cover
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
+6282370070808
Journal Mail Official
jurnal.bulletincsr@gmail.com
Editorial Address
Jalan sisingamangaraja No 338 Medan, Indonesia
Location
Kota medan,
Sumatera utara
INDONESIA
Bulletin of Computer Science Research
ISSN : -     EISSN : 27743659     DOI : -
Core Subject : Science,
Bulletin of Computer Science Research covers the whole spectrum of Computer Science, which includes, but is not limited to : • Artificial Immune Systems, Ant Colonies, and Swarm Intelligence • Bayesian Networks and Probabilistic Reasoning • Biologically Inspired Intelligence • Brain-Computer Interfacing • Business Intelligence • Chaos theory and intelligent control systems • Clustering and Data Analysis • Complex Systems and Applications • Computational Intelligence and Soft Computing • Distributed Intelligent Systems • Database Management and Information Retrieval • Evolutionary computation and DNA/cellular/molecular computing • Expert Systems • Fault detection, Fault analysis, and Diagnostics • Fusion of Neural Networks and Fuzzy Systems • Green and Renewable Energy Systems • Human Interface, Human-Computer Interaction, Human Information Processing • Hybrid and Distributed Algorithms • High-Performance Computing • Information storage, security, integrity, privacy, and trust • Image and Speech Signal Processing • Knowledge-Based Systems, Knowledge Networks • Knowledge discovery and ontology engineering • Machine Learning, Reinforcement Learning • Networked Control Systems • Neural Networks and Applications • Natural Language Processing • Optimization and Decision Making • Pattern Classification, Recognition, speech recognition, and synthesis • Robotic Intelligence • Rough sets and granular computing • Robustness Analysis • Self-Organizing Systems • Social Intelligence • Soft computing in P2P, Grid, Cloud and Internet Computing Technologies • Support Vector Machines • Ubiquitous, grid and high-performance computing • Virtual Reality in Engineering Applications • Web and mobile Intelligence, and Big Data • Cryptography • Model and Simulation • Image Processing
Articles 11 Documents
Search results for , issue "Vol. 5 No. 3 (2025): April 2025" : 11 Documents clear
Benchmarking Local Development Environments: Analyzing the Performance of XAMPP, MAMP, and Laragon Albert Yakobus Chandra; Putry Wahyu Setyaningsih
Bulletin of Computer Science Research Vol. 5 No. 3 (2025): April 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i3.493

Abstract

In the rapidly evolving landscape of web application development, the choice of a local development environment significantly influences both productivity and performance. This study aims to benchmark three widely utilized local server solutions—XAMPP, MAMP, and Laragon—through a rigorous performance analysis grounded in information technology principles. By examining critical performance metrics such as load times, resource utilization, scalability, and compatibility with various programming languages and frameworks, we provide a holistic view of each platform's capabilities.Utilizing empirical testing methodologies, including stress testing and response time measurements, this research evaluates the environments under varying workloads to simulate real-world application development scenarios. Additionally, we explore factors such as ease of installation, configuration flexibility, and community support, which are essential for developers in selecting an appropriate development environment. The findings reveal significant differences in performance and user experience among the three platforms, emphasizing the implications of server performance on developer efficiency, project timelines, and overall software quality. This study contributes to the body of knowledge in the information technology field by providing actionable insights for practitioners, educators, and researchers. Ultimately, it serves as a foundational resource for informed decision-making regarding local development environments in web application projects, fostering a deeper understanding of how these tools impact the software development lifecycle.
Pemanfaatan Algoritma K-Means Clustering Pada Sistem Rental Mobil Maesaroh, Sri Wulandari; Diansyah, T M; Liza, Risko; Lubis, Yessi Fitri Annisah
Bulletin of Computer Science Research Vol. 5 No. 3 (2025): April 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i3.494

Abstract

This research utilizes the K-Means clustering algorithm to analyze car rental data from PT. Station Armada Indonesia, aiming to simplify customer car selection and improve the company's market responsiveness. The study addresses the problem of customer confusion stemming from the wide variety of car types offered by the company. By employing K-Means clustering on August 2023 rental data, the research groups cars based on rental price and mileage. The dataset, initially encompassing four car categories (Minibus MVP, SUV, City Car, and Van/Bus), was further detailed to include individual car models. Three parameters—rental duration, rental price, and mileage—were used for clustering. The K-Means algorithm, chosen for its ease of implementation and speed, was applied iteratively using Euclidean distance to assign data points to the nearest centroid. The study initially defined two clusters. Manual calculations, detailed in the paper, demonstrate the clustering process. These manual results were then compared against results obtained using RapidMiner Studio version 10.1, showcasing the software's efficiency in handling the K-Means process. The RapidMiner output included Data, Statistics, and Annotations views, providing a comprehensive analysis of the clusters. The final clustering, achieved after three iterations, revealed two distinct clusters: one representing less popular car types (Cluster 0), and the other representing the most popular car types (Cluster 1). Cluster 0 contained six car types with average customer mileage ranging from 673 km to 2050 km, while Cluster 1 included 24 car types with average mileage between 270 km and 3388 km. The findings enable PT. Station Armada Indonesia to optimize fleet management and marketing strategies by focusing on the most in-demand car types. The study concludes that K-Means clustering, implemented via RapidMiner, offers a valuable tool for enhancing customer understanding of car selection and improving the company's overall efficiency.
Rancang Bangun Sistem Informasi Organisasi Berbasis Website Menerapkan Metode Waterfall Irmansyah Lubis, Ahmadi
Bulletin of Computer Science Research Vol. 5 No. 3 (2025): April 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i3.495

Abstract

The development of information technology has had a significant impact on the effectiveness and efficiency in organizational management, including within the Muhammadiyah Branch Executive (PCM) of Batam Kota District. However, in its operations, there are still obstacles in data management, information delivery, and reporting activities that are still carried out manually. Therefore, this research aims to develop a website-based organizational information system digitization application that can help in managing information and administration in a more structured and efficient manner. The system development method used is the Waterfall model approach which consists of several stages, namely needs analysis, design, implementation, testing, and maintenance. The analysis stage is carried out by collecting data through interviews and observations to understand the needs of the system. The designing stage involves the design of the system, database, and user interface. Implementation is carried out by building applications using the Laravel Framework which has an MVC (Model-View-Controller) architecture for more structured code management. Data storage is carried out using a MySQL database which allows for faster and organized information management. After that, the testing stage is applied to ensure that the system runs according to the specifications that have been determined. The results of the study show that the application developed can increase efficiency in the management of Batam City PCM administration such as recording member data, activity schedules, and automatic report making. Testing of the system using the Black Box Testing method shows that the application works well without any functional errors. With this application, it is hoped that PCM Batam Kota can be more optimal in managing the organization and conveying information to its members effectively.
Sistem Informasi Surat Keluar dan Surat Perintah Tugas Berbasis Web Menggunakan Metode Rapid Application Development Fadilah Maysarah Nasution; Arie Linarta; Masrizal
Bulletin of Computer Science Research Vol. 5 No. 3 (2025): April 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i3.498

Abstract

Information technology has been widely applied in various sectors, including in supporting government administration activities. One activity that is still carried out manually is the process of making outgoing letters and task orders. Problems that arise include the length of the letter-making process, errors in formatting, and dependence on certain staff in preparing letters. The research was conducted at the Dumai City Social and Community Empowerment Service, sepecially in the Social Rehabilition Division. This research aims to build a web-based information system that can automate the process of making outgoing letters and task orders, making it faster, more efficient, and minimal errors. Data collection techniques used in this research include observation, interviews, and dicumentation studies. System development is carried out using the Rapid Application Development (RAD) method, which focuses on rapid development by involving users. Testing of this system will be carried out using the black box testing method. The results showed that the information system built was able to produce outgoing letters and task orders automatically using templates that had been prepared. Users only need to fill in data through the available forms, so that the process of making letters becomes faster, more precise and easier to use. With this system, it s expected that the mail administration process in the Social Rehabilitation Division will be more efficient can be more effective and efficient, and reduce the potential for errors in letter creation.
Evaluasi Framework Pengembangan Web KinarBhusana: Studi Performance, SEO, dan Accessibility Menggunakan Laravel dan Bootstrap Muhammad Daffa Al-farel; Akhmad Rizal Dzikrillah
Bulletin of Computer Science Research Vol. 5 No. 3 (2025): April 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i3.499

Abstract

Web programming skills are essential in today’s digital world for anyone who wants to work in the information and communication technology field. In order to attract clients and advertise their goods and services, every business must have a strong web presence. Companies need to use technology well in order to quickly adapt to digital changes and generate new value. Web platforms must meet important requirements in this regard, including excellent performance, search engine optimization (SEO), accessibility, and effective resource management. Due to their ease of use and effectiveness in producing dynamic and responsive website, frameworks such as Laravel and Bootstrap have gained popularity in web development. Thus, the purpose of this study is to assess how well Laravel and Bootstrap perform when building the KinarBhusana online application, with an emphasis on accessibility, SEO, and performance. It is hoped that the findings of this study will offer comprehensive insights into how well the frameworks perform in achieving these goals. The performance of the websites was compared before and after the frameworks were implemented using quantitative techniques and comparative study designs. This study's testing used Google Lighthouse which revealed that the results of using Laravel and Bootstrap were better in terms of performance, SEO, and accessibility of the KinarBhusana website.
Pendekatan Hybrid K-Means SMOTE dan Logistic Regression Untuk Deteksi Dini Diabetes Mellitus Pada Imbalanced Data Salam, Abdus; Azhari, Lukman; Septarini, Ri Sabti; Heriyani, Nofitri
Bulletin of Computer Science Research Vol. 5 No. 3 (2025): April 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i3.502

Abstract

The increasing global prevalence of Diabetes Mellitus necessitates more accurate early detection efforts, particularly through machine learning-based approaches. However, one of the main challenges in medical classification lies in data imbalance, where the number of diabetic cases is significantly lower than that of non-diabetic ones. This study aims to develop a hybrid model by integrating Logistic Regression and K-Means SMOTE to enhance the sensitivity of early detection for Diabetes Mellitus, especially toward the minority class. Logistic Regression is chosen for its computational efficiency and interpretability, while K-Means SMOTE plays a role in balancing class distribution by generating synthetic samples in a structured manner based on clusters of minority class data. The dataset used consists of 2,000 records with 9 health-related features, obtained from the Kaggle platform. Evaluation results indicate that the model utilizing K-Means SMOTE achieves the best performance, with an accuracy of 82.00%, an F1-score of 72.73% for the Diabetes class, and the highest ROC-AUC score of 87.48%. Compared to models without oversampling and with standard SMOTE, this approach improves model generalization and sensitivity to positive cases. These findings have practical implications for the development of fairer and more effective machine learning-based early detection systems, particularly for implementation in healthcare facilities with limited resources.
An Entropy-Assisted COBRA Framework to Support Complex Bounded Rationality in Employee Recruitment Oprasto, Raditya Rimbawan; Wang, Junhai; Pasaribu, A Ferico Octaviansyah; Setiawansyah, Setiawansyah; Aryanti, Riska; Sumanto
Bulletin of Computer Science Research Vol. 5 No. 3 (2025): April 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i3.505

Abstract

In the employee recruitment process, decision-making often involves many criteria and relies on the subjective judgment of the decision-maker. The main problem lies in how to develop a decision support system that can overcome this complexity while maintaining rationality and objectivity. This study aims to apply a hybrid framework based on the entropy and COBRA methods to support objective decision-making in the employee recruitment process, and to overcome the limitations of subjectivity and bounded rationality in candidate selection with a structured data-driven approach. The entropy method is used to objectively determine the weight of criteria based on data variations, thereby helping to reduce subjectivity in decision-making and increase the rationality of COBRA analysis results. The results of the final calculation using the Entropy-COBRA method, were ranked nine candidates based on their final scores which reflected relative proximity to the ideal solution in the recruitment process. The candidate with the lowest score is considered to be the closest to the ideal solution and has the best overall performance. Raka employees ranked first with a final score of -0.0618, followed by Andra in second place with a score of -0.0597, and Fajar in third place with -0.0357. The results of the final score in the COBRA method with a lower score indicate that an alternative shows superior performance over the other. This framework makes a real contribution to data-driven decision-making for human resource management, particularly in the context of recruitment involving multiple criteria and alternatives.
Restorasi Penjadwalan Sumur Minyak Yang Mengalami Off-Time Menggunakan Algoritma Backtracking Dalam Upaya Optimasi Produksi Angel Caroline Billan; Tata Sutabri
Bulletin of Computer Science Research Vol. 5 No. 3 (2025): April 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i3.507

Abstract

Inefficient well restart scheduling is often caused by the limitations of conventional methods in handling operational and field complexity. This study proposes a solution in the form of implementing a backtracking algorithm in compiling an oil well restart schedule that is experiencing off-time. This algorithm is chosen because of its ability to systematically explore solutions through depth-first search and forward checking mechanisms to meet various operational constraints such as crew availability, geological conditions, and interconnectedness between wells. The purpose of this study is to develop a Constraint Satisfaction Problem (CSP)-based scheduling model that is able to minimize off-time and optimize resource utilization. The main contribution of this study is the integrative approach between the CSP model and the backtracking algorithm which has not been widely applied in the context of oil and gas operations. The interim results of simulations on historical data show that this method is able to reduce the average off-time by 25%, increase resource utilization efficiency by 28.6%, and accelerate the scheduling process by 66.7% compared to conventional methods. This approach shows significant potential in improving operational efficiency and supporting the digitalization of scheduling in the oil industry.
Deteksi dan Klasifikasi Kendaraan Berbasis Algoritma You Only Look Once (Yolov7) Rohiman, Yusuf Kautsar; Bulkis Kanata; L Ahmad S Irfan Akbar
Bulletin of Computer Science Research Vol. 5 No. 3 (2025): April 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i3.509

Abstract

The increasing traffic density in Indonesia highlights the need for an accurate vehicle detection system to support infrastructure planning. This study aims to implement the YOLOv7 algorithm for detecting and classifying various types of vehicles in traffic images. The method involves training the model using Google Colab on a Kaggle dataset consisting of 6,633 images, with a batch size of 1, 19 training epochs, and optimization using the Stochastic Gradient Descent (SGD) algorithm. The training results show that the model achieved a precision of 93.22%, recall of 90.64%, mAP@0.5 of 94.27%, and mAP@0.5:0.95 of 69.19%, with a total training time of 1 hours. In conclusion, the YOLOv7 algorithm is effective for vehicle detection and classification, although increasing the number of training epochs is recommended to further enhance model performance.
Qualitative Analysis of Shadow IT Practices in Higher Education to Identify IT Security Needs Ahmad Aunul Bari Hayiz; Arif Wibisono
Bulletin of Computer Science Research Vol. 5 No. 3 (2025): April 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i3.520

Abstract

The presence of Shadow IT in educational settings often stems from users' attempts to fulfill work needs that are not met by formal systems. These tools, typically accessed outside institutional infrastructure, are preferred due to their practical use in day-to-day activities. However, such informal practices have been observed to trigger a variety of technical and security-related issues that remain undocumented by institutional IT policies. These tools may also pose significant risks to information security and work system reliability. This research aims to examine recurring problems encountered by users and interpret how these issues relate to key components in the work systems such as participants, technologies, information, processes, and products/services. The study employed a qualitative case study and applied the Eisenhardt method (1989) approach involving 35 respondents through interviews and field observations. Data was analyzed using open coding to extract recurring problem patterns. The analysis revealed four primary categories of problems System Error, Slow System Response, Access Limitations and Data Loss. These findings indicate that Shadow IT disrupts the flow of information and affects both technological and human elements within the work system. The study contributes by mapping factual user difficulties to concrete IT security needs that extend beyond formal policies. It suggests that effective IT security must address not only technical safeguards but also user behavior, access reliability, and adaptive policies capable of integrating informal digital practices.

Page 1 of 2 | Total Record : 11