Godwin Okon Ansa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Godwin Okon Ansa has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Abdinasir Hirsi
Advanced Telecommunication Research Center, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia (UTHM), Parit Raja, Malaysia
3 shared publications Abdullahi Farah
Engineering Department, Somtel Telecommunication Company, Bosaso, Somalia
3 shared publications- Adeb Salh
Faculty of Information and Communication Technology, Universiti Tunku Abdul Rahman (UTAR), Kampar, Malaysia
3 shared publications - Lukman Audah
Advanced Telecommunication Research Center, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia (UTHM), Parit Raja, Malaysia
3 shared publications - Mohammed A. Alhartomi
Department of Electrical Engineering, University of Tabuk, Tabuk, Saudi Arabia
3 shared publications - Salman Ahmed
VLSI and Embedded Technology (VEST) Focus Group, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Parit Raja, Malaysia
3 shared publications
Latest Publications
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 23, 2507-2527
Hybrid CNN-LSTM Model for DDoS Detection and Mitigation in Software-Defined Networks
Software-Defined Networking (SDN) enhances programmability and control but remains highly vulnerable to distributed denial-of-service (DDoS) attacks. Existing solutions often adapt conventional methods without leveraging SDN’s native features or addressing real-time mitigation. This study introduces a novel hybrid deep learning framework for DDoS detection and mitigation in SDN, significantly advancing the state of the art. We develop a custom dataset in a Mininet–Ryu testbed that reflects realistic SDN traffic conditions, and employ a multistage feature selection pipeline to reduce redundancy and highlight the most discriminative flow attributes. A hybrid Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) model is then applied, capturing both spatial and temporal traffic patterns. The proposed system achieves 99.5% accuracy and a 97.7% F1-score, demonstrating a significant improvement over baseline ML and DL approaches. In addition, a lightweight and scalable mitigation module embedded in the SDN controller dynamically drops or reroutes malicious flows, enabling real-time, low-latency responsiveness. Experimental results across diverse topologies confirm the framework’s scalability and applicability in real-world SDN environments.
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 23, 2507-2527
Hybrid CNN-LSTM Model for DDoS Detection and Mitigation in Software-Defined Networks
Software-Defined Networking (SDN) enhances programmability and control but remains highly vulnerable to distributed denial-of-service (DDoS) attacks. Existing solutions often adapt conventional methods without leveraging SDN’s native features or addressing real-time mitigation. This study introduces a novel hybrid deep learning framework for DDoS detection and mitigation in SDN, significantly advancing the state of the art. We develop a custom dataset in a Mininet–Ryu testbed that reflects realistic SDN traffic conditions, and employ a multistage feature selection pipeline to reduce redundancy and highlight the most discriminative flow attributes. A hybrid Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) model is then applied, capturing both spatial and temporal traffic patterns. The proposed system achieves 99.5% accuracy and a 97.7% F1-score, demonstrating a significant improvement over baseline ML and DL approaches. In addition, a lightweight and scalable mitigation module embedded in the SDN controller dynamically drops or reroutes malicious flows, enabling real-time, low-latency responsiveness. Experimental results across diverse topologies confirm the framework’s scalability and applicability in real-world SDN environments.
- Open Access
- 27 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 112303-112323
HSF: A Hybrid SVM-RF Machine Learning Framework for Dual-Plane DDoS Detection and Mitigation in Software-Defined Networks
Software-defined networking (SDN) has revolutionized network management by centralizing control through software, thereby enabling dynamic traffic adjustments that are independent of the data plane. However, this innovation introduces significant security vulnerabilities because the existing solutions are largely adaptations of traditional methods and fail to address the unique challenges of SDN environments. To address this issue, this study proposes a machine-learning (ML)-based intrusion detection framework tailored specifically for SDN. In particular, the framework utilizes a hybrid model that combines a Support Vector Machine (SVM) and Random Forest (RF) classifiers (HSF), which significantly improves intrusion detection accuracy. Specifically, the proposed solution is structured as a three-layer protection mechanism. First, the Data Plane Monitoring layer examines features, such as packet count and byte count, to detect anomalies. Second, the Control Plane Monitoring layer evaluates attributes such as the source IP, destination IP, and protocols to identify suspicious activity. Finally, the Detection Layer leverages the hybrid ML approach to further strengthen detection capabilities and ensure timely responses. Importantly, the experimental results reveal that the HSF technique achieves an anomaly detection rate exceeding 99% across both data and control planes. This highlights its efficacy in securing the next-generation SDN networks.
- 27 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 112303-112323
Open AccessHSF: A Hybrid SVM-RF Machine Learning Framework for Dual-Plane DDoS Detection and Mitigation in Software-Defined Networks
Software-defined networking (SDN) has revolutionized network management by centralizing control through software, thereby enabling dynamic traffic adjustments that are independent of the data plane. However, this innovation introduces significant security vulnerabilities because the existing solutions are largely adaptations of traditional methods and fail to address the unique challenges of SDN environments. To address this issue, this study proposes a machine-learning (ML)-based intrusion detection framework tailored specifically for SDN. In particular, the framework utilizes a hybrid model that combines a Support Vector Machine (SVM) and Random Forest (RF) classifiers (HSF), which significantly improves intrusion detection accuracy. Specifically, the proposed solution is structured as a three-layer protection mechanism. First, the Data Plane Monitoring layer examines features, such as packet count and byte count, to detect anomalies. Second, the Control Plane Monitoring layer evaluates attributes such as the source IP, destination IP, and protocols to identify suspicious activity. Finally, the Detection Layer leverages the hybrid ML approach to further strengthen detection capabilities and ensure timely responses. Importantly, the experimental results reveal that the HSF technique achieves an anomaly detection rate exceeding 99% across both data and control planes. This highlights its efficacy in securing the next-generation SDN networks.
- Open Access
- 31 May 2025
- Published by Universitas Sains dan Teknologi Komputer in Journal of Technology Informatics and Engineering
- Vol. 4 (2) , 225-251
Contextual Framework for Remote Intelligent Monitoring and Detection System for Prediction of Pregnancy Complications
Maternal health disorders can cause complications and harmful incidents in women during pregnancy. To minimize risks, this research developed a platform powered by a supervised machine learning model (SMLM) to support remote intelligent monitoring and prediction of pregnancy complications caused by hypertensive disorder, gestational diabetes, and related indicators. The study used real-world datasets with six UCI Machine Learning Repository features to identify and predict Maternal Health Risk (MHR) factors. A Support Vector Machine (SVM) algorithm was applied to construct the classifier model, which was trained and evaluated using StratifiedKFold cross-validation (k=10). The model achieved 80% accuracy with a precision, recall, and F1-score of 77%. The outcome of this work is the P-Health mobile application, designed to record and track blood pressure, blood sugar, heart rate, body temperature, and weight, while predicting the risk level of pregnancy complications through inference from the integrated machine learning model. Developed with Kotlin and Android Studio, the application enables healthcare practitioners to remotely monitor patients’ vitals in real time. This innovation addresses the challenge of early detection of pregnancy complications and provides continuous monitoring and assessment. The findings suggest that P-Health can improve early detection and timely intervention, helping medical specialists minimize maternal health risks. The system also has the potential to raise public awareness of maternal health issues, thereby contributing to the prevention of complications during pregnancy.
- 31 May 2025
- Published by Universitas Sains dan Teknologi Komputer in Journal of Technology Informatics and Engineering
- Vol. 4 (2) , 225-251
Open AccessContextual Framework for Remote Intelligent Monitoring and Detection System for Prediction of Pregnancy Complications
Maternal health disorders can cause complications and harmful incidents in women during pregnancy. To minimize risks, this research developed a platform powered by a supervised machine learning model (SMLM) to support remote intelligent monitoring and prediction of pregnancy complications caused by hypertensive disorder, gestational diabetes, and related indicators. The study used real-world datasets with six UCI Machine Learning Repository features to identify and predict Maternal Health Risk (MHR) factors. A Support Vector Machine (SVM) algorithm was applied to construct the classifier model, which was trained and evaluated using StratifiedKFold cross-validation (k=10). The model achieved 80% accuracy with a precision, recall, and F1-score of 77%. The outcome of this work is the P-Health mobile application, designed to record and track blood pressure, blood sugar, heart rate, body temperature, and weight, while predicting the risk level of pregnancy complications through inference from the integrated machine learning model. Developed with Kotlin and Android Studio, the application enables healthcare practitioners to remotely monitor patients’ vitals in real time. This innovation addresses the challenge of early detection of pregnancy complications and provides continuous monitoring and assessment. The findings suggest that P-Health can improve early detection and timely intervention, helping medical specialists minimize maternal health risks. The system also has the potential to raise public awareness of maternal health issues, thereby contributing to the prevention of complications during pregnancy.
- Top Cited PapersOpen Access
- 29 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 23013-23071
Comprehensive Analysis of DDoS Anomaly Detection in Software-Defined Networks
Software-Defined Networking (SDN) offers significant advantages for modern networks, including flexibility, centralized control, and reduced dependency on vendor-specific hardware. However, these benefits introduce security vulnerabilities, particularly from Distributed Denial-of-Service (DDoS) attacks, which represent some of the most disruptive threats to SDN environments. A review of the literature shows that while various techniques have been proposed to counteract DDoS threats, many studies have focused on single detection methods, with only a few utilizing multiple approaches. This fragmented focus limits a comprehensive approach to addressing DDoS threats across the SDN layers. To bridge this gap, this paper presents the first comprehensive review of DDoS anomaly detection in SDN, examining over 165 primary research articles published between 2020 and 2024. A novel taxonomy of DDoS attacks is introduced, categorizing them by distinct characteristics, and mapping each attack type to relevant detection methods within specific SDN layers. The survey provides a layer-by-layer analysis of DDoS detection techniques, covering the application, control, and infrastructure layers, and offers a structured overview that clarifies the applicability and effectiveness of each method. The paper concludes by synthesizing key findings, identifying unresolved challenges, and outlining future research directions to advance DDoS detection mechanisms in SDN. This roadmap is designed to guide researchers in addressing security vulnerabilities and enhancing SDN resilience against evolving DDoS threats.
- 29 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 23013-23071
Top Cited PapersOpen AccessComprehensive Analysis of DDoS Anomaly Detection in Software-Defined Networks
Software-Defined Networking (SDN) offers significant advantages for modern networks, including flexibility, centralized control, and reduced dependency on vendor-specific hardware. However, these benefits introduce security vulnerabilities, particularly from Distributed Denial-of-Service (DDoS) attacks, which represent some of the most disruptive threats to SDN environments. A review of the literature shows that while various techniques have been proposed to counteract DDoS threats, many studies have focused on single detection methods, with only a few utilizing multiple approaches. This fragmented focus limits a comprehensive approach to addressing DDoS threats across the SDN layers. To bridge this gap, this paper presents the first comprehensive review of DDoS anomaly detection in SDN, examining over 165 primary research articles published between 2020 and 2024. A novel taxonomy of DDoS attacks is introduced, categorizing them by distinct characteristics, and mapping each attack type to relevant detection methods within specific SDN layers. The survey provides a layer-by-layer analysis of DDoS detection techniques, covering the application, control, and infrastructure layers, and offers a structured overview that clarifies the applicability and effectiveness of each method. The paper concludes by synthesizing key findings, identifying unresolved challenges, and outlining future research directions to advance DDoS detection mechanisms in SDN. This roadmap is designed to guide researchers in addressing security vulnerabilities and enhancing SDN resilience against evolving DDoS threats.