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 4 Documents
 1 
Search results for , issue "Vol. 3 No. 6 (2025)" : 4 Documents clear
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.
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.

Page 1 of 1 | Total Record : 4

 1 

Filter by Year

2025 2025


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