2026
Phishing URL Detection Using URL Characteristics: A Multi-Algorithm Machine Learning and Explainable AI (XAI) Approach
JESSI · 7(2), 243–257
XGBoost achieved 97.89% accuracy with SHAP-based explanations.
View publication ↗
2026
Feature Selection and Explainable AI for Heart Disease Detection using Machine Learning
Sistemasi: Jurnal Sistem Informasi, Vol. 15, No. 6, pp. 2328–2341
Random Forest achieved 85.2% accuracy and 97.0% recall; Chi-Square and RFE were evaluated with Random Forest, XGBoost, and SVM, with SHAP for explanation.
View publication ↗
2026
Multi-Class Skin Disease Classification using Transfer Learning and Explainable AI
Sistemasi: Jurnal Sistem Informasi, Vol. 15, No. 6, pp. 2342–2356
DenseNet201 achieved 87.79% accuracy, 87.51% precision, 87.48% recall, and 87.45% F1-score; Grad-CAM, SHAP, and LIME were used for interpretability.
View publication ↗
2025
Survey on Risks Cyber Security in Edge Computing for The Internet of Things Understanding Cyber Attacks Threats and Mitigation
JUTI · 23(1), 29–50
Research taxonomy covering four cybersecurity-risk dimensions.
View publication ↗
2025
Analyzing the Impact of Data Filtering on Anomaly Detection under Distribution Shift Conditions
JESSI · 6(3), 478–492
Examines filtering and model adaptation under distribution shift.
View publication ↗
2025
AI-Powered Botox Dosage Classification: A Comparative Study of CNN Architectures on Facial Wrinkle Analysis
JESSI · 6(3)
Compares CNN architectures for facial-wrinkle classification.
View publication ↗
2025
Keamanan Data dan Informasi: Konsep, Ancaman, dan Implementasi
Book / Chapter
Book contribution on data and information security.
View publication ↗
2025
Teknologi Wireless: Konsep, Arsitektur, dan Inovasi di Era Konektivitas Modern
Book / Chapter
Book contribution on wireless technologies and connectivity.
View publication ↗
2024
Exploring the Potential of Feature Selection Methods for Effective and Efficient IoT Malware Detection
IEEE ICCCNT 2024
Pearson Correlation + Gradient Boosting reported 99.98% accuracy.
View publication ↗
2024
Normality Shift Identification for Anomaly Detection of Windows Event Logs
IEEE ICOIACT 2024, 61–66
Compares KLD, JSD, and Hellinger Distance for normality-shift identification.
View publication ↗
2024
Improving the UI/UX Quality of the JasBi Application using UEQ and UCD
Pinisi Discretion Review, Vol. 7, Issue 2, pp. 335–352
UEQ and User-Centered Design were used to redesign the JasBi application; the study reports post-design scores for attractiveness 2.30, perspicuity 1.98, efficiency 2.30, stimulation 1.88, and novelty 2.10.
View publication ↗
2024 · IEEE ICSCC
Zero-Shot Entity Recognition on Forensic Timeline
Zero-shot entity recognition for digital forensic timelines, comparing large language models for extracting and labeling entities from forensic log data.
View publication ↗