Article Per Year (5 Year)
p-Index From 2021 - 2026
0.702
P-Index
This Author published in this journals
All Journal Journal of Defense Technology and Engineering
Adam Mardamsyah
Universitas Pertahanan Republik Indonesia, Bogor, Indonesia
Aerospace Engineering Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Mechanical Engineering Transportation

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

Found 4 Documents
Search

 1 
Enhanced cyber attack detection using optimized random forest with SMOTE-based class balancing and feature selection Jonson Manurung; Adam Mardamsyah; Baringin Sianipar
Journal of Defense Technology and Engineering Vol. 1 No. 2 (2026): January, Journal of Defense Technology and Engineering
Publisher : Fakultas Teknik dan Teknologi Pertahanan, Universitas Pertahanan Republik Indonesia

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

Abstract

The rapid expansion of interconnected enterprise networks has intensified cybersecurity threats, while traditional signature-based intrusion detection systems remain ineffective against evolving and imbalanced attack patterns, particularly zero-day and low-frequency attacks. This study aims to develop an optimized and practically deployable intrusion detection framework by leveraging a Random Forest classifier on the CIC-IDS2017 benchmark dataset, with emphasis on robust minority attack detection, computational efficiency, and interpretability for real-world security operations. The proposed method integrates comprehensive data preprocessing, Synthetic Minority Over-sampling Technique (SMOTE) for class imbalance mitigation, feature importance–driven dimensionality reduction, and exhaustive grid search–based hyperparameter optimization within a unified machine learning pipeline. Experiments conducted on 2.52 million network flow records demonstrate that the optimized model achieves 98.14% accuracy, 96.25% weighted F1-score, and 0.993 ROC-AUC, while maintaining stable performance across all attack categories, including minority classes such as Infiltration and Botnet with F1-scores exceeding 93%. Feature selection reduced dimensionality by 58.3% and training time by 63.2% without degrading performance, enhancing deployment feasibility in enterprise intrusion detection environments. Comparative analysis confirms that the proposed approach outperforms baseline Random Forest models, traditional machine learning methods, and recent deep learning approaches while requiring significantly lower computational resources. These findings indicate that a holistically optimized Random Forest framework offers a reliable, interpretable, and operationally efficient solution for real-world network security monitoring and cyber defense systems.
Big data analytics framework for defense strategic intelligence and decision support systems Rochedi Idul Adha; Adam Mardamsyah; Khaerul Imam Phatoni
Journal of Defense Technology and Engineering Vol. 1 No. 2 (2026): January, Journal of Defense Technology and Engineering
Publisher : Fakultas Teknik dan Teknologi Pertahanan, Universitas Pertahanan Republik Indonesia

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

Abstract

The contemporary defense environment faces rapidly evolving threats, vast heterogeneous data, and linguistic diversity, creating significant challenges for timely and accurate intelligence analysis. This study aims to develop an integrated big data analytics framework that combines open-source intelligence, social media monitoring, and satellite imagery into a unified temporal knowledge graph to support multilingual, cross-modal threat assessment. The proposed methodology incorporates five key phases: multi-source data collection and preprocessing, multilingual transformer-based natural language processing for entity, relation, and event extraction, temporal knowledge graph construction, machine learning-driven analytical modeling for threat prediction and risk assessment, and comprehensive evaluation using both system performance and intelligence value metrics. Experimental results demonstrate that the framework achieves superior entity recognition (F1-score 0.882) and relation extraction (F1-score 0.869), reduces processing latency by 92.6% compared to baseline systems, and integrates 6.3 million entities across 15 languages. Multi-source data fusion improves assessment accuracy by 18.4%, enabling near real-time situational awareness and enhanced strategic decision-making. The system’s explainable reasoning and temporal modeling capabilities provide transparent, actionable intelligence for defense planners, addressing limitations of traditional single-modality and monolingual systems. These findings indicate that integrating multilingual NLP, cross-modal fusion, and temporal knowledge representation significantly enhances operational readiness and early warning capabilities, offering a practical framework adaptable to national and regional security contexts.
Security threat prediction model using graph neural networks and deep temporal learning Eryan Ahmad Firdaus; Adam Mardamsyah; Jeremia Paskah Sinaga
Journal of Defense Technology and Engineering Vol. 1 No. 2 (2026): January, Journal of Defense Technology and Engineering
Publisher : Fakultas Teknik dan Teknologi Pertahanan, Universitas Pertahanan Republik Indonesia

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

Abstract

The increasing complexity and interconnectedness of modern security threats, including terrorism, social unrest, and transnational conflicts, pose significant challenges for traditional intelligence and threat detection systems, which struggle to capture both relational and temporal dynamics of evolving security environments. This study aims to develop a predictive framework capable of providing early warnings of emerging security threats by integrating graph-based relational modeling with temporal sequence learning. We propose a hybrid architecture combining Graph Neural Networks (GNN) with bidirectional Long Short-Term Memory (LSTM) networks, enhanced with an attention-based fusion mechanism to jointly model actor interactions and temporal evolution. The framework leverages large-scale event data from GDELT and ACLED spanning 2015–2025, encompassing over 9.8 million events and 14,532 unique actors, and constructs dynamic, attributed security networks to capture multi-dimensional actor relationships. Experimental results demonstrate that the proposed GNN-LSTM model achieves an overall accuracy of 94.3% and an F1-score of 88.3% for critical threat detection, outperforming traditional machine learning baselines and providing early warnings up to nine days in advance. The model also offers interpretability by highlighting influential actors and key relational patterns contributing to threat escalation. These findings suggest that integrating relational and temporal information through hybrid deep learning architectures significantly enhances predictive accuracy and operational utility in security threat assessment, offering a practical tool for proactive decision-making and resource allocation in complex security environments.
A multi-objective Particle Swarm Optimization framework for defense logistics decision-making under dynamic and crisis conditions anindito anindito; Adam Mardamsyah; Jonson Manurung
Journal of Defense Technology and Engineering Vol. 1 No. 2 (2026): January, Journal of Defense Technology and Engineering
Publisher : Fakultas Teknik dan Teknologi Pertahanan, Universitas Pertahanan Republik Indonesia

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

Abstract

The complexity of decision-making in defense logistics systems has increased significantly due to demands for cost efficiency, distribution speed, and operational resilience in dynamic and crisis conditions. Conventional optimization approaches generally fail to capture these conflicting objectives simultaneously. This study aims to develop and evaluate a multi-objective optimization framework based on Multi-Objective Particle Swarm Optimization (MO-PSO) to support adaptive and performance-based defense logistics decision-making. The proposed method optimizes three main objective functions, namely minimizing operational costs, minimizing distribution time, and maximizing logistics readiness levels, with numerical parameter adjustments designed for the defense environment. Simulation results show that MO-PSO is capable of producing a more convergent and evenly distributed Pareto Front compared to comparison methods such as NSGA-II and standard MOPSO, with a 12.4–18.7% increase in hypervolume and a 21.3% decrease in solution dominance error. These findings indicate that the proposed approach is more effective in simultaneously balancing multi-objective trade-offs. Practically, the research results provide policy implications for defense planners in designing logistics strategies that are more efficient, responsive, and resilient to operational uncertainty.
Co-Authors anindito anindito Baringin Sianipar Eryan Ahmad Firdaus Jeremia Paskah Sinaga Jonson Manurung Khaerul Imam Phatoni Manurung, Jonson Rochedi Idul Adha