Amro Saleh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Amro Saleh has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
Hatem Mosa
Princess Sumaya University for Technology,Department of Computer Science,Amman,Jordan
3 shared publicationsMouhammd Alkasassbeh
Princess Sumaya University for Technology,Department of Computer Science,Amman,Jordan
2 shared publications- Nailah Al-Madi
Princess Sumaya University for Technology
2 shared publications Abdallah Qusef
Princess Sumaya University for Technology,King Hussein School of Computing Sciences,Department of Computer Science,Amman,Jordan
1 shared publication- Abdullah Alzaqebah
Department of Computer Science, The World Islamic Sciences and Education University, Amman 11947, Jordan
1 shared publication Abdullah Qusef
Princess Sumaya University for Technology, Jordan
1 shared publication
Latest Publications
- 9 February 2026
- Published by Springer Nature in Wireless Networks
- Vol. 32 (2) , 1113-1129
Iot botnet intrusion detection system using federated learning techniques
- 9 February 2026
- Published by Springer Nature in Wireless Networks
- Vol. 32 (2) , 1113-1129
Iot botnet intrusion detection system using federated learning techniques
- Open Access
- 13 December 2025
- Published by MDPI AG in Computation
- Vol. 13 (12) , 292
mDA: Evolutionary Machine Learning Algorithm for Feature Selection in Medical Domain
The rapid expansion of medical data, characterized by its complex high-dimensional attributes, presents numerous promising opportunities and substantial challenges in healthcare analytics. Adopting effective feature selection techniques is essential to take advantage of the potential of such data. This research presents a modified algorithm called (mDA), which is the hybrid algorithm between the Evolutionary Population Dynamics and the Dragonfly Algorithm. This method combines Evolutionary Population Dynamics’s strength with the Dragonfly Algorithm’s flexible capabilities, offering a robust evolutionary machine learning approach specifically designed for medical data analysis. By integrating the dynamic population modeling of Evolutionary Population Dynamics with the adaptive search techniques of Dragonfly Algorithm, the proposed mDA significantly improves accuracy, reduces the number of features, and obtains the minimum average of the fitness scores. Comparative experiments conducted on seven diverse medical datasets against other established algorithms confirm the superior performance of the proposed mDA, establishing it as a valuable approach in examining complex medical data.
- 13 December 2025
- Published by MDPI AG in Computation
- Vol. 13 (12) , 292
Open AccessmDA: Evolutionary Machine Learning Algorithm for Feature Selection in Medical Domain
The rapid expansion of medical data, characterized by its complex high-dimensional attributes, presents numerous promising opportunities and substantial challenges in healthcare analytics. Adopting effective feature selection techniques is essential to take advantage of the potential of such data. This research presents a modified algorithm called (mDA), which is the hybrid algorithm between the Evolutionary Population Dynamics and the Dragonfly Algorithm. This method combines Evolutionary Population Dynamics’s strength with the Dragonfly Algorithm’s flexible capabilities, offering a robust evolutionary machine learning approach specifically designed for medical data analysis. By integrating the dynamic population modeling of Evolutionary Population Dynamics with the adaptive search techniques of Dragonfly Algorithm, the proposed mDA significantly improves accuracy, reduces the number of features, and obtains the minimum average of the fitness scores. Comparative experiments conducted on seven diverse medical datasets against other established algorithms confirm the superior performance of the proposed mDA, establishing it as a valuable approach in examining complex medical data.
- 8 October 2025
- Published by Springer Nature
- p. 195-206
Breast Ultrasound Imaging Classification Using Federated Learning Techniques
- 8 October 2025
- Published by Springer Nature
- p. 195-206
Breast Ultrasound Imaging Classification Using Federated Learning Techniques
- Open Access
- 7 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 180953-180991
Mathematical Programming Through the Lens of LLMs: Systematic Evidence and Empirical Gaps
This paper investigates the capabilities of large language models (LLMs) in formulating and solving decision-making problems using mathematical programming. We first conduct a systematic review and meta-analysis of recent literature to assess how well LLMs understand, structure, and solve optimization problems across domains. The analysis is guided by critical review questions focusing on learning approaches, dataset designs, evaluation metrics, and prompting strategies. Our systematic evidence is complemented by targeted experiments designed to evaluate the performance of state-of-the-art LLMs in automatically generating optimization models for problems in computer networks. Using a newly constructed dataset, we apply three prompting strategies: Act-as-expert, chain-of-thought, and self-consistency, and evaluate the obtained outputs based on optimality gap, token-level F1 score, and compilation accuracy. Results show promising progress in LLMs’ ability to parse natural language and represent symbolic formulations, but also reveal key limitations in accuracy, scalability, and interpretability. These empirical gaps motivate several future research directions, including structured datasets, domain-specific fine-tuning, hybrid neuro-symbolic approaches, modular multi-agent architectures, and dynamic retrieval via chain-of-RAGs. This paper contributes a structured roadmap for advancing LLM capabilities in mathematical programming.
- 7 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 180953-180991
Open AccessMathematical Programming Through the Lens of LLMs: Systematic Evidence and Empirical Gaps
This paper investigates the capabilities of large language models (LLMs) in formulating and solving decision-making problems using mathematical programming. We first conduct a systematic review and meta-analysis of recent literature to assess how well LLMs understand, structure, and solve optimization problems across domains. The analysis is guided by critical review questions focusing on learning approaches, dataset designs, evaluation metrics, and prompting strategies. Our systematic evidence is complemented by targeted experiments designed to evaluate the performance of state-of-the-art LLMs in automatically generating optimization models for problems in computer networks. Using a newly constructed dataset, we apply three prompting strategies: Act-as-expert, chain-of-thought, and self-consistency, and evaluate the obtained outputs based on optimality gap, token-level F1 score, and compilation accuracy. Results show promising progress in LLMs’ ability to parse natural language and represent symbolic formulations, but also reveal key limitations in accuracy, scalability, and interpretability. These empirical gaps motivate several future research directions, including structured datasets, domain-specific fine-tuning, hybrid neuro-symbolic approaches, modular multi-agent architectures, and dynamic retrieval via chain-of-RAGs. This paper contributes a structured roadmap for advancing LLM capabilities in mathematical programming.
- 29 April 2025
- Published by IGI Global Scientific Publishing
- p. 263-288
Cloud-Based Software Architecture for Scalability and Resilience
Cloud-based software has gained popularity for its scalability, flexibility, and cost savings, but traditional software architectures are not directly applicable to these environments. Challenges such as performance, resiliency, and high availability must be addressed. This chapter proposes a hybrid cloud infrastructure-based approach to designing resilient software architectures. It incorporates new cloud-based services and demonstrates their applicability across various cloud platforms. The approach supports scalability, performance, and innovation in cloud software design while enabling digital transformation. A methodology for testing cloud software resilience is introduced, focusing on workload-based failure analysis and fault injection using internal and external tests. The chapter emphasizes the importance and benefits of integrating robust resilience design into software development.
- 29 April 2025
- Published by IGI Global Scientific Publishing
- p. 263-288
Cloud-Based Software Architecture for Scalability and Resilience
Cloud-based software has gained popularity for its scalability, flexibility, and cost savings, but traditional software architectures are not directly applicable to these environments. Challenges such as performance, resiliency, and high availability must be addressed. This chapter proposes a hybrid cloud infrastructure-based approach to designing resilient software architectures. It incorporates new cloud-based services and demonstrates their applicability across various cloud platforms. The approach supports scalability, performance, and innovation in cloud software design while enabling digital transformation. A methodology for testing cloud software resilience is introduced, focusing on workload-based failure analysis and fault injection using internal and external tests. The chapter emphasizes the importance and benefits of integrating robust resilience design into software development.
- 16 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 299-306
Streaming-Based Intrusion Detection with Big Data and Online Learning Algorithms
Effective intrusion detection systems are essential for protecting computer networks amid growing cyberattacks. Traditional batch training approaches for intrusion detection in real-time streaming systems often fall short in adapting to rapidly changing attack patterns. This paper proposes two innovative methods for intrusion detection in streaming data environments: (1) a Kafka-based big data analytics framework integrating distributed streaming with deep learning for high-throughput adaptability and accuracy, and (2) an online incremental learning approach using the Hoeffding Very Fast Decision Tree classifier (VFDT) to enable responsiveness through real-time model updates. Evaluated on real-world datasets, the Kafka method achieves 98.1% accuracy and scalability under fluctuating data loads, while the Hoeffding VFDT classifier attains a 98.45% F1-score with fully adaptive incremental learning, outperforming batch methods in both responsiveness and adaptability. Threats to validity and experimental analysis demonstrate that the synergy of these methods addresses critical non-functional requirements (adaptability, accuracy, responsiveness) for dynamic intrusion detection. Future work directions include broader deployment scenarios and latency optimization.
- 16 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 299-306
Streaming-Based Intrusion Detection with Big Data and Online Learning Algorithms
Effective intrusion detection systems are essential for protecting computer networks amid growing cyberattacks. Traditional batch training approaches for intrusion detection in real-time streaming systems often fall short in adapting to rapidly changing attack patterns. This paper proposes two innovative methods for intrusion detection in streaming data environments: (1) a Kafka-based big data analytics framework integrating distributed streaming with deep learning for high-throughput adaptability and accuracy, and (2) an online incremental learning approach using the Hoeffding Very Fast Decision Tree classifier (VFDT) to enable responsiveness through real-time model updates. Evaluated on real-world datasets, the Kafka method achieves 98.1% accuracy and scalability under fluctuating data loads, while the Hoeffding VFDT classifier attains a 98.45% F1-score with fully adaptive incremental learning, outperforming batch methods in both responsiveness and adaptability. Threats to validity and experimental analysis demonstrate that the synergy of these methods addresses critical non-functional requirements (adaptability, accuracy, responsiveness) for dynamic intrusion detection. Future work directions include broader deployment scenarios and latency optimization.
- 17 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 169-175
RPL Routing Attacks Detection for IoT Networks Using Machine Learning
Cyberattacks on Internet of Things (IoT) networks are escalating rapidly due to the widespread use of these networks and the lack of adequate security measures derived from inherent constraints, such as those related to power consumption. Consequently, considering their unique characteristics, a robust methodology is critical for detecting IoT attacks. Many IoT attacks target the RPL routing protocol designed for low-power and lossy networks. In this study, we propose and evaluate the effectiveness of the Random Forest classifier and KNN classifier in detecting four types of attacks: Hello flooding attack, version number attack, Blackhole attack, and decreased rank attack. The analysis utilizes a publicly available dataset containing over 160 million records. Experimental results demonstrate a 99% accuracy rate using the Random Forest algorithm and a 98% accuracy rate using the KNN algorithm.
- 17 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 169-175
RPL Routing Attacks Detection for IoT Networks Using Machine Learning
Cyberattacks on Internet of Things (IoT) networks are escalating rapidly due to the widespread use of these networks and the lack of adequate security measures derived from inherent constraints, such as those related to power consumption. Consequently, considering their unique characteristics, a robust methodology is critical for detecting IoT attacks. Many IoT attacks target the RPL routing protocol designed for low-power and lossy networks. In this study, we propose and evaluate the effectiveness of the Random Forest classifier and KNN classifier in detecting four types of attacks: Hello flooding attack, version number attack, Blackhole attack, and decreased rank attack. The analysis utilizes a publicly available dataset containing over 160 million records. Experimental results demonstrate a 99% accuracy rate using the Random Forest algorithm and a 98% accuracy rate using the KNN algorithm.
- 10 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Leveraging Blockchain for Ethical Sourcing and Sustainability in Supply Chains: A Systematic Review
Ethical sourcing and sustainability within supply chains are increasingly acknowledged as key components of modern procurement methodologies. This systematic literature review thoroughly evaluates the current scholarly dialogue regarding blockchain-based strategies that foster ethical sourcing and sustainability within supply chain management (SCM). This study methodically examines academic contributions from 2016 to 2024 to clarify significant trends, obstacles, and prospects related to deploying blockchain technology in enhancing ethical practices and sustainability within supply chains. The findings of this systematic literature review indicate that blockchain operates as a validation tool for organizations attempting to confirm compliance with ethical sourcing standards. Furthermore, the contribution of blockchain to the advancement of sustainability includes its ability to facilitate resource optimization and improve decision-making processes within remanufacturing activities, thereby reinforcing the principles of a circular economy. This study identifies the lack of a practical blockchain framework to be integrated within supply chain management in different industries. It also emphasizes the necessity for empirical research to assess blockchain’s utility in supply chains. This paper reviews blockchain applications in various industries, such as food, Agri-food, and financial flows of humanitarian supply for the enhancement of ethical sourcing, sustainability, and transparency. Major trends, challenges, and future directions are deliberated upon in the adoption of blockchains for sustainable supply chains. Researchers should undertake case studies across various sectors to analyze blockchain’s scalability and its effects on ethical sourcing and sustainability. The exploration of regulatory frameworks to support blockchain adoption in compliance-heavy industries is imperative.
- 10 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Leveraging Blockchain for Ethical Sourcing and Sustainability in Supply Chains: A Systematic Review
Ethical sourcing and sustainability within supply chains are increasingly acknowledged as key components of modern procurement methodologies. This systematic literature review thoroughly evaluates the current scholarly dialogue regarding blockchain-based strategies that foster ethical sourcing and sustainability within supply chain management (SCM). This study methodically examines academic contributions from 2016 to 2024 to clarify significant trends, obstacles, and prospects related to deploying blockchain technology in enhancing ethical practices and sustainability within supply chains. The findings of this systematic literature review indicate that blockchain operates as a validation tool for organizations attempting to confirm compliance with ethical sourcing standards. Furthermore, the contribution of blockchain to the advancement of sustainability includes its ability to facilitate resource optimization and improve decision-making processes within remanufacturing activities, thereby reinforcing the principles of a circular economy. This study identifies the lack of a practical blockchain framework to be integrated within supply chain management in different industries. It also emphasizes the necessity for empirical research to assess blockchain’s utility in supply chains. This paper reviews blockchain applications in various industries, such as food, Agri-food, and financial flows of humanitarian supply for the enhancement of ethical sourcing, sustainability, and transparency. Major trends, challenges, and future directions are deliberated upon in the adoption of blockchains for sustainable supply chains. Researchers should undertake case studies across various sectors to analyze blockchain’s scalability and its effects on ethical sourcing and sustainability. The exploration of regulatory frameworks to support blockchain adoption in compliance-heavy industries is imperative.
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Content-based Image Retrieval for Breast Ultrasound Images using Convolutional Autoencoders: A Feasibility Study
Ultrasound imaging is one of the most widely used medical imaging modalities for detecting breast cancer. However, the accuracy of diagnosing the tumors in breast ultrasound (BUS) images might vary based on the experience level of the radiologist. Content-based image retrieval (CBIR) systems can be employed to improve the diagnosis accuracy by providing the radiologist with BUS images of previous, clinically relevant cases. In this study, a CBIR system is developed based on deep learning technology to support the diagnosis of BUS images. In particular, each query BUS image submitted to the system is analyzed using a custom-made convolutional autoencoder (CAE) to extract a latent features vector that represents the image. An important advantage of the proposed CAE is its ability to extract the latent features vector without the need to localize or outline the tumor. The latent features vector of the query image is analyzed using a similarity measure to identify and retrieve the most relevant BUS images from a reference BUS image database. Finally, the retrieved BUS images are displayed to the radiologist. The performance of the proposed CBIR system has been evaluated using a set of BUS images that includes benign and malignant breast tumors. The results reported in this study suggest the feasibility of employing the proposed CBIR system to improve the diagnosis of BUS images.
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Content-based Image Retrieval for Breast Ultrasound Images using Convolutional Autoencoders: A Feasibility Study
Ultrasound imaging is one of the most widely used medical imaging modalities for detecting breast cancer. However, the accuracy of diagnosing the tumors in breast ultrasound (BUS) images might vary based on the experience level of the radiologist. Content-based image retrieval (CBIR) systems can be employed to improve the diagnosis accuracy by providing the radiologist with BUS images of previous, clinically relevant cases. In this study, a CBIR system is developed based on deep learning technology to support the diagnosis of BUS images. In particular, each query BUS image submitted to the system is analyzed using a custom-made convolutional autoencoder (CAE) to extract a latent features vector that represents the image. An important advantage of the proposed CAE is its ability to extract the latent features vector without the need to localize or outline the tumor. The latent features vector of the query image is analyzed using a similarity measure to identify and retrieve the most relevant BUS images from a reference BUS image database. Finally, the retrieved BUS images are displayed to the radiologist. The performance of the proposed CBIR system has been evaluated using a set of BUS images that includes benign and malignant breast tumors. The results reported in this study suggest the feasibility of employing the proposed CBIR system to improve the diagnosis of BUS images.