Claim Missing Document
Check
Articles

Found 3 Documents
Search

PELATIHAN FUN LEARNING DENGAN MENGGUNAKAN KECERDASAN BUATAN PADA PEMBELAJARAN EDUKATIF UNTUK SISWA SISWI DI SMP MUHAMMADIYAH 29 SAWANGAN Ilham Idfiana; Wahid Aldi Nugroho; Muhammad Akbar Chalil; Muhammad Suprihatin; Rizki Kurniandi; Muhammad Ilham Kurniawan; Irfan Saeful Bahri; Sudarno
Abdi Jurnal Publikasi Vol. 4 No. 3 (2026): Januari
Publisher : Abdi Jurnal Publikasi

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

Abstract

This Community Service activity carries the theme “Fun Learning Training Using Artificial Intelligence in Educational Learning for Junior High School Students.” This program aims to provide an interactive learning experience by utilizing AI chatbots and other AI-based applications to support general learning. This training involves basic theory on AI, demonstrations on the use of chatbots for subjects, hands-on practice in the form of interactive quizzes and storytelling, to creative mini projects. Through this activity, it is hoped that students will be more motivated to learn, understand how to use AI wisely, and improve their digital literacy. Of the 29 participants divided into 6 groups, all activities—from creating short stories with AI chatbots, visualizing images, to creating songs. These results confirm that the use of AI in educational learning can provide an interactive, enjoyable, and productive learning experience, while also opening up new insights for teachers in integrating modern technology into the learning process.
Zero Trust Network Architecture Design For Mid-Scale Organizations Nurul Kamila; Makhsun; Sudarno
Jurnal Teknologi Informatika dan Komputer Vol. 12 No. 1 (2026): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v12i1.3292

Abstract

The development of information technology, the adoption of cloud-based services, and the implementation of remote work patterns increase network security risks in medium-sized organizations. Traditional network security approaches that focus on the perimeter are considered no longer adequate in facing increasingly complex cyber threats. This study presents the design of a Zero Trust Network (ZTN) architectural blueprint specifically designed for medium-sized organizations. The research method used is a conceptual approach through literature review, network security requirements analysis, and the design of the ZTN logical architecture. The research results are a Zero Trust Network architectural blueprint that emphasizes continuous verification, identity-based access control, and the application of the principles of least privilege and micro-segmentation. The architectural design is arranged in a modular and phased manner and is aligned with the NIST SP 800-207 framework, so it remains realistic for adoption without requiring drastic infrastructure changes. The resulting ZTN architectural blueprint can be used as an initial reference for medium-sized organizations in designing a Zero Trust-based network security strategy. This research is conceptual in nature and does not include the implementation stage or empirical testing in a real operational environment. It is hoped that the results of this study can serve as an initial reference for medium-sized organizations in designing a more adaptive and sustainable network security strategy.
Performance Analysis of CatBoost, XGBoost and Random Forest Models for Cloud Top Height Predicition Using Satelliite Data Ade Sekarningsih; Choirul Basir; Sudarno
CSRID (Computer Science Research and Its Development Journal) Vol 18 No 3 (2026): Oktober 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.3.2026.457-473

Abstract

Cloud Top Height (CTH) is a critical parameter for convective weather monitoring and aviation meteorology, particularly over the Indonesian maritime continent, where deep convection occurs frequently. This study evaluates the predictive performance and behavior of three tree-based ensemble models XGBoost, CatBoost, and Random Forest—for estimating CTH from Himawari multispectral observations using the Sentinel-5P/TROPOMI CTH product as the reference. The input variables comprise Himawari brightness-temperature channels, cloud fraction, latitude, and longitude. Evaluation on an independent spatial validation set of 3,444,543 observations shows that XGBoost achieved the best aggregate performance, with a mean absolute error of 971.71 m, root mean square error of 1297.57 m, coefficient of determination of 0.646, and mean bias of -33.55 m. CatBoost and Random Forest produced RMSE values of 1340.95 m and 1371.11 m, respectively. Multi-method interpretability analysis using built-in importance, permutation importance, group permutation, SHAP, partial dependence, and individual conditional expectation indicates that spectral channels and cloud fraction are the principal information sources, whereas coordinates provide weaker but non-zero spatial context. The error audit reveals relatively stable predictions for mid-level clouds but strong underprediction for extremely high cloud tops. Inter-model disagreement is positively but weakly related to actual error, indicating that it is a useful diagnostic signal rather than a calibrated uncertainty estimate. These results demonstrate that model selection for operational meteorology should consider not only aggregate accuracy but also error regimes, spatial dependence, and physical consistency.