cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Yuhefizar
Contact Email
jurnal.jacost@gmail.com
Phone
+628126777956
Journal Mail Official
jurnal.jacost@gmail.com
Editorial Address
Indonesian Society of Applied Science Jl. Raya ITS, Sukolilo, Surabaya, 60111 » Tel / fax : 08126777956 / 08126777956
Location
Unknown,
Unknown
INDONESIA
Journal of Applied Computer Science and Technology (JACOST)
Published by Indonesian Society of Applied Science
ISSN : -     EISSN : 27231453     DOI : https://doi.org/10.52158/jacost
Core Subject : Science,
Computer Science & IT
Fokus dan Ruang Lingkup Journal of Applied Computer Science and Technology (JACOST) dimaksudkan sebagai media kajian ilmiah hasil penelitian, pemikiran dan kajian analisis-kritis mengenai penelitian bidang ilmu komputer dan teknologi. Sebagai bagian dari semangat menyebarluaskan ilmu pengetahuan hasil dari penelitian dan pemikiran untuk pengabdian pada Masyarakat luas dan sebagai sumber referensi akademisi di bidang Ilmu Komputer dan Teknologi. Journal of Applied Computer Science and Technology (JACOST) menerima artikel ilmiah dengan lingkup penelitian pada: Rekayasa Perangkat Lunak Rekayasa Perangkat Keras Keamanan Informasi Rekayasa Sistem Sistem Pakar Sistem Penunjang Keputusan Data Mining Sistem Kecerdasan Buatan Jaringan Komputer Teknik Komputer Pengolahan Citra Algoritma Genetik Sistem Informasi Business Intelligence and Knowledge Management Database System Big Data Internet of Things Enterprise Computing Machine Learning Topik kajian lainnya yang relevan
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 105 Documents
 7   8   9   10   11 
Pengembangan Website Harga Bapokting Real-time dengan Extreme Programming dan Integrasi API SILINDA Setiawan, Ridwan; Parlina, Rina; Gunadhi, Erwin
Journal of Applied Computer Science and Technology Vol. 6 No. 2 (2025): Desember 2025
Publisher : Indonesian Society of Applied Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52158/98c7mh73

Abstract

This study aims to implement the SILINDA API from the West Java Provincial Government on a prototype website to present real-time price data for Basic Necessities and Important Goods (Bapokting) in Garut Regency. This addresses the problem of reporting delays and potential data inaccuracies that arise from the manual process of reporting via WhatsApp and weekly recapitulation using Microsoft Excel. The system was developed using the Extreme Programming (XP) methodology, which includes the stages of planning, design, coding, and testing. System design utilizes Unified Modeling Language (UML), specifically use case and class diagrams. The implementation uses JavaScript with the React.js library for the frontend and Node.js with the Express.js framework for the backend. The result of this research is a website prototype that is synchronized with the SILINDA API to perform automatic price updates. System testing included unit testing with a black-box approach and acceptance testing using the System Usability Scale (SUS) method, which yielded an average score of 83, categorized as Grade A (Excellent) with an "Acceptable" level of acceptance. This research contributes a system that replaces the manual reporting process with a website synchronized with SILINDA, providing real-time data for the Disperindag ESDM, Garut Satu Data, and the general public. It also demonstrates the effectiveness of the XP method in building an adaptive system that is relevant to user needs.
Klasifikasi Pemohon Pinjaman dengan Hyperparameter Tuning dan Teknik Penyeimbangan Data Yulvida, Donata; Quinevera, Stefanie; Mardianto, Ricky; Joses, Steven
Journal of Applied Computer Science and Technology Vol. 6 No. 2 (2025): Desember 2025
Publisher : Indonesian Society of Applied Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52158/krjtrh05

Abstract

Loan classification is a critical component of credit risk management, as it categorizes loans based on risk levels and supports the financial stability of banks, where loan-related income represents a substantial share of assets. Effective classification aims to ensure secure asset allocation, minimize credit risk, and prevent potential repayment issues. This study enhances loan classification performance through two strategies: hyperparameter optimization of Decision Tree and Random Forest algorithms, and data balancing techniques to address class imbalance. Experimental results show that the Decision Tree achieves 89.21% accuracy with an F1-Score of 70.17%, while the Random Forest demonstrates higher performance, reaching 94.04% accuracy and an F1-Score of 79.75%. Random Oversampling reduces bias toward majority classes by improving model sensitivity, while hyperparameter tuning with GridSearchCV identifies optimal parameter settings, thereby strengthening predictive performance. The findings highlight that combining data balancing with hyperparameter optimization effectively improves accuracy and F1-Scores. These approaches are not limited to the algorithms tested but can also be applied to other classification methods, offering broader potential for enhancing credit risk prediction in banking.
A Comparative Study of Random Forest, K-Nearest Neighbors, and XGBoost Models for Weather-Aware Smart Office Building Automation Erwin Yonata; Maya Anggun Beer; Ni Nyoman Putri Shopia; Emilia Loho; Gilang Raka Rayuda Dewa
Journal of Applied Computer Science and Technology Vol. 7 No. 1 (2026): Juni 2026 (In progress)
Publisher : Indonesian Society of Applied Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52158/7925qh24

Abstract

The intelligent control of lighting and HVAC systems plays a critical role in reducing energy consumption in smart buildings. However, many existing automation systems rely on static scheduling strategies that fail to adapt to dynamic environmental conditions. Although machine learning has been widely applied to weather-based building automation, inconsistent feature selection, model configuration, and evaluation procedures limit the validity of comparative performance claims. This study aims to develop and evaluate a machine-learning-based weather classification framework for smart building automation. The proposed methodology follows a structured pipeline comprising data acquisition and preprocessing, model training and testing, parameter tuning, and performance evaluation. A publicly available Weather Type Classification dataset is used, consisting of numerical weather parameters, which are encoded prior to training. Feature selection is applied to identify the most influential predictors. Three machine learning models, Random Forest, K Nearest Neighbors, and XGBoost, are trained using an 80:20 stratified split, with hyperparameters optimized through grid search to ensure an optimized model. Model performance is evaluated using accuracy, precision, recall, F1 score, and a confusion matrix. Experimental results demonstrate that Random Forest achieves the highest accuracy of 97.50 percent, followed by XGBoost at 96.90 percent and K Nearest Neighbors at 95.73 percent, with balanced performance across all weather categories. The findings indicate that ensemble-based classifiers are well-suited for robust weather recognition. The classified weather outputs can be directly mapped to real-time control strategies for lighting and HVAC systems, enabling adaptive automation and improved energy efficiency in smart buildings.
Paradoks Keamanan Autentikasi Dua Faktor (2FA): Systematic Literature Review terhadap Kesenjangan Protokol Teoretis dan Kegagalan Implementasi Praktis Dzikri Izzatul Haq; Syafrial Fachri Pane
Journal of Applied Computer Science and Technology Vol. 7 No. 1 (2026): Juni 2026 (In progress)
Publisher : Indonesian Society of Applied Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52158/h9qv3j56

Abstract

Two-Factor Authentication (2FA) has been widely adopted as a fundamental security standard, yet sophisticated cyberattacks continue to exploit security loopholes that often lie not in the protocol itself, but in its implementation. This study aims to systematically synthesize current scientific literature to uncover the root causes of the gap between the theoretical security of 2FA protocols and practical exploitation risks in the field. Using the Systematic Literature Review (SLR) method with PRISMA guidelines, 43 high-quality articles (Q1-Q4) from the Scopus database published between 2020 and 2025 were analyzed using thematic synthesis. The findings reveal a central paradox where, although 2FA protocols are becoming mathematically stronger, 88% of failure points have shifted to implementation fundamentals; the most critical weaknesses identified are the storage of secret keys in plaintext format on client applications and the effectiveness of social engineering attacks against users. This study concludes that real-world 2FA security is determined more by the quality of implementation code and user awareness than by the cryptographic strength of the protocol alone, implying that industry priorities must shift from developing new protocols to enforcing secure implementation audits and continuous user education.
Generative Chatbot Berbahasa Indonesia Dengan Menggunakan Arsitektur Transformer Winarto Saputro; Edi Winarko
Journal of Applied Computer Science and Technology Vol. 7 No. 1 (2026): Juni 2026 (In progress)
Publisher : Indonesian Society of Applied Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52158/v1x82029

Abstract

Chatbot merupakan program komputer yang dirancang untuk berinteraksi dengan manusia melalui pesan teks maupun suara. Salah satu pendekatan yang banyak dikaji adalah Generative Chatbot, yang menghasilkan respons secara dinamis berdasarkan data percakapan, berbeda dengan pendekatan Retrieval maupun Rule-based yang bergantung pada templat atau basis pengetahuan tetap. Penelitian ini secara khusus bertujuan untuk mengembangkan model sequence-to-sequence berbasis Transformer untuk percakapan berbahasa Indonesia serta melakukan pembandingan empiris dengan arsitektur GRU yang diperkaya dengan mekanisme Attention. Dataset yang digunakan berupa pasangan tanya–jawab berbahasa Indonesia yang diambil dari penelitian terdahulu dan diperluas melalui teknik augmentasi berbasis sinonim guna meningkatkan variasi dan keberagaman data pelatihan. Model dievaluasi menggunakan metrik BLEU-Score untuk mengukur kualitas respons yang dihasilkan serta indikator efisiensi komputasi selama pelatihan dan inferensi. Hasil eksperimen menunjukkan bahwa arsitektur Transformer menunjukkan kinerja yang lebih baik dalam mempertahankan konteks pada urutan kalimat yang panjang, yang tercermin pada peningkatan nilai BLEU-Score dibandingkan GRU+Attention pada data setiap dataset yang diuji. Selain itu, sifat pemrosesan paralel pada Transformer berkontribusi pada efisiensi waktu pelatihan yang lebih baik dibandingkan model berbasis GRU+Attention yang bersifat sequential. Penelitian ini menunjukkan potensi Transformer sebagai fondasi yang efektif untuk pengembangan generative chatbot berbahasa Indonesia

Page 11 of 11 | Total Record : 105

 7   8   9   10   11 

Filter by Year

2020 2026


Reset
Filter By Issues
All Issue Vol. 7 No. 1 (2026): Juni 2026 (In progress) Vol. 6 No. 2 (2025): Desember 2025 Vol 6 No 1 (2025): Juni 2025 Vol 5 No 2 (2024): Desember 2024 Vol 5 No 1 (2024): Juni 2024 Vol 4 No 2 (2023): Desember 2023 Vol 4 No 1 (2023): Juni 2023 Vol 3 No 2 (2022): Desember 2022 Vol 3 No 1 (2022): Juni 2022 Vol 2 No 2 (2021): Desember 2021 Vol 2 No 1 (2021): Juni 2021 Vol 1 No 2 (2020): Desember 2020 Vol 1 No 1 (2020): Juni 2020 More Issue