Amro Saleh

Dr. Amro Saleh

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2019
Verified
Conference Paper
Closed access
MDMohammad I. Daoud
Mohammad I. Daoud
Amro SalehAmro Saleh
Amro Saleh
IHIsmail Ismail Hababeh
Ismail Ismail Hababeh
RARami Alazrai
Rami Alazrai
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.

17 December 2024
Verified
Conference Paper
Closed access
HMHatem Mosa
Hatem Mosa
Amro SalehAmro Saleh
Amro Saleh
MAMouhammd Alkasassbeh
Mouhammd Alkasassbeh
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.

7 October 2025 in IEEE Access
Verified
Journal Article
Open access
Mohammad J. Abdel-RahmanMohammad J. Abdel-Rahman
Mohammad J. Abdel-Rahman
YAYasmeen Shaher Alslman
Yasmeen Shaher Alslman
DRDania Refai
Dania Refai
Amro SalehAmro Saleh
Amro Saleh
MLMalik A. Abu Loha
Malik A. Abu Loha
MHMohammad Yahya Hamed
Mohammad Yahya Hamed
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.

9 February 2026 in Wireless Networks
Verified
Journal Article
Closed access
PDF file
Amro SalehAmro Saleh
Amro Saleh
mouhammd alkasassbehmouhammd alkasassbeh
mouhammd alkasassbeh
Mohammad AlmseidinMohammad Almseidin
Mohammad Almseidin

13 December 2025 in Computation
Verified
Journal Article
Open access
PDF file
Ibrahim AljarahIbrahim Aljarah
Ibrahim Aljarah
Abdullah Issa AlzaqebahAbdullah Issa Alzaqebah
Abdullah Issa Alzaqebah
NANailah Al-Madi
Nailah Al-Madi
AAAla’ M. Al-Zoubi
Ala’ M. Al-Zoubi
Amro SalehAmro Saleh
Amro Saleh
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.

16 April 2025
Verified
Conference Paper
Closed access
Amro SalehAmro Saleh
Amro Saleh
HMHatem Mosa
Hatem Mosa
MAMouhammd Alkasassbeh
Mouhammd Alkasassbeh
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.