Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal Journal of Information Systems and Informatics Journal of Computer Science and Technology Application
Djoko Soetarno
Binus University
Computer Science & IT Other

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Ensemble Learning for Pediatric Stunting Detection: A Comparative Study of XGBoost, Random Forest, and LightGBM with Oversampling Techniques Tri Sugihartono; Djoko Soetarno; Rahmat Sulaiman; Sarwindah; Marini; Fitriyani
Journal of Information System and Informatics Vol 8 No 2 (2026): April
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i2.1568

Abstract

Stunting, driven by chronic childhood malnutrition, remains a critical global public health concern. Early detection is persistently challenged by class imbalance in pediatric health datasets and the absence of systematic comparisons between oversampling strategies and ensemble classifiers. This study develops and evaluates an ensemble learning pipeline for stunting detection, benchmarking XGBoost, Random Forest, and LightGBM across five oversampling configurations — Original, SMOTE, ADASYN, Borderline-SMOTE, and SMOTE-ENN — using 10,000 pediatric health records from posyandu activities in Bangka Belitung Province, Indonesia. Seven anthropometric and demographic features were utilized, with stratified 80:20 train-test splitting and five-fold cross-validation. XGBoost with original imbalanced data achieved the highest Recall (0.9573) and a competitive F1-Score (0.9158), while LightGBM with SMOTE delivered the strongest balanced performance (F1-Score: 0.9160, ROC-AUC: 0.8431). SMOTE-ENN consistently underperformed across all classifiers. To our knowledge, this is the first study to simultaneously compare five oversampling strategies across three ensemble models within a unified framework, offering a foundation for high-sensitivity stunting surveillance in resource-constrained healthcare settings.
Comparative Performance Analysis of Dual-Prime RSA and Eight-Prime RSA Rahmat Sulaiman; Agustina Mardeka Raya; Djoko Soetarno; Tri Sugihartono; Ellya Helmud
Journal of Information System and Informatics Vol 8 No 2 (2026): April
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i2.1569

Abstract

This study presents a comparative performance analysis of Dual-Prime RSA and Eight-Prime RSA by evaluating computational efficiency in key generation, encryption, and decryption at 1024-bit and 2048-bit key lengths. Experiments were conducted in a controlled environment, using processing time as the primary performance metric. The results show a consistent computational advantage for Dual-Prime RSA across all operations. At the 2048-bit key length, Eight-Prime RSA requires substantially more time for key generation, performing approximately 643% slower than Dual-Prime RSA, which highlights the overhead associated with increasing the number of prime factors. Decryption results further reinforce this gap: Eight-Prime RSA at 2048-bit records about a 247% increase in processing time compared with its own 1024-bit baseline and remains markedly slower than Dual-Prime RSA at the same key length. Although differences in encryption time are less significant, Eight-Prime RSA offers no meaningful efficiency advantage. While earlier studies suggest that additional prime factors may provide theoretical security benefits, this work is limited to empirical performance benchmarking and does not include a full security analysis. Overall, the findings indicate that Dual-Prime RSA is the more practical and scalable choice for real-world 2048-bit applications and performance-sensitive deployments.
Analysis of User Perceptions on Interactive Learning Platforms Based on Artificial Intelligence Eirene Sana; Anandha Fitriani; Purwanti; Djoko Soetarno; Maulana Yusuf
CORISINTA Vol 1 No 1 (2024): February
Publisher : Pandawan Sejahtera Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/corisinta.v1i1.12

Abstract

Education is one field that is increasingly adopting artificial intelligence (AI) technology in an effort to improve the learning experience. AI-based interactive learning platforms have become a significant trend in modern education. This research aims to analyze user perceptions of AI-based interactive learning platforms and identify factors that influence their acceptance of this technology. We conducted an analysis using the SmartPLS method to explore the relationship between variables that influence user perceptions of AI in education. Research data was collected through surveys given to educational participants using AI-based learning platforms. The results of this research include findings about the extent to which factors such as interaction quality, usability, and social factors influence user perceptions of AI-based learning platforms. The results of data analysis will provide valuable insight into how the educational community accepts and adopts AI technology in the learning process. It is hoped that this research will make a significant contribution to the understanding of the acceptance of AI technology in educational contexts, as well as provide guidance for the development of more effective interactive learning platforms. The findings of this research can also support decision making in implementing AI in educational settings.
Comparative Classification of Promotional Sources in Higher Education Admissions Using K-Nearest Neighbor and Naive Bayes Elly Yanuarti; Sujono; Djoko Soetarno; Rahmat Sulaiman
Journal of Information System and Informatics Vol 8 No 4 (2026): August
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i4.1689

Abstract

This study evaluates and compares the performance of Naive Bayes and K-Nearest Neighbor (KNN) algorithms for classifying promotional-source categories in higher education admissions based on ten years of historical admission records. The objective is to analyze the capability of machine learning approaches in identifying patterns of applicant acquisition sources and to provide insights for institutional data-driven evaluation. After data preprocessing and quality filtering, 2,618 out of 4,901 records with complete target-variable information were retained and classified into seven promotional-source categories. Both algorithms were assessed using 5-fold cross-validation with multiple evaluation measures, including accuracy, macro-averaged recall, and comparison against a majority-class baseline to address the effect of severe class imbalance. Experimental results indicate that KNN achieved substantially higher overall accuracy (82.24%) than Naive Bayes (43.74%). However, neither model surpassed the majority-class baseline, demonstrating that accuracy alone can lead to misleading conclusions in highly imbalanced classification problems. In contrast, Naive Bayes obtained higher macro recall (36.32% compared with 18.14% for KNN), indicating a broader capability in recognizing minority promotional-source categories. The findings emphasize the importance of imbalance-aware evaluation and provide analytical insights into historical promotional-source distributions to support strategic admission planning and future institutional decision-making.
Co-Authors Agustina Mardeka Raya Anandha Fitriani Eirene Sana Elly Yanuarti Ellya Helmud Fitriyani Marini Maulana Yusuf Purwanti Rahmat Sulaiman Sarwindah Sujono Tri Sugihartono