About the Journal
J-KOMA: Jurnal Ilmu Komputer dan Aplikasinya is dedicated to researchers and practitioners in the field of computer science and information technology, focusing on publishing high-quality research covering topics such as Artificial Intelligence, Data Mining, Big Data Analytics, Software Engineering, Information Systems, Cybersecurity, and the development of web, mobile, and human-computer interaction (HCI) systems. J-KOMA is committed to serving as a scientific platform that promotes the advancement of knowledge and technological innovation in computing and its applications across education, research, and industry sectors.
J-KOMA: Jurnal Ilmu Komputer dan Aplikasinya is published by Universitas Negeri Jakarta and managed by the Research and Community Service Institute (LPPM), Universitas Negeri Jakarta in collaboration with the Computer Science Study Program, Faculty of Mathematics and Natural Sciences, Universitas Negeri Jakarta. J-KOMA also maintains an academic partnership with the Faculty of Mathematics and Natural Sciences, Universitas Negeri Surabaya, under collaboration agreements 3940/UN39.5.FMIPA/HK.07/2025 and 98477/UN38.3/KS.03.02/2025.
Publisher Information
Publisher: Universitas Negeri Jakarta
Management: LPPM Universitas Negeri Jakarta
Address: Kampus A, Universitas Negeri Jakarta, Jl. Rawamangun Muka, Jakarta Timur, Indonesia
Website: https://lppm.unj.ac.id/jurnal/
Contact Person: Devi Anggraeni (ojs@unj.ac.id)
Dedicated Email: uniilmukomouter@gmail.com
Current Issue
This volume presents seven cutting-edge research articles in the fields of computer science and applied statistics. This edition features a diverse range of data analysis methods, from robust regression for handling outliers in poverty modeling, Random Forest-based imputation techniques for missing data, to clustering algorithms for grouping forest fire hotspots and poverty-stricken areas in Indonesia. The articles in this volume also explore the application of machine learning and deep learning, including the prediction of lignin content in rice bran using K-Nearest Neighbor with PCA preprocessing, as well as student dropout risk prediction using Long Short-Term Memory (LSTM) based on longitudinal academic performance data. Overall, the contributions in this volume demonstrate the application of modern computational methods to address real-world problems in social, environmental, agricultural, and higher education domains, making it relevant reading for researchers, data science practitioners, and policymakers.
