I. Dewa Made Widia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
I. Dewa Made Widia has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Muhammad Faisal
Universitas Muhammadiyah Makassar
3 shared publications - Eka Ratri Noor Wulandari
Universitas Brawijaya
2 shared publications - Ida Mulyadi
Universitas Muhammadiyah Makassar
2 shared publications Selvakumar Manickam
2 shared publicationsAedah Abd Rahman
Asia e University, Malaysia
1 shared publication- Alders Paliling
Universitas Sembilanbelas November Kolaka
1 shared publication
Latest Publications
- Open Access
- 1 July 2026
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 43 (1) , 345-354
Hybrid machine learning framework for anomaly detection in industrial IoT environments
The industrial internet of things (IIoT) has become a core component of Industry 4.0, enabling highly connected and data-driven industrial systems while simultaneously increasing exposure to cyber threats. Conventional intrusion detection systems (IDS), especially rule-based and signature-driven approaches, often struggle to cope with the dynamic, high-dimensional, and heterogeneous nature of IIoT traffic. This study proposes a hybrid anomaly detection framework that integrates autoencoder, isolation forest, and long short-term memory (LSTM) models using a weighted decision fusion strategy. Each component contributes complementary capabilities, including nonlinear feature learning, efficient outlier detection, and temporal pattern modeling. The framework is evaluated on the botnet of things (BoT-IoT) dataset and further validated using IoT-23. Experimental results show that the proposed hybrid approach achieves a precision of 0.999, recall of 0.970, and an F1-score of 0.985, while maintaining a false-negative rate below 0.001%. Although its area under the curve (AUC) is slightly lower than that of a standalone light gradient boosting machine (LightGBM) baseline, the hybrid framework consistently reduces missed detections, making it well suited for reliable real-time IIoT security monitoring.
- 1 July 2026
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 43 (1) , 345-354
Open AccessHybrid machine learning framework for anomaly detection in industrial IoT environments
The industrial internet of things (IIoT) has become a core component of Industry 4.0, enabling highly connected and data-driven industrial systems while simultaneously increasing exposure to cyber threats. Conventional intrusion detection systems (IDS), especially rule-based and signature-driven approaches, often struggle to cope with the dynamic, high-dimensional, and heterogeneous nature of IIoT traffic. This study proposes a hybrid anomaly detection framework that integrates autoencoder, isolation forest, and long short-term memory (LSTM) models using a weighted decision fusion strategy. Each component contributes complementary capabilities, including nonlinear feature learning, efficient outlier detection, and temporal pattern modeling. The framework is evaluated on the botnet of things (BoT-IoT) dataset and further validated using IoT-23. Experimental results show that the proposed hybrid approach achieves a precision of 0.999, recall of 0.970, and an F1-score of 0.985, while maintaining a false-negative rate below 0.001%. Although its area under the curve (AUC) is slightly lower than that of a standalone light gradient boosting machine (LightGBM) baseline, the hybrid framework consistently reduces missed detections, making it well suited for reliable real-time IIoT security monitoring.
- Open Access
- 1 December 2025
- Published by KEAI Publishing in Cyber Security and Applications
- Vol. 3
Leveraging federated learning for DoS attack detection in IoT networks based on ensemble feature selection and deep learning models
- 1 December 2025
- Published by KEAI Publishing in Cyber Security and Applications
- Vol. 3
Open AccessLeveraging federated learning for DoS attack detection in IoT networks based on ensemble feature selection and deep learning models
- 14 November 2025
- Published by IGI Global Scientific Publishing
- p. 1-48
Machine Learning for Threat Detection and Intrusion Prevention
This chapter provides a comprehensive analysis of machine-learning-driven security for wireless communication networks, showing how adaptive models supplant static, rule-based defenses to counter sophisticated cyber threats. Motivated by escalating traffic volume and protocol heterogeneity, it explains key algorithms, architectural patterns, and training pipelines that enable real-time anomaly detection, autonomous intrusion response, and scalable protection across diverse topologies. Data challenges including labeling scarcity, class imbalance, and concept drift are reviewed alongside adversarial robustness, interpretability, and computational limits at the edge. Case studies demonstrate practical deployments of supervised, unsupervised, and reinforcement techniques, while ethical concerns such as privacy preservation and algorithmic bias are critically assessed. The chapter concludes by mapping open research directions that position machine learning as a pivotal enabler of intelligent, resilient wireless cybersecurity.
- 14 November 2025
- Published by IGI Global Scientific Publishing
- p. 1-48
Machine Learning for Threat Detection and Intrusion Prevention
This chapter provides a comprehensive analysis of machine-learning-driven security for wireless communication networks, showing how adaptive models supplant static, rule-based defenses to counter sophisticated cyber threats. Motivated by escalating traffic volume and protocol heterogeneity, it explains key algorithms, architectural patterns, and training pipelines that enable real-time anomaly detection, autonomous intrusion response, and scalable protection across diverse topologies. Data challenges including labeling scarcity, class imbalance, and concept drift are reviewed alongside adversarial robustness, interpretability, and computational limits at the edge. Case studies demonstrate practical deployments of supervised, unsupervised, and reinforcement techniques, while ethical concerns such as privacy preservation and algorithmic bias are critically assessed. The chapter concludes by mapping open research directions that position machine learning as a pivotal enabler of intelligent, resilient wireless cybersecurity.
- Open Access
- 1 September 2025
- Published by Ital Publication in HighTech and Innovation Journal
- Vol. 6 (3) , 770-792
Assessing AI-Driven Personalization in Smart Cities Using Hybrid Machine Learning and MCDM Approach
This study aims to assess AI-driven personalization strategies in smart cities, focusing on promoting digital inclusion across diverse urban populations. As artificial intelligence becomes increasingly central to urban service delivery, ensuring equitable and effective personalization is critical to preventing the amplification of digital inequality. To address this challenge, a hybrid evaluation framework is proposed, integrating Multi-Criteria Decision Making (MCDM) techniques, specifically Step-wise Weight Assessment Ratio Analysis (SWARA), Linguistic q-Rung Orthopair Fuzzy Numbers (Lq-ROFNs), and the Multi-Attributive Border Approximation Area Comparison (MABAC) with a Machine Learning (ML) classification model based on Random Forest. The framework is applied to stakeholder input from ten Indonesian smart cities, evaluating personalization readiness across five dimensions: accessibility, affordability, user engagement, privacy, and personalization effectiveness. The results indicate that accessibility and user engagement are the most influential criteria, while affordability and privacy are areas requiring strategic policy focus. The integrated model classifies cities by readiness level and identifies sensitivity patterns relevant to inclusive digital policy-making. The novelty of this research lies in its synthesis of MCDM and ML approaches to produce a transparent, scalable, and data-driven tool for evaluating AI personalization. This contributes to inclusive smart city development by aligning AI implementation with broader social equity objectives.
- 1 September 2025
- Published by Ital Publication in HighTech and Innovation Journal
- Vol. 6 (3) , 770-792
Open AccessAssessing AI-Driven Personalization in Smart Cities Using Hybrid Machine Learning and MCDM Approach
This study aims to assess AI-driven personalization strategies in smart cities, focusing on promoting digital inclusion across diverse urban populations. As artificial intelligence becomes increasingly central to urban service delivery, ensuring equitable and effective personalization is critical to preventing the amplification of digital inequality. To address this challenge, a hybrid evaluation framework is proposed, integrating Multi-Criteria Decision Making (MCDM) techniques, specifically Step-wise Weight Assessment Ratio Analysis (SWARA), Linguistic q-Rung Orthopair Fuzzy Numbers (Lq-ROFNs), and the Multi-Attributive Border Approximation Area Comparison (MABAC) with a Machine Learning (ML) classification model based on Random Forest. The framework is applied to stakeholder input from ten Indonesian smart cities, evaluating personalization readiness across five dimensions: accessibility, affordability, user engagement, privacy, and personalization effectiveness. The results indicate that accessibility and user engagement are the most influential criteria, while affordability and privacy are areas requiring strategic policy focus. The integrated model classifies cities by readiness level and identifies sensitivity patterns relevant to inclusive digital policy-making. The novelty of this research lies in its synthesis of MCDM and ML approaches to produce a transparent, scalable, and data-driven tool for evaluating AI personalization. This contributes to inclusive smart city development by aligning AI implementation with broader social equity objectives.
- Open Access
- 1 August 2025
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 14 (4) , 3033-3046
Machine learning for global trade analysis: a hybrid clustering approach using DBSCAN, elbow, and SOM
Global trade constitutes a highly complex and interdependent system influenced by diverse economic, geographic, and political factors. This study proposes a hybrid clustering framework that integrates density-based spatial clustering of applications with noise (DBSCAN), elbow, and self-organizing maps (SOM) methods to uncover latent structures in international trade patterns. Utilizing averaged trade data from 25 countries spanning the period from 2013 to 2023, the framework identifies distinct clusters based on export-import characteristics. The DBSCAN is employed to detect dense trade hubs and outlier behaviors, the elbow method determines the optimal number of clusters, and SOM facilitates the visualization of non-linear, high-dimensional trade relationships. The analysis reveals three prominent trade clusters: Global Trade Leaders, Emerging Trade Powers, and Niche Exporters, each reflecting varying degrees of trade diversification and dependency. These empirical findings align with established economic theories, including the Heckscher Ohlin model and dependency theory, and provide actionable insights for policymakers seeking to enhance trade competitiveness and regional integration strategies.
- 1 August 2025
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 14 (4) , 3033-3046
Open AccessMachine learning for global trade analysis: a hybrid clustering approach using DBSCAN, elbow, and SOM
Global trade constitutes a highly complex and interdependent system influenced by diverse economic, geographic, and political factors. This study proposes a hybrid clustering framework that integrates density-based spatial clustering of applications with noise (DBSCAN), elbow, and self-organizing maps (SOM) methods to uncover latent structures in international trade patterns. Utilizing averaged trade data from 25 countries spanning the period from 2013 to 2023, the framework identifies distinct clusters based on export-import characteristics. The DBSCAN is employed to detect dense trade hubs and outlier behaviors, the elbow method determines the optimal number of clusters, and SOM facilitates the visualization of non-linear, high-dimensional trade relationships. The analysis reveals three prominent trade clusters: Global Trade Leaders, Emerging Trade Powers, and Niche Exporters, each reflecting varying degrees of trade diversification and dependency. These empirical findings align with established economic theories, including the Heckscher Ohlin model and dependency theory, and provide actionable insights for policymakers seeking to enhance trade competitiveness and regional integration strategies.
- Open Access
- 16 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 91129-91160
A Review of Applicable Technologies, Routing Protocols, Requirements, and Architecture for Disaster Area Networks
The swift progress of various cutting-edge network topologies, especially Fifth-Generation Networks (5G), Sixth-Generation Networks (6G), Unmanned Aerial Vehicles (UAVs), and satellite technologies, presents a promising opportunity to guarantee reliable communication and offer consistent and secure emergency services in times of calamities. Fuelled by the rapid evolution of network architectures, this study provides a comprehensive overview of the emerging network topologies, technologies, routing protocols, and difficulties associated with disaster area networks (DANs). This investigation seeks to examine the integration of various DAN topologies, including aerial, terrestrial, and maritime networks, to enhance communication during a disaster. Subsequently, we assess numerous network performance metrics, such as delay, overhead, throughput, energy consumption, packet ratio, and security. The review is concluded by illuminating recent research trends and open issues in the domain of emergency communication. Ultimately, this review serves as a valuable resource for researchers, network engineers, and policymakers in the domain of DANs, offering a thorough basis for informed decision-making to streamline network deployments and preserve lives.
- 16 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 91129-91160
Open AccessA Review of Applicable Technologies, Routing Protocols, Requirements, and Architecture for Disaster Area Networks
The swift progress of various cutting-edge network topologies, especially Fifth-Generation Networks (5G), Sixth-Generation Networks (6G), Unmanned Aerial Vehicles (UAVs), and satellite technologies, presents a promising opportunity to guarantee reliable communication and offer consistent and secure emergency services in times of calamities. Fuelled by the rapid evolution of network architectures, this study provides a comprehensive overview of the emerging network topologies, technologies, routing protocols, and difficulties associated with disaster area networks (DANs). This investigation seeks to examine the integration of various DAN topologies, including aerial, terrestrial, and maritime networks, to enhance communication during a disaster. Subsequently, we assess numerous network performance metrics, such as delay, overhead, throughput, energy consumption, packet ratio, and security. The review is concluded by illuminating recent research trends and open issues in the domain of emergency communication. Ultimately, this review serves as a valuable resource for researchers, network engineers, and policymakers in the domain of DANs, offering a thorough basis for informed decision-making to streamline network deployments and preserve lives.