cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Jordy Lasmana Putra
Contact Email
jordy.jlp@nusamandiri.ac.id
Phone
+6221-231170
Journal Mail Official
jurnal.coscience@bsi.ac.id
Editorial Address
Jl. Kramat Raya No.98, RT.2/RW.9, Kwitang, Kec. Senen, Kota Jakarta Pusat, Daerah Khusus Ibukota Jakarta 10450 (Gedung Rektorat Universitas Bina Sarana Informatika)
Location
Kota adm. jakarta barat,
Dki jakarta
INDONESIA
Computer Science (CO-SCIENCE)
Published by Universitas Bina Sarana Informatika
ISSN : -     EISSN : 27749711     DOI : https://doi.org/10.31294/coscience
Core Subject : Science,
Computer Science & IT
Computer Science (CO-SCIENCE) pertama kali publikasi tahun 2021 dengan nomor ISSN (Elektonik): 2774-9711 yang diterbitkan oleh Lembaga Ilmu Pengetahuan Indonesia (LIPI). Computer Science (CO-SCIENCE) adalah jurnal yang diterbitkan oleh Program Studi Ilmu Komputer Universitas Bina Sarana Informatika. Computer Science (CO-SCIENCE) terbit 2 kali setahun (Januari dan Juli) dalam bentuk elektronik. Redaksi menerima naskah berupa artikel ilmiah dan penelitian pada bidang: Networking, Aplication Mobile, Software Engineering, Web Programming, Mobile Computing, Cloud Computing, Data Mining, dan Aplikasi Sains.
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 131 Documents
 10   11   12   13   14 
Perancangan Sistem Informasi Surat Administrasi Penduduk Elektronik Menggunakan Metode Scrum Indana, Luthfi; Ilmananda, Asri Samsiar
Computer Science (CO-SCIENCE) Vol. 5 No. 2 (2025): Juli 2025
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/co-science.v5i2.9511

Abstract

Letter management is a routine activity carried out at the Kerta Jaya Village office in Banyuasin. Currently, the administration of administrative documents in this village has been done manually, resulting in long queues. This study aims to develop an information system for managing electronic administrative documents for residents, such as domicile certificates, death certificates, and single-marriage certificates. This research is a research and development (R&D) study using the Scrum method. The Scrum method divides tasks into small parts (sprints). In each sprint, researchers focus on completing several features that can be used immediately. The Scrum method was used because it has a structured framework with sprints that produce functional incremental products. This method is suitable because it allows for rapid adaptation so that application development does not take too long. The result of this study is an information system for managing electronic administrative letters in Kerta Jaya Village, Banyuasin District. From the results of the application's usability aspect, the percentage obtained on 30 respondents was 79.16%, meaning this application is suitable for use by the community.
Design and Development of IdentifiKu: A Web-Based Diagnostic Model for Differentiated Learning Siregar, Muhammad Noor Hasan; Ramadhani, Yulia Rizki; Fadhillah, Yusra; Pratama, Yoviansyah Rizki
Computer Science (CO-SCIENCE) Vol. 6 No. 1 (2026): January 2026
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/co-science.v6i1.9762

Abstract

This study aims to develop and evaluate IdentifiKu, a web-based diagnostic assessment platform designed to support differentiated learning within the Kurikulum Merdeka framework in Indonesia. Specifically, the research seeks to bridge the gap in existing assessment platforms that predominantly focus on cognitive dimensions by integrating cognitive and non-cognitive domains—learning styles, personality traits, and multiple intelligences—into a unified scoring model. The platform was developed using a Design and Development Research (DDR) approach combined with the Waterfall Software Development Life Cycle (SDLC), encompassing requirements analysis, system design, implementation, testing, and deployment. The architecture adopts a three-tier client–server model, with a Laravel-based application layer and a MySQL database optimized to the third normal form. Performance evaluation involved functional testing and user feedback from twelve teachers across diverse subject areas. Quantitative results indicated that the system met or exceeded all operational benchmarks, including an average page load time of 2.4 seconds, 99.8% uptime, 100% scoring accuracy, and a System Usability Scale (SUS) score of 85.3. Teachers reported that the platform’s comprehensive learner profiles facilitated targeted instructional strategies, improved student engagement, and streamlined assessment processes. This research contributes a scalable, pedagogically aligned model for integrating multidimensional diagnostics into differentiated learning practices, which may be adapted to other educational contexts to enhance data-driven instruction.
Optimization of Crop Recommendation Model Using Ensemble Learning Techniques for Multiclass Classification Marlina, Siti; Misriati, Titik; Aryanti, Riska
Computer Science (CO-SCIENCE) Vol. 6 No. 1 (2026): January 2026
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/co-science.v6i1.10044

Abstract

Crop recommendation systems play a crucial role in modern agriculture by helping farmers make data-driven decisions to maximize yield, optimize resource use, and ensure sustainable farming practices. By analyzing environmental and soil parameters, these systems can suggest the most suitable crops for specific conditions, reducing the risks of crop failure and improving overall productivity. This study evaluates the performance of five ensemble learning algorithms—Random Forest, Extra Trees, CatBoost, XGBoost, and LightGBM—for multiclass classification in a crop recommendation system. All models achieved high accuracy above 98%, with Random Forest demonstrating the best and most stable performance. The feature importance analysis revealed that climatic factors, particularly rainfall and humidity, contributed the most to prediction outcomes, followed by macronutrients such as potassium, phosphorus, and nitrogen. In contrast, temperature and soil pH showed relatively lower influence. These findings highlight the dominance of climatic factors over soil chemical properties and demonstrate the capability of ensemble learning methods to capture complex data patterns. Random Forest is recommended as the primary model to support more effective land management and crop cultivation strategies.
Development of Web and Mobile Health Services Information System Using Waterfall Method Pratrian, Yoga; Hendriyan, Yayan; Kahfi, Ahmad Hafidzul
Computer Science (CO-SCIENCE) Vol. 6 No. 1 (2026): January 2026
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/co-science.v6i1.10072

Abstract

The increasing demand for fast, accurate, and efficient healthcare services has encouraged the development of integrated information systems. This study aims to design and develop a Health Service Information System (SILAKES) based on web and mobile platforms at the Oputa Yi Koo Heart and Blood Vessel Hospital (RSJPD) in Kendari. The system is developed to facilitate patients in accessing doctor schedules, taking queue numbers online, consulting services, checking blood stock availability, and filling out satisfaction surveys. The development process adopts the waterfall (linear sequential model) method, which consists of five stages (requirement definition, system and software design, implementation and unit testing, integration and system testing, operation and maintenance). The results of this study show that SILAKES improves the efficiency of hospital staff and provides convenience for patients to access health services without space and time constraints. The implementation of this system also contributes to the digitalization of hospital services and supports the enhancement of overall healthcare service quality
Developing an Efficient PPDB System Integrating Payment Gateway and Secure Exams Syah, Muhammad Rohman; Novianti, Deny; Rosdiyanto, Roynaldy
Computer Science (CO-SCIENCE) Vol. 6 No. 1 (2026): January 2026
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/co-science.v6i1.10103

Abstract

The New Student Admission (PPDB) process is a critical gateway for educational institutions. However, SMKS Jakarta 1 Pondok Kopi faced a significant 35.4% decline in applicants between 2021 and 2024 due to an inefficient and fragmented PPDB system. Key issues included an outdated information platform, a complex multi-platform registration flow, error-prone manual payment verification, and an insecure online exam system. This research aimed to develop a web-based integrated PPDB information system that consolidates all stages: registration, digital payments via a payment gateway, an online examination with anti-cheating features, and centralized announcements. Using the Waterfall development model, the system was evaluated in two stages. Black Box testing confirmed that all functionalities performed as expected. Furthermore, User Acceptance Testing (UAT) revealed a very high acceptance rate, achieving average scores of 4.48 out of 5.00 from student proxies and 4.50 from the committee, yielding a final interpretation of “Very Good.” The practical implication of this system is a significant improvement in administrative efficiency, data accuracy, and modernization of the school's services. This research contributes by providing and validating an effective integrated PPDB system model, proving it to be a comprehensive solution for vocational education institutions.
Analysis of Student Academic Performance Using Random Forest and Support Vector Machines Agung, Galih Mifta; Zuama, Robi Aziz; Budi, Eko Setia
Computer Science (CO-SCIENCE) Vol. 6 No. 1 (2026): January 2026
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/co-science.v6i1.10123

Abstract

Assessing student academic performance objectively remains a challenge at SMP Negeri 16 Bogor due to diverse internal and external factors in student records. This study aims to compare the classification performance of the Random Forest and Support Vector Machine (SVM) algorithms using a dataset of 403 students containing demographic, socioeconomic, and school-related attributes. Although the attributes are not traditional academic indicators (e.g., assignment or exam scores), they are used to explore whether non-academic features can contribute to predictive models. Following data preprocessing—handling missing values, encoding categorical variables, and managing class imbalance—both algorithms were evaluated using accuracy, precision, recall, and confusion matrix analysis. Results show that SVM outperforms Random Forest with 78.00% accuracy, 89.98% precision, and 70.24% recall. These findings indicate that SVM is more robust for imbalanced classification tasks and can provide useful insights even when academic-performance labels are predicted from non-academic attributes.
Saliency-Enhanced Deep Learning Framework for Stain-Robust White Blood Cell Segmentation and Classification Gashti, Mehdi Zekriyapanah; Mohammadpour, Mostafa; Farjamnia, Ghasem
Computer Science (CO-SCIENCE) Vol. 6 No. 1 (2026): January 2026
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/co-science.v6i1.10182

Abstract

Accurate segmentation and classification of white blood cell (WBC) are essential for clinical hematology, yet remain challenging due to staining variability, complex backgrounds, and class imbalance. This study introduces an explainable, saliency-enhanced deep learning framework designed to achieve stain-robust leukocyte analysis. The framework integrates a saliency-driven preprocessing module, a lightweight EfficientSwin hybrid backbone, and a ResNeXt-CC–inspired cross-layer feature fusion block to capture complementary fine-grained and global features. A multi-task head jointly performs WBC segmentation and subtype classification, while a saliency-alignment loss enforces consistency between learned attention and saliency priors, providing training-time interpretability rather than post-hoc visualization alone. SG-CLDFF was evaluated on three public datasets (BCCD, LISC, ALL-IDB) and further tested under cross-stain and cross-dataset conditions. The framework achieved 95.8% accuracy, 0.94 F1-score, and 0.82 IoU, improving over strong CNN and transformer baselines. Ablation studies confirmed that both saliency preprocessing and cross-layer fusion contribute independently to performance, with saliency alignment yielding ≥2 IoU improvement in cross-stain scenarios (p < 0.05). Qualitative results using saliency maps and Grad-CAM demonstrate focused attention on diagnostically meaningful regions. These findings validate SG-CLDFF as a robust, interpretable, and stain-resilient solution for automated WBC analysis, offering a practical foundation for deployment in digital hematology workflows.
Analyzing Public Sentiment Toward Makanan Bergizi Gratis Program Using Machine Learning Napiah, Musriatun; Heristian, Sujiliani; Raharjo, Mugi; Purnama, Rachmat Adi
Computer Science (CO-SCIENCE) Vol. 6 No. 1 (2026): January 2026
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/co-science.v6i1.10445

Abstract

Makanan Bergizi Gratis (MBG) program is a strategic initiative of the Indonesian government to improve the nutritional quality of schoolchildren. This research seeks to examine public sentiment regarding the MBG program by leveraging 10,000 tweets obtained from Kaggle. The method used combines Natural Language Processing (NLP) and Machine Learning approaches, several algorithms such as Logistic Regression, Support Vector Machine (SVM), Random Forest, Naive Bayes, XGBoost, and LightGBM were tested to compare classification performance. The dataset contains a collection of public reviews categorized into three sentiment classes: positive, negative, and neutral. The analysis process includes text cleaning, tokenization, stopword removal, and stemming to obtain a cleaner text representation. Text features were then extracted using the Term Frequency–Inverse Document Frequency (TF-IDF) method. The results showed that the Logistic Regression 97% with an F1-score of 0.9552 models showed the most optimal performance. Sentiment analysis revealed 65% positive responses, 25% neutral, and 10% negative, with the dominant keywords being “nutrisi,” “sehat,” “anak sekolah,” and “gratis.” The results visualization, in the form of a Word Cloud and a bar chart, indicate that public opinion tends to be positive towards the implementation of the MBG program, particularly regarding improving the nutrition of schoolchildren. This research is expected to provide input for policymakers in evaluating public perceptions of the implementation of food-based social programs.
SIBI-Based Gesture Recognition System Using Random Forest for Hearing-Impaired Communication Pratama, Andre; Wahidin, Ahmad Jurnaidi
Computer Science (CO-SCIENCE) Vol. 6 No. 1 (2026): January 2026
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/co-science.v6i1.10570

Abstract

Individuals with hearing impairments often face communication barriers when interacting with people unfamiliar with sign language. One officially recognized sign system in Indonesia is the Indonesian Sign System (SIBI), which conveys meaning through hand gestures. Most existing sign language recognition studies focus on single-hand gestures, limiting expressiveness. This study proposes a two-hand gesture recognition system based on digital image processing to translate SIBI gestures into alphabetic letters, while additional gestures enable text control functions. The dataset consists of 29 gesture classes with 1,000 images per class, totaling 29,000 images, and is divided into training and testing sets using a train–test split. A Random Forest classifier is employed to handle high-dimensional landmark coordinate data. Experimental results demonstrate a classification accuracy of 99.97%. The system is implemented as a real-time, user-friendly application. Although high accuracy is achieved, potential overfitting due to the controlled dataset is identified as a limitation. Future work will focus on improving generalization using more diverse real-world data.
UML-Based Design and Kano Evaluation of an Augmented Reality Library Application Feoh, Gerson; Anggreni, Ni Putu Ria
Computer Science (CO-SCIENCE) Vol. 6 No. 1 (2026): January 2026
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/co-science.v6i1.11637

Abstract

The application of Augmented Reality (AR) technology in library services has the potential to enhance the user experience through more interactive and engaging information presentations. This study aims to create an augmented reality (AR) book search system that uses marker-based tracking to help students find references at the Dhyana Pura University Library, while also measuring how satisfied users are using the Kano Model. The system was created using the waterfall approach for developing software and used Unified Modeling Language (UML) to outline how activities flow and how different parts of the system connect. The satisfaction test involved 54 respondents, with attribute analysis using the Kano Model and Customer Satisfaction Coefficient (CSC). The results of the study show that most of the application features fall into the Attractive category, which indicates that these features provide added value and a positive experience for users. The combination of UML-based system design and evaluation with the Kano Model was successful in creating a library application that is functional, easy to use, and focused on user satisfaction.

Page 13 of 14 | Total Record : 131

 10   11   12   13   14 

Filter by Year

2021 2026


Reset
Filter By Issues
All Issue Vol. 6 No. 1 (2026): January 2026 Vol. 5 No. 2 (2025): Juli 2025 Vol. 5 No. 1 (2025): Januari 2025 Vol. 4 No. 2 (2024): Juli 2024 Vol. 4 No. 1 (2024): Januari 2024 Vol. 3 No. 2 (2023): Juli 2023 Vol. 3 No. 1 (2023): Januari 2023 Vol. 2 No. 2 (2022): Juli 2022 Vol. 2 No. 1 (2022): Januari 2022 Vol. 1 No. 2 (2021): Juli 2021 Vol. 1 No. 1 (2021): Januari 2021 More Issue