cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Adam Mudinillah
Contact Email
adammudinillah@staialhikmahpariangan.ac.id
Phone
+6285379388533
Journal Mail Official
adammudinillah@staialhikmahpariangan.ac.id
Editorial Address
Jorong Kubang Kaciak Dusun Kubang Kaciak, Kelurahan Balai Tangah, Kecamatan Lintau Buo Utara, Kabupaten Tanah Datar, Provinsi Sumatera Barat, Kodepos 27293.
Location
Kab. tanah datar,
Sumatera barat
INDONESIA
Journal of Computer Science Advancements
Published by Yayasan Adra Karima Hubbi
ISSN : 30263379     EISSN : 3024899X     DOI : https://doi.org/10.70177/jsca
Core Subject : Science,
Computer Science & IT
Journal of Computer Science Advancements is an international peer-reviewed journal dedicated to interchange for the results of high quality research in all aspect of science, engineering and information technology. The journal publishes state-of-art papers in fundamental theory, experiments and simulation, as well as applications, with a systematic proposed method, sufficient review on previous works, expanded discussion and concise conclusion. As our commitment to the advancement of science and technology, the Journal of Computer Science Advancements follows the open access policy that allows the published articles freely available online without any subscription.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 106 Documents
 7   8   9   10   11 
DEVELOPMENT OF A WEB-BASED PURCHASE ORDER SYSTEM IN THE PURCHASING DIVISION USING THE AGILE MODEL (CASE STUDY: CV KLAMBY) Mawarni, Fauziah Ika; Razi, Fahrul
Journal of Computer Science Advancements Vol. 3 No. 4 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v3i4.2412

Abstract

This study aims to design and develop a web-based purchase order (PO) system equipped with an integrated approval feature by implementing the Agile development methodology. Agile is chosen for its iterative, flexible, and user-oriented development approach. The research follows several stages, including planning, requirements analysis, system design, development, testing, implementation, and evaluation. The system was developed using JavaScript (Node.js) and MySQL, and tested through blackbox testing. The results show that the system effectively facilitates PO creation, vendor and product data management, and supports secure, automated multi-level approval. The implementation of this system has been proven to enhance the efficiency and accuracy of procurement processes, reduce human error, and provide better-organized documentation. This system is expected to serve as a digital solution that can be adopted by other companies and strengthen the application of Agile methodology in information system development projects.
DESIGN OF A WEB-BASED GOODS DELIVERY INFORMATION SYSTEM WITH API SERVICES AND IOT INTEGRATION AT PT. ESA MANDIRI RUBBER Putri, Nadia Natasya; Terisia, Vany; Syamsu, Muhajir
Journal of Computer Science Advancements Vol. 3 No. 3 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v3i3.2415

Abstract

The advancement of information technology has driven various industrial sectors, including manufacturing, to transform toward more efficient and responsive distribution systems. PT. Esa Mandiri Rubber, a rubber manufacturing company, still relies on manual processes in managing goods delivery, resulting in various issues such as delays, distribution errors, and a lack of transparency in tracking. This study aims to design a web-based goods delivery information system integrated with Internet of Things (IoT) technology and API services. The system development method used is the Waterfall method, which consists of five stages: requirement analysis, system design, implementation, testing, and maintenance. The developed system includes delivery recording, real-time tracking, IoT device data integration, and access to information through a web interface. The results of the study show that the designed system successfully replaces the previously used manual processes, enhances distribution effectiveness, and facilitates easier monitoring and reporting. Thus, this system is capable of improving operational efficiency and the quality of logistics services at PT. Esa Mandiri Rubber.
WEB-BASED FINANCIAL MANAGEMENT INFORMATION SYSTEM FOR MSMES USING RAD METHOD Rizky, Haikal; Terisia, Vany; Syamsu, Muhajir
Journal of Computer Science Advancements Vol. 3 No. 6 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v3i6.2416

Abstract

Micro, Small, and Medium Enterprises (MSMEs), such as the Sukamurni Cracker Factory, often rely on manual financial recording, a practice prone to human error, data loss, and significant inefficiencies in generating financial reports. This research addresses these challenges by developing a web-based financial management information system tailored to the operational needs of MSMEs. The primary objective was to design and implement a system that improves the effectiveness, efficiency, and accuracy of financial record-keeping. The study employed the Rapid Application Development (RAD) methodology, encompassing requirements planning, user design, rapid construction, and system validation. The resulting system was built using the Laravel framework, PHP programming language, and a MySQL database. Functional validation was conducted through Black Box testing, which confirmed that all system modules—including income and expense tracking, automated report generation, and role-based access control for Admins and Staff—operate as specified. The novelty of this work lies in its practical application of the RAD model to create a user-centric and rapidly deployable solution for a resource-constrained MSME environment. This research provides a functional model for digital transformation in small-scale businesses, demonstrating that a well-designed system can significantly enhance operational efficiency and support strategic decision-making.
STUDENT GRADUATION PREDICTION USING DECISION TREE ALGORITHM WITH CRISP-DM METHOD (CASE STUDY: ITB AHMAD DAHLAN) Husni, Kholilah; Sestri, Elliya; Terisia, Vany
Journal of Computer Science Advancements Vol. 3 No. 5 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v3i5.2429

Abstract

On-time graduation is an important indicator of higher education effectiveness; however, delays in student graduation are still observed at ITB Ahmad Dahlan Jakarta. This study develops a student graduation prediction system using the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology and the Decision Tree algorithm based on historical academic data. The model was built through six CRISP-DM stages, including problem understanding, data preparation, modeling, and evaluation. Testing results indicate high performance with an Accuracy of 97.44%, Precision of 97.14%, Recall of 100%, and F1-Score of 98.55%. This system has the potential to support strategic decision-making to enhance academic quality through data-driven approaches.
INTEGRATING COMPUTER VISION AND MECHATRONICS FOR AUTOMATED QUALITY CONTROL IN SMART PRODUCT MANUFACTURING Faizin, Kholis Nur; Al-Fahim, Ahmed; Lahti, Maria
Journal of Computer Science Advancements Vol. 3 No. 3 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v3i3.2638

Abstract

Smart manufacturing’s (Industry 4.0) complexity demands automated quality control (AQC), as manual inspection is a major bottleneck. A critical gap exists in integrating “passive” Computer Vision (CV) detection with “active” mechatronic intervention, creating a “siloed” research problem. This research aims to design, develop, and validate a closed-loop AQC framework, integrating deep learning CV and mechatronics to autonomously perform the full QC cycle from detection to real-time physical intervention. An experimental systems integration design was employed. A Convolutional Neural Network (CNN) was trained on a 17,000-image dataset. A Robotic Operating System (ROS) framework was utilized as the integration layer for “hand-eye” calibration, synchronizing the CV node with a 6-axis robotic arm on a test rig. The CV model achieved 99.7% mAP (42ms latency) and calibration yielded ±0.35mm precision. The fully integrated system validation achieved a 99.15% Defect Detection Rate (DDR), a 0.11% False Positive Rate (FPR), and a 97.4% Successful Rejection Rate (SRR). The research empirically validates a holistic, closed-loop AQC framework, successfully solving the “siloed” gap. The system provides a proven, scalable blueprint for moving beyond passive detection to fully autonomous quality control in smart manufacturing.
NATURAL LANGUAGE PROCESSING FOR AUTOMATED REQUIREMENT ENGINEERING IN AGILE SOFTWARE DEVELOPMENT Sungkar, Muchamad Sobri; Baibek, Serikbek; Hamdan, Salma
Journal of Computer Science Advancements Vol. 3 No. 3 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v3i3.2646

Abstract

Manual Requirement Engineering (RE) in Agile software development creates a significant bottleneck. The reliance on natural language user stories at scale results in high-volume backlogs prone to ambiguity, duplication, and incompleteness, leading to costly, downstream development defects. This research aims to design, develop, and empirically validate a novel, hybrid Natural Language Processing (NLP) framework, termed the Agile Requirement Quality (ARQ) framework, to automate the detection of these common requirement defects. The goal is to reduce cognitive load and improve defect detection velocity during backlog refinement. A mixed-methods Design Science Research (DSR) methodology was employed. We developed the ARQ artifact (a hybrid BERT and heuristic model) and validated it both in-vitro against a 5,000-story “gold standard” annotated corpus (Fleiss’ Kappa 0.86) and in-situ through a quasi-experiment with professional Agile teams. The findings demonstrate high efficacy. In-vitro validation achieved high accuracy (overall 95.2%, with F1-scores of 0.87 for ambiguity and 0.94 for duplication). The in-situ experiment was conclusive: the ARQ-assisted team achieved a 73% increase in defect detection and an 87.5% reduction in “defect leakage” compared to the control team, registering high usability (88.5 SUS). This study provides robust empirical evidence that NLP-driven automation is a viable, high-impact strategy for mitigating risk in Agile RE. The framework functions as a practical “augmented intelligence” tool, significantly reducing defect leakage and improving quality assurance velocity.
NOT JUST A CHATBOT: THE RISE OF AGENTIC AI THAT CAN WORK AUTONOMOUSLY Demir, Ahmet; Akbulut, Baran; Kaya, Cemil
Journal of Computer Science Advancements Vol. 3 No. 6 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v3i6.3321

Abstract

Artificial intelligence research has long framed conversational systems as reactive tools responding to human prompts, a view increasingly insufficient to explain recent developments in autonomous AI. The emergence of Agentic AI signals a shift toward systems capable of planning, acting, and evaluating outcomes independently within complex digital environments. This study aims to conceptualize Agentic AI as a distinct paradigm beyond chatbot-based architectures and to examine its implications for human–AI interaction and governance. The research employs a qualitative conceptual design based on systematic analysis of secondary literature, comparative frameworks, and documented case studies of autonomous AI agents. Analytical synthesis is used to examine autonomy, system architecture, and modes of control across implementations. The results demonstrate that Agentic AI exhibits measurable autonomy through goal persistence, multi-step planning, and self-directed execution, enabling performance advantages in complex tasks while introducing new risks of misalignment and responsibility diffusion. Comparative analysis confirms that autonomy emerges from system-level integration rather than model scale alone. The study concludes that Agentic AI represents a substantive transformation in artificial intelligence practice, requiring revised evaluation metrics, governance structures, and theoretical frameworks. Recognizing Agentic AI as an operational actor rather than a conversational interface is essential for design, deployment, and future research.
CODING REVOLUTION: HOW AI AGENTS ARE TAKING OVER SOFTWARE REPOSITORY MAINTENANCE Teo, Ryan; Lee, Ava; Lim , Sofia
Journal of Computer Science Advancements Vol. 3 No. 6 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v3i6.3322

Abstract

The rapid expansion of global software infrastructure has created a critical bottleneck, as human developers struggle to manage escalating technical debt and complex repository maintenance. This research explores the transformative shift toward “Autonomous Repository Management” (ARM), where AI agents transition from passive assistants to independent maintainers. The primary objective is to evaluate the efficacy of agentic architectures in performing end-to-end maintenance tasks across diverse software ecosystems. Employing a longitudinal experimental design, this study utilized a purposive sample of 50 open-source repositories, applying a custom “RepoHealth-Bench” framework to measure performance. Findings indicate that AI agents reduced technical debt by 31.5% in legacy systems and achieved a 96.5% patch success rate in standardized libraries, significantly outperforming human-centric benchmarks in speed and security remediation. Inferential analysis reveals a strong correlation between repository documentation quality and agent reliability, suggesting a “compounding health” effect through iterative machine-led refactoring. The study concludes that the “Coding Revolution” effectively reverses software entropy, shifting the developer's role from manual execution to high-level orchestration. These results provide a foundational blueprint for integrating autonomous digital workforces into the modern software development lifecycle, marking the end of the manual maintenance era.
IMAGE PROCESSING AND COMPUTER VISION TECHNIQUES FOR AUTOMATED SMART SURVEILLANCE SYSTEMS Syahlan, Zainal; Lim, Sofia; Wong, Lucas
Journal of Computer Science Advancements Vol. 3 No. 6 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v3i6.3323

Abstract

The rapid development of urbanization and security concerns has prompted the integration of automated smart surveillance systems to enhance public safety and operational efficiency. Traditional surveillance methods often rely on human monitoring, which is prone to errors and inefficiencies. Image processing and computer vision techniques provide a solution by automating object detection, tracking, and anomaly recognition. This study aims to investigate advanced image processing and computer vision techniques for improving the performance of automated smart surveillance systems. A hybrid approach combining convolutional neural networks (CNNs), attention mechanisms, and edge computing is proposed to enhance both detection accuracy and real-time processing speed. The research employed experimental design, utilizing a dataset of 12,000 annotated image frames and 85 hours of video footage from diverse environmental conditions. Performance metrics such as precision, recall, mean average precision (mAP), and processing speed were measured. Results demonstrate that the proposed model outperforms traditional CNN models, achieving higher detection accuracy and faster processing speed. The study concludes that integrating edge computing with adaptive image processing and attention-based neural networks significantly improves automated surveillance system performance in real-world settings. These findings offer valuable insights for the development of scalable and efficient smart surveillance technologies.
PEELING THE WILLOW CHIP GOOGLE’S BREAKTHROUGH IN TAMING QUANTUM ERROR Dara, Ravi; Dara, Chenda; Sothy, Chak
Journal of Computer Science Advancements Vol. 3 No. 5 (2025)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/jsca.v3i5.3324

Abstract

The realization of fault-tolerant quantum computing is currently impeded by the stochastic nature of qubit decoherence and the inherent complexity of scaling control systems. This study rigorously evaluates the architectural innovations of Google’s Willow processor, specifically investigating its efficacy in mitigating noise through surface code error correction. The primary objective is to verify the hypothesis of exponential error suppression within a superconducting transmon array, determining if the system can surpass the critical “break-even” point. Methodologically, the research employs a quantitative performance analysis, configuring physical qubits into logical units of varying code distances (d=3 to d=7) and subjecting them to sustained syndrome extraction cycles under millikelvin cryogenic conditions. Results indicate a fundamental departure from previous scaling paradoxes; logical error rates were observed to halve with every increment in code distance, definitively crossing the algorithmic break-even threshold. The data confirms that real-time decoding and optimized tunable coupler designs effectively isolate errors, preventing topological lattice corruption. In conclusion, the Willow chip provides empirical validation that increasing system size now yields higher fidelity, establishing a critical engineering baseline for the development of large-scale, utility-grade quantum computers.

Page 9 of 11 | Total Record : 106

 7   8   9   10   11 

Filter by Year

2023 2026


Reset
Filter By Issues
All Issue Vol. 4 No. 1 (2026) Vol. 3 No. 6 (2025) Vol. 3 No. 5 (2025) Vol. 3 No. 4 (2025) Vol. 3 No. 3 (2025) Vol. 3 No. 2 (2025) Vol. 3 No. 1 (2025) Vol. 2 No. 6 (2024) Vol. 2 No. 5 (2024) Vol. 2 No. 4 (2024) Vol. 2 No. 3 (2024) Vol. 2 No. 2 (2024) Vol. 2 No. 1 (2024) Vol. 1 No. 6 (2023) Vol. 1 No. 5 (2023) Vol. 1 No. 4 (2023) Vol. 1 No. 3 (2023) Vol. 1 No. 2 (2023) Vol. 1 No. 1 (2023) More Issue