cover
Contact Name
Abdul Aziz
Contact Email
abdulazizbinceceng@gmail.com
Phone
+6282180992100
Journal Mail Official
journaleastasouth@gmail.com
Editorial Address
Grand Slipi Tower, level 42 Unit G-H Jl. S Parman Kav 22-24, RT. 01 RW. 04 Kel. Palmerah Kec. Palmerah Jakarta Barat 11480
Location
Kota adm. jakarta barat,
Dki jakarta
INDONESIA
The Eastasouth Journal of Information System and Computer Science
Published by Eastasouth Institute
ISSN : 30266041     EISSN : 3025566X     DOI : https://doi.org/10.58812/esiscs
Core Subject : Science,
ESISCS - The Eastasouth Journal of Information System and Computer Science is a peer-reviewed journal and open access three times a year (April, August, December) published by Eastasouth Institute. ESISCS aims to publish articles in the field of Enterprise systems and applications, Database management systems, Decision support systems, Knowledge management systems, E-commerce and e-business systems, Business intelligence and analytics, Information system security and privacy, Human-computer interaction, Algorithms and data structures, Artificial intelligence and machine learning, Computer vision and image processing, Computer networks and communications, Distributed and parallel computing, Software engineering and development, Information retrieval and web mining, Cloud computing and big data. ESISCS accepts manuscripts of both quantitative and qualitative research. ESISCS publishes papers: 1) review papers, 2) basic research papers, and 3) case study papers. ESISCS has been indexed in, Crossref, and others indexing. All submissions should be formatted in accordance with ESISCS template and through Open Journal System (OJS) only.
Articles 198 Documents
A Machine Learning-Based Intrusion Detection Framework for Enhanced Network Security Ranobir Hasan; Hira Jamal; Kamal Kamal; Khan Khan; Amit Kumar; Antu Roy
The Eastasouth Journal of Information System and Computer Science Vol. 4 No. 01 (2026): The Eastasouth Journal of Information System and Computer Science (ESISCS)
Publisher : Eastasouth Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/esiscs.v4i01.1168

Abstract

The rapid expansion of interconnected networks, cloud computing, Internet of Things (IoT) devices, and digital communication technologies has significantly increased the complexity of modern cyber threats, making traditional network security mechanisms increasingly inadequate. Intrusion Detection Systems (IDS) are essential components of cybersecurity infrastructures, designed to monitor network activities and identify malicious behavior before it compromises system integrity. However, conventional signature-based and rule-based IDS are primarily effective against previously known attack patterns and often fail to detect zero-day attacks, advanced persistent threats (APTs), and other evolving cyber threats. To address these limitations, machine learning (ML) has emerged as a transformative technology that enables adaptive, intelligent, and data-driven intrusion detection by learning complex patterns from network traffic and system behavior. This review presents a comprehensive analysis of machine learning-based intrusion detection systems, covering a wide range of techniques including supervised learning, unsupervised learning, ensemble learning, and deep learning models. The paper examines widely used benchmark datasets, feature selection and feature engineering methods, data preprocessing techniques, and commonly adopted performance evaluation metrics for assessing intrusion detection effectiveness. It also reviews various IDS deployment architectures, including centralized, distributed, edge-based, cloud-enabled, and hybrid frameworks, highlighting their strengths and limitations in different networking environments. To provide a clear understanding of intelligent intrusion detection mechanisms, the review introduces two conceptual frameworks: a machine learning-based intrusion detection pipeline that illustrates the end-to-end process from data acquisition to threat classification, and a layered network security architecture demonstrating the integration of ML techniques into modern cybersecurity infrastructures. Furthermore, the paper discusses critical challenges affecting the deployment of ML-based IDS, including data imbalance, scalability, computational complexity, model interpretability, adversarial machine learning attacks, privacy preservation, and real-time processing constraints.
Intent-Aware Enterprise Architecture Using Persistent AI Agents for Dynamic FinTech Service Composition Nithesh Gudipuri
The Eastasouth Journal of Information System and Computer Science Vol. 2 No. 01 (2024): The Eastasouth Journal of Information System and Computer Science (ESISCS)
Publisher : Eastasouth Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/esiscs.v2i01.1170

Abstract

As financial technology (FinTech) ecosystems grow increasingly complex, the rigidity of traditional service-focused enterprise architectures (EA) becomes a problem in the face of changing customer intent, diverse data sources and shifting regulatory requirements. This paper gathers insights from twenty-one peer-reviewed publications over the last 14 years (2009 to 2022) and suggests an intent-aware enterprise architecture in which the persistent artificial intelligence (AI) agents continuously interpret the organizational and customer intent to orchestrate dynamic FinTech service composition. From the reviewed literature, 52.4 percent covered the use of artificial intelligence and machine learning in financial services, 38.1 percent covered the coordination of multi-agent system (MAS), and 9.5 percent covered service-oriented enterprise architecture and integration with distributed ledger. The study builds on these three streams, with a five-layer architecture: intent interpretation, persistent agent orchestration, dynamic service composition, domain services, and governance. The synthesis suggests that the explanation of these agents, which are persistent, can be used to increase the flexibility and auditability in coordination compared to traditional service-oriented designs, but also imposes new governance and security requirements. The proposed framework provides the FinTech enterprises with structured guidance on delivering adaptive and intent-driven services and supplies a researchers' framework for empirical testing and validation of the proposed framework.
Intelligent Cybersecurity Frameworks for Data Protection in Cloud-Integrated Management Information Systems Kesavan Sundara Mudaliyar; S. Satish Kumar
The Eastasouth Journal of Information System and Computer Science Vol. 2 No. 02 (2024): The Eastasouth Journal of Information System and Computer Science (ESISCS)
Publisher : Eastasouth Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/esiscs.v2i02.1165

Abstract

Enterprise workloads keep moving to public, private, and hybrid cloud environments, and that shift is widening the attack surface available to would-be intruders just as organizations lean harder on Management Information Systems (MIS) to run day-to-day decisions. This paper works through fifteen recent studies sitting at the crossing point of artificial intelligence (AI), cybersecurity, cloud computing, and MIS governance, and tries to say something coherent about what they add up to. Rather than proposing and testing one new tool, the review pulls out the themes that keep resurfacing, AI and machine-learning-based threat detection, cyber threat intelligence, big-data analytics, data governance, federated and privacy-preserving learning, sustainable data-center design, and the human side of security that technical papers tend to skip and organizes them into a five-layer conceptual framework meant to help later empirical work. The review follows an explicit search, screening, and synthesis process, described in Section II; each proposed framework layer is traced back, in the discussion itself, to the specific literature that motivates it, and a thematic distribution chart shows how attention is split across sub-topics in the corpus. What comes out of this is that detection capability and MIS governance are comparatively well covered, while a handful of cross-cutting issues, explainability at the implementation level, how employees behave once AI is in the loop, energy-aware security operations, and the practical limits of federated learning, are thinner than their real-world importance would suggest. The paper closes by naming its own limitations and laying out where empirical work still needs to happen.
Hybrid Artificial Intelligence for Brain Tumor Classification Using MRI Images Kallol Chakraborty Shekhor; Sumayya Jahan; Md Sahid Hossain; Md Fakrul Alam; Abdur Rahim; Md Sazzad Hossain Shehan; Md Anwar Hossain; Md Abedur Rahman; Mohammed Adnan
The Eastasouth Journal of Information System and Computer Science Vol. 2 No. 02 (2024): The Eastasouth Journal of Information System and Computer Science (ESISCS)
Publisher : Eastasouth Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/esiscs.v2i02.1184

Abstract

Accurate classification of brain tumors from magnetic resonance images is essential for supporting clinical assessment, although variations in tumor morphology, anatomical location, image orientation, and visual similarity among diagnostic categories can limit the effectiveness of conventional deep learning models. This study proposes a hybrid learning framework that integrates local structural information, global contextual relationships, and frequency domain characteristics for four class brain tumor classification. The model combines an ImageNet pretrained ConvNeXt Tiny branch for local feature extraction, a Swin Transformer Tiny branch for hierarchical contextual representation, and a wavelet convolutional neural network branch based on two level Haar decomposition. The resulting branch features are aligned within a shared representation space and integrated through bidirectional cross attention and adaptive gated fusion before classification. A dataset containing 10,464 brain magnetic resonance images was evaluated at the individual image level, including 2,726 glioma, 2,737 meningioma, 2,300 no tumor, and 2,701 pituitary tumor images. The dataset was divided into 9,417 training images, 653 validation images, and 394 independent testing images. Brain contour cropping, contrast limited adaptive histogram equalization, normalization, and controlled augmentation were applied during preprocessing. On the independent test set, the proposed model correctly classified 389 of 394 images, achieving an accuracy of 98.73% with a 95% confidence interval from 97.06% to 99.46%. It further obtained a macro precision of 98.84%, macro recall of 98.82%, macro F1 score of 98.82%, macro specificity of 99.56%, Matthews correlation coefficient of 0.9830, and macro area under the receiver operating characteristic curve of 0.9995. The proposed framework outperformed the strongest individual backbone, Swin Transformer Tiny, which achieved 96.45% accuracy and a macro F1 score of 96.63%. These findings indicate that coordinated integration of spatial, contextual, and frequency information can improve image level brain tumor classification. However, the absence of patient identifiers and magnetic resonance sequence metadata limits patient level interpretation and sequence specific analysis.
Deep Learning for Accurate Classification of Seven Types of Skin Lesions from Dermoscopic Images Sumayya Jahan; Kallol Chakraborty Shekhor; Md Sahid Hossain; Md Fakrul Alam; Abdur Rahim; Md Sazzad Hossain Shehan; Md Anwar Hossain; Md Abedur Rahman; Mohammed Adnan
The Eastasouth Journal of Information System and Computer Science Vol. 1 No. 02 (2023): The Eastasouth Journal of Information System and Computer Science (ESISCS)
Publisher : Eastasouth Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/esiscs.v1i02.1185

Abstract

Accurate multiclass classification of dermatoscopic images remains challenging because skin lesions often exhibit substantial visual similarity, considerable variation in color and morphology, and severe class imbalance. This study presents a hybrid deep learning framework that integrates ConvNeXt Tiny, pyramid pooling context modeling, and a hierarchical Swin Transformer for seven class skin lesion classification. The ConvNeXt branch extracts progressive local texture, color, and morphological representations, while the pyramid pooling module aggregates lesion context at spatial scales defined by pooling bins of 1, 2, 3, and 6. In parallel, the Swin Transformer branch models hierarchical spatial relationships and long range dependencies through shifted window attention. The three branch representations are globally pooled, projected into a shared 512 dimensional latent space, and combined using a learned gated attention mechanism that adaptively controls their contributions to the final prediction. The framework was evaluated on the HAM10000 dataset containing 10,015 dermatoscopic images from seven diagnostic categories. Images were partitioned at the lesion level into 7,010 training, 1,502 validation, and 1,503 testing samples to prevent information leakage between images of the same lesion. Class balanced focal loss, AdamW optimization, ImageNet normalization, and controlled image augmentation were used during training. The proposed model achieved an accuracy of 95.81%, balanced accuracy of 92.51%, macro precision of 92.64%, macro recall of 92.51%, macro F1 score of 92.58%, and macro area under the receiver operating characteristic curve of 99.01%. Ablation analysis showed progressive improvements after introducing pyramid pooling, Swin features, channel attention, and gated fusion, with a macro F1 increase of 3.21 percentage points over the ConvNeXt Tiny baseline. These findings indicate that complementary local, contextual, and global representations can improve image level skin lesion classification, particularly under substantial class imbalance.
Improving Sentiment Classification of Indonesia's School Zoning Admission Policy on Twitter Renaldiansyah Gumay; Wiranto Herry Utomo
The Eastasouth Journal of Information System and Computer Science Vol. 4 No. 01 (2026): The Eastasouth Journal of Information System and Computer Science (ESISCS)
Publisher : Eastasouth Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/esiscs.v4i01.1162

Abstract

Since 2016, the Indonesian government has implemented a zoning-based policy for its online New Student Admission (Penerimaan Peserta Didik Baru, PPDB) system to ensure equitable access to quality education. Despite this intent, the policy has repeatedly drawn mixed public reactions, and in 2024 the debate intensified on social media, particularly on Twitter (X), which has become a primary channel for the public to express opinions on the policy. Understanding this sentiment at scale requires an approach that can cope with the unstructured, informal, and slang-heavy nature of Indonesian social media text. This study proposes a hybrid sentiment analysis approach that combines the InSet (Indonesia Sentiment) Lexicon with a Recurrent Neural Network (RNN) based on Long Short-Term Memory (LSTM) to classify public sentiment toward the 2024 PPDB zoning policy from 1,771 crawled tweets. Two scenarios were tested: Scenario 1 used an LSTM model trained on text alone, while Scenario 2 combined the LSTM with InSet Lexicon polarity scores as an auxiliary input. Scenario 1 achieved a training accuracy of 94.61% but only 66.18% on validation data, indicating overfitting, whereas Scenario 2 achieved a validation accuracy of 95%, with 92% precision, 96% recall, and a 93% F1-score. The results indicate that combining lexicon-based scoring with LSTM substantially improves classification accuracy and generalization on Indonesian-language, informal social media text, and that the overall public sentiment toward the 2024 zoning policy tended to be positive.
Big Data and Predictive Analytics for Cost, Quality, and Performance Optimization in Project Management Ruhul Amin Md Rashed; Tajul Islam Rafi; Ikbal Hossain
The Eastasouth Journal of Information System and Computer Science Vol. 4 No. 01 (2026): The Eastasouth Journal of Information System and Computer Science (ESISCS)
Publisher : Eastasouth Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/esiscs.v4i01.1194

Abstract

Most project managers already sense that their status reports arrive too late to matter. A budget line is flagged as over only after the money is spent; a defect surfaces only after the code has shipped. This paper looks at how big data and predictive analytics can close that gap, focusing on three things project teams care about most: cost, quality, and schedule performance. Rather than treating these as three separate problems with three separate toolkits, the paper argues they should be read together, since a decision that helps one almost always pushes on the other two. Drawing on recent work in artificial intelligence, digital twins, cloud-based management information systems, and agile practice, the paper builds an integrated framework that connects raw project data to a predictive analytics engine and, from there, to the everyday decisions stakeholders make. Companion data architecture shows, more concretely, how information travels from operational systems and sensors through cloud integration and machine-learning layers into a governance dashboard. Along the way, the paper discusses how predictive models catch cost overruns early, flag likely defects before they reach production, and support more realistic scheduling, while also being honest about what can go wrong: patchy data integration, added cybersecurity exposure, models nobody can quite explain, and teams that were never trained to trust the outputs. The overall claim is a modest one, in a sense: none of this works because of any single clever tool. It works when it works, because organizations pair the analytics with the infrastructure and the decision habits needed to act on it. The paper closes with suggestions for the empirical research still needed to test the framework across industries.
Data Privacy Concerns and User Trust in Indonesia’s Fintech Ecosystem Apriyanto Apriyanto; Adih Supriadi
The Eastasouth Journal of Information System and Computer Science Vol. 4 No. 01 (2026): The Eastasouth Journal of Information System and Computer Science (ESISCS)
Publisher : Eastasouth Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/esiscs.v4i01.1205

Abstract

The rapid expansion of the financial technology (fintech) ecosystem in Indonesia has transformed the delivery of financial services by improving accessibility, efficiency, and convenience. However, increasing reliance on digital financial platforms has also raised concerns regarding personal data protection, application usability, and user confidence. This study aims to examine the influence of data privacy issues and application usability on user trust within the Indonesian fintech ecosystem. A quantitative research approach was employed using survey data collected from 125 fintech users in Indonesia through a structured questionnaire measured with a five-point Likert scale. The collected data were analyzed using Statistical Package for the Social Sciences (SPSS) version 25, including validity testing, reliability testing, classical assumption testing, multiple linear regression analysis, t-test, F-test, and coefficient of determination analysis. The findings indicate that both data privacy issues and application usability have a positive and significant effect on user trust. The regression results demonstrate that application usability has a stronger influence on user trust compared with data privacy protection, indicating that user experience, ease of interaction, and system reliability are critical factors in building confidence toward fintech services. Furthermore, the model explains 58.7% of the variance in user trust, confirming that privacy management and usability are important determinants of fintech acceptance and continued usage. This study highlights the importance for fintech providers to integrate robust data protection mechanisms with user-centered application design to develop secure, reliable, and sustainable digital financial services in Indonesia.
Information Technology Governance Research in the Digital Era: A Scopus-Based Bibliometric Analysis Loso Judijanto; Hanifah Nurul Muthmainah; Joni Wilson Sitopu
The Eastasouth Journal of Information System and Computer Science Vol. 4 No. 01 (2026): The Eastasouth Journal of Information System and Computer Science (ESISCS)
Publisher : Eastasouth Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/esiscs.v4i01.1206

Abstract

This study aims to map and analyze the global research landscape of information technology (IT) governance in the digital era through a bibliometric approach. Data were retrieved from the Scopus database and analyzed using VOSviewer software to examine co-authorship patterns, institutional collaborations, country contributions, keyword co-occurrence structures, and citation impact. The co-authorship network reveals that this segment of the literature is dominated by a single, tightly interconnected research team rather than a broad community of independent contributors, while institutional collaboration remains sparse and is bridged only by a public-administration-affiliated unit connecting a geospatial land-governance research community with a cross-border, financial-technology-oriented data-governance community. At the country level, China, the United States, the United Kingdom, India, and Indonesia emerge as the principal hubs of international collaboration, supported by extensive participation from Europe, the Middle East, and Southeast Asia, indicating that IT governance research constitutes a genuinely global, multipolar undertaking. The keyword co-occurrence analysis shows that the field is organized around four interconnected clusters covering cybersecurity and blockchain-based governance, artificial intelligence and digital transformation, big data-driven decision-making, and e-government and ICT-based public governance, with digital governance and information management forming the field's conceptual core. The citation analysis further shows that the field's intellectual foundation is anchored in the digital-era governance model and its subsequent extension toward artificial intelligence, alongside diverse contributions from e-government adoption, geospatial data integration, and data-driven policymaking research. Taken together, these findings indicate that IT governance research has developed into a rapidly expanding, technology-driven field, with growing convergence toward artificial intelligence, cybersecurity, and data governance as its emerging frontiers.
The Intellectual Evolution of Digital Literacy Studies: A Bibliometric Analysis of Scopus Publications Loso Judijanto
The Eastasouth Journal of Information System and Computer Science Vol. 4 No. 01 (2026): The Eastasouth Journal of Information System and Computer Science (ESISCS)
Publisher : Eastasouth Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/esiscs.v4i01.1207

Abstract

This study aims to map and analyze the global research landscape of digital literacy through a bibliometric approach. Data were retrieved from the Scopus database and analyzed using VOSviewer software to examine co-authorship patterns, institutional collaborations, country contributions, keyword co-occurrence structures, and citation impact. The co-authorship analysis reveals that author-level collaboration in digital literacy research is not organized into a single integrated community but into four largely disconnected teams that are unified almost entirely through the boundary-spanning position of one prolific author, while institutional collaboration remains sparse and structured as a thin, crossing chain linking business and communication, management, and nursing faculties. At the country level, China and the United States function as dual central hubs, with Indonesia forming a substantial secondary hub that reflects the strong presence of Southeast Asian scholarship, alongside more selective participation from countries such as Canada, Australia, Spain, and the Russian Federation. As shown by the keyword co-occurrence analysis, the field is organized around four interconnected clusters covering the library- and bibliometric-oriented dimension of digital literacy, the artificial-intelligence-driven pedagogical dimension, the human-subject and disability-oriented dimension, and a smaller pandemic-related bridging dimension, with digital literacy, artificial intelligence, and human forming the dominant conceptual anchors. The overlay and density analyses further indicate a clear temporal shift from foundational information-literacy and human-subject themes toward generative-AI-oriented and bibliometric-mapping themes in more recent years. The citation analysis demonstrates that the field draws on cross-disciplinary foundational works spanning financial literacy, disability inclusion, multimodal literacy, and generative artificial intelligence. Taken together, these findings suggest that digital literacy research has developed into a globally distributed yet structurally fragmented field that is rapidly reorienting itself around the integration of artificial intelligence into literacy theory and practice.