cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Muh. Zainul Arifin
Contact Email
rumahjurnal25@gmail.com
Phone
+6285378329037
Journal Mail Official
rumahjurnal25@gmail.com
Editorial Address
Jalan Tanjung Barangan, Lorong Barangan 6 Bukit Baru Palembang Jalan Tanjung Barangan, Lorong Barangan 6 Bukit Baru Palembang
Location
Kota palembang,
Sumatera selatan
INDONESIA
Indonesian Journal of Computer Science and Engineering
Published by CV. Cendekiawan Muda Sriwijaya
ISSN : 30629497     EISSN : 30629519     DOI : https://doi.org/10.70656/ijcse.v1i02
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering
1. Artificial Intelligence and computer application 2. Data science, statistics and analytics 3. Information system 4. Geospatial and image processing 5. Computer networking and security 6. Engineering 7. Electrical and instrument aplication 8. Quantum and physic modelling 9. Education technology and implementation
Arjuna Subject : Ilmu Komputer (semua kategori) - Sistem Informasi
Articles 37 Documents
 1   2   3   4 
Segmentation of Problematic Loan Customers Using The K-Means Clustering Algorithm to Support Strategic Decision-Making (Case Study: Bank Mega Finance Bengkulu) Willi Novrian; Annisa Afriani; Julia Purnama Sari; Yusran Panca Putra
Indonesian Journal of Computer Science and Engineering Vol. 2 No. 02 (2025): IJCSE Volume 02 Number 02, November 2025
Publisher : CV. Cendekiawan Muda Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study analyzes 5,305 records of non-performing loan customers from Bank Mega Finance Bengkulu using the K-Means Clustering algorithm within the CRISP-DM framework. Based on variables such as tenure, outstanding balance, installment amount, and payment delay duration, the analysis identified three customer risk clusters (high, medium, and low) with a Davies-Bouldin Index (DBI) of 0.201, indicating good clustering quality. The segmentation results can help determine collection priorities, loan restructuring, and risk mitigation strategies, demonstrating the effectiveness of data mining in supporting strategic decision-making in banking risk management.
Design of a Medical Record Management Information System Based on Long-Term Storage for Hospital Efficiency Using V-Model Yuda Syahidin; Rena Novia Dewi Rena; Sali Setiatin
Indonesian Journal of Computer Science and Engineering Vol. 2 No. 02 (2025): IJCSE Volume 02 Number 02, November 2025
Publisher : CV. Cendekiawan Muda Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study aims to design an information system for the long-term storage of outpatient medical records in hospitals, focusing on improving data management efficiency, especially in retrieving inactive records. The research method used is descriptive with a qualitative approach. Data collection techniques include interviews, observations, and literature reviews. The software development process adopts the V-Model method, which emphasizes verification and validation at each development stage. The main problem identified in the long-term storage process is the manual classification of active and inactive records, which is done by checking the patient's last visit date one by one. This manual process is considered inefficient, time-consuming, and potentially disruptive to effective medical record management. To address this issue, the study proposes the design of an application that systematically manages inactive medical records in a computerized manner. This system is expected to help hospitals optimize time and resources, as well as support digital-based data storage policies. By implementing this information system, medical record management can become more structured, efficient, and accurate, ultimately enhancing the quality of health information services in hospitals.
User Interface (UI) Development For Ganeshpress Book Publisher Website With User-Centered Design Approach Aly Yudin Abdul Rohman; Candra Mecca Sufyana
Indonesian Journal of Computer Science and Engineering Vol. 3 No. 01 (2026): IJCSE Volume 03 Number 01, May 2026
Publisher : CV. Cendekiawan Muda Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70656/ijcse.v3i01.440

Abstract

In order to expand the publisher’s promotional reach, Ganeshpress, as a publishing company for written works, requires a user interface design that can build trust and credibility in the eyes of clients toward the publisher. This research adopts a case study approach to describe the development of the Ganeshpress book publisher’s website user interface using the User-Centered Design approach. The objective of this study is to design and develop a user interface (UI) based on User-Centered Design (UCD), in which the software development cycle focuses on user needs and relies on user feedback. The results of applying the User-Centered Design method indicate that active user involvement in the design process is proven effective in creating software that is not only functional but also aligned with user expectations.
Project: Analysis, Design, and Information System for a Web-Based Library System Azizah Hanifah; Dira Bulan Dari; Dewangga Nugroho Anwar; Lina Rosalinda; Yudi Setiawan
Indonesian Journal of Computer Science and Engineering Vol. 3 No. 01 (2026): IJCSE Volume 03 Number 01, May 2026
Publisher : CV. Cendekiawan Muda Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70656/ijcse.v3i01.508

Abstract

The system to be developed is a web-based library system. This system is designed to facilitate library administration in storing information regarding books, library collections, book loans, and collection loans, as well as overall library management. This system was developed to meet the needs of library management, which requires a system capable of improving operational efficiency and providing information on book and library collection loans. In assessing the resulting added value, the system is expected to have a positive impact in line with these needs.The development of this web-based system is also expected to improve the productivity and effectiveness of library services by automating the business processes of library units. On an intangible level, the developed system can enhance the user experience in terms of convenience and satisfaction, as well as increase the value of the library as a provider of educational services to the community.
Integration Of Conservation And The Blue Economy In Supporting Social Welfare In The Coastal Area of Purworejo Dian Mardiati Sari Alimuddin; Sapardiyono Sapardiyono; M. Nur Kamila Amrullah M. Nur Kamila Amrullah
Indonesian Journal of Computer Science and Engineering Vol. 3 No. 01 (2026): IJCSE Volume 03 Number 01, May 2026
Publisher : CV. Cendekiawan Muda Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

urworejo Regency has a coastline of approximately ±25 km crossing several coastal sub-districts such as Purwodadi. This area contains important ecosystems including mangrove forests, tourism-potential beaches such as Jatimalang and Jatikontal Beach, as well as capture fisheries and aquaculture pond activities. However, these potentials have not yet been fully developed in an integrated manner. Data from the Purworejo Marine and Fisheries Office (2023) show that the production value of capture fisheries in coastal areas has not demonstrated a significant upward trend. Meanwhile, mangrove forest areas have decreased due to abrasion and land conversion. Future government policy, as stated in Law No. 59 of 2024 concerning the National Long-Term Development Plan (RPJP) 2025–2045, Article 6 paragraph (2) letter c, emphasizes ensuring synergy among government and non-government development actors and achieving efficient, effective, equitable, and sustainable resource utilization. Community involvement in coastal management— particularly in fisheries, tourism, aquaculture ponds, and mangrove conservation—is significant. Most tourism management is conducted independently by the community, from planning and financing to management and development, except for Dewa Ruci tourism in Jatimalang Village, which is managed by the relevant government agency. Many residents work as fishermen and fish/shrimp pond farmers, generally without involvement from external parties. Government support is limited to providing fish auction facilities in Jatimalang Village, while other villages prepare facilities independently. Mangrove conservation efforts arise from collective awareness, with agreements to preserve and expand mangrove populations and impose sanctions on violators. To improve economic conditions, the community seeks to establish joint economic activities among fishermen, tourism actors, and pond farmers to create integrated management that enhances collective welfare.
A Comparative Study of SMOTE Variants and Particle Swarm Optimization for Feature Selection and Hyperparameter Tuning on Decision Tree in Breast Cancer Classification Himam Bashiran; Fito Satrio; Agung Malik Ibrahim
Indonesian Journal of Computer Science and Engineering Vol. 3 No. 01 (2026): IJCSE Volume 03 Number 01, May 2026
Publisher : CV. Cendekiawan Muda Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70656/ijcse.v3i01.661

Abstract

Breast cancer is one of the most prevalent types of cancer in Indonesia, making accurate early detection highly crucial to reduce mortality rates. However, classification effectiveness is often hindered by high-dimensional data and class imbalance issues, which can introduce bias into predictive models. This study proposes the integration of the Decision Tree algorithm with hybrid sampling techniques and Particle Swarm Optimization (PSO). PSO is employed to perform a dual role, namely simultaneous feature selection and hyperparameter tuning. Experimental results show that using 30 particles in PSO successfully reduced the data dimensionality significantly from 30 features to only 6 essential features: texture1, symmetry1, radius2, area3, smoothness3, and symmetry3. The combination of SMOTE-Tomek and PSO-based feature selection emerged as the best-performing scenario, achieving an accuracy of 99.68% while producing only one False Negative prediction. In addition to superior precision, the model demonstrated remarkable computational efficiency with an average latency of 0.0036 ms and a throughput of 274,897 samples per second. Explainable AI (XAI) analysis using SHAP confirmed that area3 was the most dominant feature, which is clinically consistent with indicators of cancer cell proliferation. This study proves that the synergy between data balancing techniques and metaheuristic optimization can produce an accurate, transparent, and efficient diagnostic model suitable for real-time medical implementation.
Comparative Evaluation of MobileNetV2 and Vision Transformer for Pneumonia Classification on Chest X-Ray Images: Fine-Tuning, Focal Loss, and Decision-Threshold Analysis Hendra Marcos; Ali Novian; Ma`dan Ma`dan Shomsomi; Widhaksa Triawan
Indonesian Journal of Computer Science and Engineering Vol. 3 No. 01 (2026): IJCSE Volume 03 Number 01, May 2026
Publisher : CV. Cendekiawan Muda Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70656/ijcse.v3i01.857

Abstract

Pneumonia remains a major respiratory infection that imposes a substantial health burden and requires rapid and accurate detection. This study evaluates five deep-learning configurations for binary classification of chest X-ray (CXR) images into Normal and Pneumonia classes: MobileNetV2 with a frozen backbone, fine-tuned MobileNetV2, fine-tuned MobileNetV2 with Focal Loss, Vision Transformer (ViT) without full fine-tuning, and fine-tuned ViT. The public dataset used in the experiments contains 5,856 images, comprising 5,216 training images, 16 validation images, and 624 test images. All metrics in this revised version were recalculated consistently from the experimental confusion matrices. ViT without full fine-tuning achieved the best overall performance at a threshold of 0.5, with 92.63% accuracy, 98.72% sensitivity, 82.48% specificity, a 94.36% F1-score, 90.60% balanced accuracy, and a Matthews correlation coefficient (MCC) of 0.845. MobileNetV2 with Focal Loss achieved 92.15% accuracy, 98.97% sensitivity, 80.77% specificity, and a 94.03% F1-score, providing slightly higher sensitivity with only four false-negative cases. In contrast, fine-tuned ViT achieved 100% sensitivity but only 57.69% specificity at the 0.5 threshold, indicating a shift in the predicted probability distribution and imbalanced generalization. Post hoc threshold analysis showed that changing the decision threshold can improve the error trade-off; however, it was not used to select the primary model because the threshold sweep was evaluated on the test set. These findings demonstrate that fine-tuning strategy and loss function affect model error characteristics differently, while screening-oriented evaluation should consider sensitivity and specificity together with accuracy

Page 4 of 4 | Total Record : 37

 1   2   3   4 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 3 No. 01 (2026): IJCSE Volume 03 Number 01, May 2026 Vol. 2 No. 02 (2025): IJCSE Volume 02 Number 02, November 2025 Vol. 2 No. 01 (2025): IJCSE Volume 02 Nomor 01, Mei 2025 Vol. 1 No. 02 (2024): IJCSE Volume 01, Nomor 02, November 2024 Vol. 1 No. 01 (2024): IJCSE Volume 01 Nomor 01, Juni 2024