque AI models for cybersecurity applications.
From Cryptography To Risk: Network Topology Of Cybersecurity Knowledge Simarmata, Simon; Boru, Meiton
Global Science: Journal of Information Technology and Computer Science Vol. 2 No. 1 (2026): March: Global Science: Journal of Information Technology and Computer Science
Publisher : International Forum of Researchers and Lecturers

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70062/globalscience.v2i1.189

Abstract

Inconsistent terminology across cybersecurity frameworks undermines global governance and interoperability. The National Institute of Standards and Technology Cybersecurity Framework (NIST CSF 2.0) and ISO/IEC 27001:2022 share similar objectives but diverge semantically in defining risk, control, and resilience. This semantic gap causes difficulties in compliance mapping and automated policy translation. Research Objectives: This study aims to analyze the semantic similarity and divergence between NIST and ISO/IEC 27000 terminologies, identify conceptual structures influencing interoperability, and propose an AI-assisted foundation for harmonizing cybersecurity language globally. Methodology: A mixed-method semantic comparative design integrates Natural Language Processing (NLP) and ontology mapping. Using the nist_glossary.csv dataset and ISO vocabularies, terms were normalized and analyzed via cosine similarity using sentence-transformer embeddings. Ontological alignment was visualized through the Semantic Threat Graph (STG) and validated by certified experts using Cohen’s Kappa reliability tests. Results: From 672 term pairs, results show 40.9% high semantic equivalence, 38.8% partial overlap, and 20.3% semantic divergence. Strongest alignment appears in “Protect” and “Identify” domains, while divergences occur in governance and recovery-related terms. Ontology mapping revealed three conceptual clusters—Risk Governance, Technical Safeguards, and Organizational Readiness. Conclusions: Findings confirm a 79.7% total semantic alignment, indicating strong potential for harmonizing global cybersecurity standards. The study contributes an empirical model combining computational linguistics and AI-based ontology mapping to establish semantic interoperability, enabling unified cybersecurity governance and AI-driven compliance automation. Keywords: Semantic Interoperability; Ontology Mapping; Cybersecurity Frameworks; Terminology Alignment; AI Harmonization
Implementation of Zero Trust Architecture for Securing Enterprise Networks
Global Science: Journal of Information Technology and Computer Science Vol. 1 No. 1 (2025): March : Global Science: Journal of Information Technology and Computer Science
Publisher : International Forum of Researchers and Lecturers

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70062/globalscience.v1i1.162

Abstract

As cyber threats grow more complex, traditional perimeter-based security models are no longer sufficient to protect enterprise networks. This study explores the implementation of Zero Trust Architecture (ZTA) in a mid-sized enterprise network. ZTA emphasizes continuous authentication, least-privilege access, and strict identity verification across all layers of the system. The study used a combination of identity management systems, micro-segmentation, and endpoint verification tools such as Okta, Cisco Duo, and VMware NSX-T. Performance metrics included authentication latency, access control policy enforcement time, and threat detection accuracy. Results showed a 45% improvement in threat containment time and a 60% reduction in lateral movement within the network. The adoption of ZTA also improved compliance with ISO/IEC 27001 standards. This research supports the growing relevance of ZTA in modern IT infrastructures and offers a practical deployment roadmap for organizations seeking to transition from legacy systems to a more resilient cybersecurity posture.
Adaptive Graph Based Intelligence Models for Cross Domain Knowledge Discovery in Large Scale Heterogeneous Information Systems Winny Purbaratri; Krisna Widi Nugraha; Rian Ardianto; Rosyid Ridlo Al-Hakim; Yogiek Indra Kurniawan; Ribut Julianto
Global Science: Journal of Information Technology and Computer Science Vol. 1 No. 4 (2025): December: Global Science: Journal of Information Technology and Computer Scienc
Publisher : International Forum of Researchers and Lecturers

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70062/globalscience.v1i4.193

Abstract

The rapid growth of heterogeneous information systems across multiple domains has introduced complex challenges in data analysis, particularly when dealing with diverse data types such as text, images, and sensor data. Traditional machine learning (ML) methods often struggle to capture the intricate relationships inherent in these large scale datasets, as they typically rely on linear models and feature vectors that fail to represent the full complexity of the data. This study aims to develop an adaptive graph based intelligence model that addresses these challenges by leveraging the power of graph structures to represent heterogeneous data and capture both structural dependencies and semantic connections. The proposed model integrates Graph Neural Networks (GNNs) with adaptive learning mechanisms, allowing for continuous knowledge extraction, pattern discovery, and cross domain inference. By representing diverse data sources as interconnected graphs, the model enables the transfer of knowledge across different domains, improving its ability to make accurate predictions and generate insights in dynamic environments. The results demonstrate that the graph based model outperforms traditional machine learning techniques in terms of accuracy, efficiency, and scalability, especially when applied to real world applications involving large and complex datasets. This paper also discusses the advantages of the adaptive learning mechanisms, which personalize the model’s training process and improve its robustness over time. Furthermore, the findings highlight the model’s potential for cross domain knowledge discovery, with applications in fields such as healthcare, marketing, and industrial automation. Finally, the paper offers recommendations for future research, including refining adaptive learning mechanisms and exploring new graph based techniques to enhance the representational power of the model. The study contributes to the ongoing development of intelligent systems capable of handling heterogeneous data across multiple domains and offers a foundation for future advancements in cross domain knowledge discovery.
Context Sensitive Artificial Intelligence for Dynamic User Behavior Modeling in Next Generation Smart Information Platforms Rusmin Saragih; Enda Ribka Meganta P; Tiwuk Widiastuti; Ahmad Jurnaidi Wahidin; Erlita Sulistiati; Muhamad Furqon
Global Science: Journal of Information Technology and Computer Science Vol. 1 No. 4 (2025): December: Global Science: Journal of Information Technology and Computer Scienc
Publisher : International Forum of Researchers and Lecturers

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70062/globalscience.v1i4.194

Abstract

This study explores the development and implementation of a context sensitive artificial intelligence (AI) model designed to predict and personalize user behavior in smart information platforms. Traditional user behavior models often fail to adapt to dynamic and evolving user needs, especially in diverse environments where contextual factors such as time of day, location, and device type play a critical role in shaping user preferences. To address these limitations, the proposed context sensitive AI model integrates real time contextual data alongside traditional behavioral data, enabling it to make more accurate predictions and provide personalized, relevant content. The model utilizes advanced machine learning techniques, such as deep learning and reinforcement learning, to continuously update and refine user behavior models based on contextual shifts. Through the integration of contextual parameters, the model demonstrates improved prediction accuracy, system responsiveness, and overall user satisfaction compared to static, context agnostic models. Furthermore, the study discusses the key advantages of context aware AI, such as its ability to dynamically adjust to real time changes in user behavior, providing more adaptive, personalized services. Challenges encountered during the model's development, including issues related to data privacy, scalability, and the integration of multiple contextual data sources, are also addressed. The findings suggest that context sensitive AI can significantly enhance the effectiveness of smart platforms by improving user engagement and content relevance. Finally, the study provides recommendations for further research to explore deep learning methods for context detection and to improve the discoverability and integration of AI driven features in user interfaces.
Energy Aware Software Architecture Optimization Using Real Time Analytics and Self Adaptive Control in Intelligent Computing Systems Ardy Wicaksono; Mursalim Mursalim; Arif Tri Widiyatmoko; Deny Prasetyo; Ahmad Budi Trisnawan; Yanuar Wicaksono
Global Science: Journal of Information Technology and Computer Science Vol. 1 No. 4 (2025): December: Global Science: Journal of Information Technology and Computer Scienc
Publisher : International Forum of Researchers and Lecturers

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70062/globalscience.v1i4.195

Abstract

The increasing demand for intelligent computing systems, including cloud computing, artificial intelligence (AI), and the Internet of Things (IoT), has resulted in a significant rise in energy consumption, which poses both environmental and economic challenges. The high computational power required by these systems, coupled with the continuous operation of data centers and connected devices, has led to inefficiencies in energy usage. This paper explores the integration of real time analytics and self adaptive control mechanisms to optimize energy consumption in intelligent systems. By employing advanced software tools for real time monitoring, dynamic adjustments based on workload conditions, and adaptive algorithms for energy optimization, significant reductions in power usage were achieved without compromising system performance. The optimized architecture dynamically adjusts system parameters such as processor frequency, task scheduling, and voltage to ensure efficient energy consumption during varying operational demands. The results show a 24% reduction in energy usage during low demand periods, demonstrating the potential of real time energy management strategies. The study also compares the optimized architecture with conventional static systems, highlighting the benefits of dynamic energy management, including improved performance balance, reduced environmental impact, and lower operational costs. These findings suggest that the integration of energy efficient practices in software design, particularly through real time analytics and self adaptive mechanisms, offers a sustainable solution for modern computing systems. Future research could focus on improving self adaptive systems, incorporating renewable energy sources, and expanding the approach to other intelligent systems, such as autonomous vehicles or large scale smart grids. The practical applications of this research are vast, particularly in large scale applications such as data centers and cloud computing, where energy efficiency is critical for sustainability.
Integrating Semantic Computing and Predictive Analytics to Enhance Reliability and Scalability of Global Information Systems
Global Science: Journal of Information Technology and Computer Science Vol. 1 No. 4 (2025): December: Global Science: Journal of Information Technology and Computer Scienc
Publisher : International Forum of Researchers and Lecturers

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70062/globalscience.v1i4.196

Abstract

Global information systems (GIS) are essential for managing large scale data across industries such as healthcare, finance, and urban planning. As the volume and complexity of data continue to grow, there is an increasing need for systems that can handle these demands while maintaining reliability and scalability. This research explores the integration of semantic computing and predictive analytics as a solution to improve the performance of GIS. Semantic computing, through the use of ontologies and standardized data models, enhances data interoperability, allowing systems to interpret and exchange data meaningfully across diverse platforms. On the other hand, predictive analytics uses statistical methods and machine learning models to forecast system behavior and optimize resource allocation, ensuring systems remain adaptive under varying loads. By integrating these two methodologies, this study demonstrates how they can address key challenges in global information systems, such as fault tolerance, system adaptability, and real time decision making. The results show significant improvements in system reliability and scalability, as well as better performance under high data volumes and diverse user interactions. The integrated approach was tested in several use cases, including urban planning, healthcare, and supply chain management, with results indicating that systems utilizing both semantic computing and predictive analytics are more resilient, accurate, and efficient. This paper discusses the practical implications of this integration for global scale applications and suggests future research directions, including the incorporation of emerging technologies like blockchain and artificial intelligence to further enhance the capabilities of GIS.
Trust Centric Machine Learning Framework for Secure Decision Making in Decentralized Digital Service Ecosystems Deny Prasetyo; Siska Narulita; Ahmad Jurnaidi Wahidin; Rosalina Yani Widiastuti; Suyahman Suyahman; Very Dwi Setiawan; Agus Wantoro
Global Science: Journal of Information Technology and Computer Science Vol. 1 No. 4 (2025): December: Global Science: Journal of Information Technology and Computer Scienc
Publisher : International Forum of Researchers and Lecturers

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70062/globalscience.v1i4.197

Abstract

This study introduces a trust centric machine learning framework designed to improve decision making reliability and security in decentralized digital service ecosystems. Traditional machine learning models often focus on accuracy and efficiency but fail to address the challenges of trust and security in decentralized environments. In contrast, the proposed framework integrates dynamic trust indicators and employs Federated Learning (FL) to ensure privacy while enhancing decision making performance. The framework also incorporates Zero Knowledge Proofp based Verifiable Machine Learning (ZKP-VML), which ensures transparency and security without compromising sensitive data. Through continuous real time trust assessments, the framework adapts to changing conditions, improving the accuracy and reliability of decisions in environments where participants may not fully trust each other. The application of this framework in autonomous vehicles and IoT networks demonstrated its ability to make robust, secure decisions, even in complex and uncertain scenarios. The framework’s ability to incorporate both trust and security into its decision making processes sets it apart from traditional models, which typically do not address the trustworthiness of data or participants. This research highlights the importance of integrating trust and security into machine learning models, particularly in decentralized systems, and offers a robust solution to trust management challenges. However, challenges such as scalability and computational efficiency remain, and future work should focus on enhancing these aspects, along with exploring the framework's applicability in other decentralized domains like finance or supply chain management. The integration of privacy preserving technologies and improvements in adversarial robustness are also potential areas for future research.

Page 3 of 3 | Total Record : 30

 1   2   3 

Filter by Year

2025 2026


Reset
Filter By Issues
All Issue Vol. 2 No. 1 (2026): March: Global Science: Journal of Information Technology and Computer Science Vol. 1 No. 4 (2025): December: Global Science: Journal of Information Technology and Computer Scienc Vol. 1 No. 3 (2025): September: Global Science: Journal of Information Technology and Computer Scien Vol. 1 No. 2 (2025): June: Global Science: Journal of Information Technology and Computer Science Vol. 1 No. 1 (2025): March : Global Science: Journal of Information Technology and Computer Science