AI-Assisted Diagnosis of Neonatal Ear Anomalies Using ResNet50 CBAM and CNN Transformer Models Syed Mohsin Bokhari, Muhammad Shafi, Fazal Noor, Abdullah Alshinqiti, Saad Alqahtany, Tazar Hussain IEEE Access, 2026 Early detection of congenital auricular deformity in infants is essential for early medical intervention, as late diagnosis would have long term psychosocial impacts and facial asymmetry. This study introduces two deep learning based architectures for the automated classification of auricular deformities: a hybrid Convolutional Neural Network Transformer (CNNT) and a new ResNet50 with a Convolutional Block Attention Module (ResNet50 CBAM). The novel ResNet50 CBAM architecture efficiently facilitates spatial and channel wise feature learning using attention mechanisms, allowing the model to focus on deformity specific regions while eliminating irrelevant background noise. Comprehensive experiments were conducted on BabyEar4k, an expert annotated, publicly released dataset containing 3,852 high resolution ear images across five clinically relevant classes of deformities. To substantiate the effectiveness of the proposed approach, a comparison was drawn with the current state-of-the-art scheme proposed by Liu Jie Ren et al., showing significant strides in classification performance. The ResNet50 CBAM model achieved a classification accuracy of 96.25%, an F1 score of 0.9576, and an AUC-ROC of 0.984, outperforming the CNNT model, which reached an accuracy of 93.97% and an F1 score of 0.9395, as well as the benchmark baseline F1 score of 0.832. These results highlight the robustness of the model and its generalization capability across classes of deformity. The proposed framework addresses some crucial shortcomings of previous works, including reliance on binary classification, insufficient subtype granularity, and inadequate preprocessing. Employing BM3D-based denoising and SMOTE-based class balancing enhances the quality and learning efficiency. In all, the methodology presents a straightforward, accurate, and scalable approach to AI-based neonatal ear deformity screening, offering substantial potential for wide integration into clinical decision-support systems to facilitate early intervention, decrease professional workload, and improve overall pediatric outcomes.
Exploring computationally efficient signcryption mechanisms for unmanned aerial vehicles (UAVs): a comparative review Muhammad Asghar Khan, Gordana Barb, Fazal Noor Iran Journal of Computer Science, 2025 Abstract Unmanned aerial vehicles (UAVs), also known as drones, have become increasingly important in modern times due to their ability to perform a wide range of tasks in both civilian and military sectors. However, the resource-constrained nature of UAVs, along with the need for secure data transmission, poses considerable challenges for cryptographic implementations. To address these challenges, lightweight cryptographic solutions have been proposed over the last several years to meet the unique demands of UAV networks. One such solution is called signcryption, which combines encryption and digital signatures into a single step, offering the most suitable cryptographic solution for UAV security. This comparative review article analyzes the most up-to-date signcryption mechanisms, particularly those proposed for UAVs, by comparing their various cryptographic methods and identifying the most suitable one. With this article, we also aim to explore the key security requirements and challenges that a typical UAV usually experiences. The key findings are then presented, and potential research directions are identified.
Implementation and performance of post-quantum cryptography for resource constrained consumer electronics Muhammad Asghar Khan, Fazal Noor, Shumaila Javaid, Justyna Żywiołek Discover Internet of Things, 2025 The proliferation of consumer electronics (CE), from smartphones to IoT-enabled smart devices, has significantly transformed our everyday lives, enhancing convenience and connectivity. However, these transformations to modern life have introduced security vulnerabilities, particularly as traditional cryptographic algorithms face mounting challenges from quantum computing technology. Post-quantum cryptography (PQC) has emerged as a promising solution for providing future-proof security for next-generation CE against the quantum computing threat. PQC algorithms are developed to resist cyberattacks from both classical and quantum computers, ensuring long-term security solutions. This article explores the integration of PQC into next-generation CE devices to ensure confidentiality, integrity, and user privacy. It highlights the vulnerabilities of classical cryptographic methods and underscores the need for transitioning to quantum-resistant solutions. Moreover, the practical implementation of PQC in resource-constrained CE devices is analyzed. Our evaluation shows that optimized PQC incurs negligible overhead on servers (5%), can be up to 12× slower on CE devices, and reduces communication overhead below conventional ECC (1 KB vs. 2.1 KB), while achieving hardware throughput thousands of times higher than RSA. By proactively exploring the opportunities and challenges associated with PQC, this research outlines future directions for implementing robust, scalable, and secure systems, thereby ensuring consumer trust in the evolving technological landscape.
Assessing ECG Interpretation Expertise in Medical Practitioners Through Eye Movement Data and Neuromorphic Models Syed Mohsin Bokhari, Muhammad Shafi, Fazal Noor, Sarmad Sohaib, Saad Alqahtany, Mark Donnelly IEEE Access, 2025 This study introduces an innovative method for assessing ECG interpretation abilities in medical professionals via eye-tracking data. We examine eye movement patterns from five separate groups of cardiology practitioners utilizing a combination of neuromorphic computing models, including Spiking Neural Networks (SNN), Spiking Convolutional Neural Networks (SCNN), Recurrent Spiking Neural Networks (RSNN), and Spiking Convolutional Long Short-Term Memory (SCLSTM). Utilizing eye movement data, we analyze the skill levels of practitioners in diverse medical positions, including consultants, nurses, and technicians, during ECG evaluations. Our proposed work combines spiking neuron activations with convolutional and recurrent architectures to analyze spatial and temporal gaze patterns that reflect clinical expertise. The suggested SNN, SCNN, RSNN, and SCLSTM models attained accuracies of 84.35%, 93.04%, 94.68%, 99.76% respectively, exceeding standard machine learning approaches in both precision and recall for identifying expertise levels based on visual attention patterns. This paradigm has the potential to construct skill evaluation tools in medical education, specifically for ECG interpretation training, thereby addressing prevalent difficulties related to inconsistent ECG diagnosis methods.
Optimizing Federated Learning With Aggregation Strategies: A Comprehensive Survey Naeem Khan, Shibli Nisar, Muhammad Asghar Khan, Yasar Abbas Ur Rehman, Fazal Noor, et al. IEEE Open Journal of the Computer Society, 2025 This article provides a comprehensive survey of aggregation strategies in federated learning (FL). This decentralized machine learning (ML) paradigm enables multiple clients to collaboratively train models without sharing their local datasets. Aggregation is a pivotal aspect of FL, as it integrates model updates from diverse clients into a unified global model while addressing critical challenges such as data heterogeneity, scalability, and privacy preservation. The study categorizes aggregation strategies into three primary approaches: data-centric, model-centric, and secure aggregation, each tailored to address distinct problems in FL systems. Data-centric strategies focus on addressing non-independent and identically distributed (non-IID) data across clients, ensuring that model updates account for imbalances in data distributions. Model-centric strategies optimize the aggregation of model parameters, emphasizing techniques such as weighted averaging and model distillation to improve model performance across clients with diverse data characteristics. Secure aggregation techniques aim to enhance privacy and robustness, protecting client data from potential adversarial threats through encryption-based methods like secure multi-party computation (SMPC) and Byzantine-resilient techniques. The analysis delves into the advantages and limitations of these aggregation strategies, particularly their role in tackling challenges like non-IID data, communication efficiency, and resistance to adversarial attacks. Furthermore, the article identifies existing research gaps in FL, including the need for more scalable and robust aggregation methods capable of reducing communication costs, enhancing privacy guarantees, and improving performance in highly heterogeneous environments. These insights provide a roadmap for future research aimed at advancing aggregation strategies in FL to improve model accuracy, security, and efficiency in real-world applications.
Security and Privacy Issues and Solutions for UAVs in B5G Networks: A Review Muhammad Asghar Khan, Neeraj Kumar, Saeed Hamood Alsamhi, Gordana Barb, Justyna Zywiołek, Insaf Ullah, Fazal Noor, Jawad Ali Shah, Abdullah M. Almuhaideb IEEE Transactions on Network and Service Management, 2025 Unmanned aerial vehicles (UAVs) in beyond 5G (B5G) are crucial for revolutionizing various industries, including surveillance, agriculture, and logistics, by enabling high-speed data transfer, ultra-low latency communication, and ultra-reliable connectivity. However, integrating UAVs into B5G networks poses various security and privacy concerns. These risks encompass the possibility of unauthorized access, breaches of data, and cyber-physical attacks which jeopardize the integrity, confidentiality, and availability of UAV operations. Moreover, UAVs in B5G networks are also at high risk from the application of machine learning (ML)-based attacks by exploiting vulnerabilities in ML models, leading to adversarial manipulation, data poisoning and model evasion techniques, which can compromise the integrity of UAV operations, lead to navigation errors, and expose sensitive data collected by UAVs. Considering the aforementioned security and privacy concerns, this review article presents emerging security and privacy solutions for UAVs in B5G networks. Firstly, We introduce the essential background of integrating UAVs into B5G networks and discuss the advantages and security challenges which the emerging integrated network architecture have. Then, we proceed to analyze and examine the security and privacy landscape by including threats and requirements of UAVs in B5G networks. Based on these threats and requirements, solutions from physical layer security (PLS), blockchain (BC), federated learning (FL) and post-quantum cryptography (PQC) are discussed and explored in details. Moreover, potential future research directions are discussed in details as open research issues.
A Certificate-Based Ring Signcryption Scheme for Securing UAV-Enabled Private Edge Computing Systems Muhammad Asghar Khan, Insaf Ullah, Neeraj Kumar, Fatemeh Afghah, Gordana Barb, Fazal Noor, Saad Alqahtany IEEE Access, 2024 The evolving paradigm of private edge computing seamlessly incorporates the more extensive functionalities of cloud computing with localized processing. This paradigm eliminates the requirement for unmanned aerial vehicles (UAVs) to transmit large volumes of data to a centralized cloud, thereby reducing response times. UAVs’ dynamic nature and dependency on unsecured and publicly accessible wireless channels make secure communication between a private edge cloud and a UAV difficult. Therefore, private edge computing-enabled UAV networks require additional security measures to protect the network and users’ data. This research article introduces a certificate-based ring signcryption scheme that mitigates security concerns by utilizing the concept of hyperelliptic curve cryptography (HECC). By combining digital signature and encryption into a single operation, the proposed method takes advantage of the most advantageous characteristic of HECC (the ability to use a short key, such as 80 bits) while maintaining the same level of security as RSA and ECC. The security properties of the proposed scheme are validated by implementing a formal security evaluation method known as the random oracle model (ROM), in addition to informal security analysis. Furthermore, the computation and communication costs of the proposed scheme are evaluated and compared to those of relevant existing schemes. The performance and security analysis demonstrate that the proposed scheme enhances efficiency and security.
An Efficient and Secure Certificateless Aggregate Signature Scheme for Vehicular Ad hoc Networks Asad Iqbal, Muhammad Zubair, Muhammad Asghar Khan, Insaf Ullah, Ghani Ur-Rehman, Alexey V. Shvetsov, Fazal Noor Future Internet, 2023 Vehicular ad hoc networks (VANETs) have become an essential part of the intelligent transportation system because they provide secure communication among vehicles, enhance vehicle safety, and improve the driving experience. However, due to the openness and vulnerability of wireless networks, the participating vehicles in a VANET system are prone to a variety of cyberattacks. To secure the privacy of vehicles and assure the authenticity, integrity, and nonrepudiation of messages, numerous signature schemes have been employed in the literature on VANETs. The majority of these solutions, however, are either not fully secured or entail high computational costs. To address the above issues and to enable secure communication between the vehicle and the roadside unit (RSU), we propose a certificateless aggregate signature (CLAS) scheme based on hyperelliptic curve cryptography (HECC). This scheme enables participating vehicles to share their identities with trusted authorities via an open wireless channel without revealing their identities to unauthorized participants. Another advantage of this approach is its capacity to release the partial private key to participating devices via an open wireless channel while keeping its identity secret from any other third parties. A provable security analysis through the random oracle model (ROM), which relies on the hyperelliptic curve discrete logarithm problem, is performed, and we have proven that the proposed scheme is unforgeable against Type 1 (FGR1) and Type 2 (FGR2) forgers. The proposed scheme is compared with relevant schemes in terms of computational cost and communication overhead, and the results demonstrate that the proposed scheme is more efficient than the existing schemes in maintaining high-security levels.
A Novel Monopole Ultra-Wide-Band Multiple-Input Multiple-Output Antenna with Triple-Notched Characteristics for Enhanced Wireless Communication and Portable Systems Shahid Basir, Ubaid Ur Rahman Qureshi, Fazal Subhan, Muhammad Asghar Khan, Syed Agha Hassnain Mohsan, Yazeed Yasin Ghadi, Khmaies Ouahada, Habib Hamam, Fazal Noor Sensors, 2023 This study introduces a monopole 4 × 4 Ultra-Wide-Band (UWB) Multiple-Input Multiple-Output (MIMO) antenna system with a novel structure and outstanding performance. The proposed design has triple-notched characteristics due to CSRR etching and a C-shaped curve. The notching occurs in 4.5 GHz, 5.5 GHz, and 8.8 GHz frequencies in the C-band, WLAN band, and satellite network, respectively. Complementary Split-Ring Resonators (CSRR) are etched at the feed line and ground plane, and a C-shaped curve is used to reduce interference between the ultra-wide band and narrowband. The mutual coupling of CSRR enables the MIMO architecture to achieve high isolation and polarisation diversity. With prototype dimensions of (60.4 × 60.4) mm2, the proposed antenna design is small. The simulated and measured results show good agreement, indicating the effectiveness of the UWB-MIMO antenna for wireless communication and portable systems.
Crop Yield Maximization Using an IoT-Based Smart Decision Amna Ikram, Waqar Aslam, Roza Hikmat Hama Aziz, Fazal Noor, Ghulam Ali Mallah, Sunnia Ikram, Muhammad Saeed Ahmad, Ako Muhammad Abdullah, Insaf Ullah Journal of Sensors, 2022
Building Energy Management System Based on Microcontrollers Fazal Noor, Atiqur Rahman, Yazed Alsaawy, Mohammed Husain Lecture Notes of the Institute for Computer Sciences Social Informatics and Telecommunications Engineering Lnicst, 2019
A Method to Detect Object's Width with Ultrasonic Sensor Fazal Noor, Mohammed Swaied, Moath AlMesned, Nasser AlMuzini Proceedings 2018 International Conference on Computing Electronics and Communications Engineering Iccece 2018, 2018
Fingerprint verification using cloud services with message passing interface over PC clusters Ap2ps 2012 4th International Conference on Advances in P2p Systems, 2012
AI Assisted Diagnosis of Neonatal Ear Deformities Using ResNet50 CBAM and CNN Transformer Models SM Bokhari, M Shafi, F Noor, A Alshinqiti, S Alqahtany, T Hussain IEEE Access , 2026 2026
Implementation and performance of post-quantum cryptography for resource constrained consumer electronics MA Khan, F Noor, S Javaid, J Żywiołek Discover Internet of Things 5 (1), 139 , 2025 2025 Citations: 6
Exploring computationally efficient signcryption mechanisms for unmanned aerial vehicles (UAVs): a comparative review MA Khan, G Barb, F Noor Iran Journal of Computer Science, 1-19 , 2025 2025 Citations: 2
Optimizing federated learning with aggregation strategies: A comprehensive survey N Khan, S Nisar, MA Khan, YAU Rehman, F Noor, G Barb IEEE Open Journal of the Computer Society , 2025 2025 Citations: 19
in Recognition of Sign Language SK Taha, A Alshanqiti, F Noor, W Nawaz, TA Syed Emerging Technologies in Computing: 7th EAI International Conference, iCETiC … , 2025 2025
Assessing ECG interpretation expertise in medical practitioners through eye movement data and neuromorphic models SM Bokhari, M Shafi, F Noor, S Sohaib, S Alqahtany, M Donnelly IEEE Access 13, 9430-9449 , 2025 2025 Citations: 6
Implementation of Deep Neural Nets on Microcontrollers for Speech Recognition F Noor, HM El-Boghdadi International Journal of Computer Science & Network Security, 65-74 , 2025 2025
Security and privacy issues and solutions for UAVs in B5G networks: A review MA Khan, N Kumar, SH Alsamhi, G Barb, J Zywiołek, I Ullah, F Noor, ... IEEE Transactions on Network and Service Management 22 (1), 892-912 , 2024 2024 Citations: 52
Performance of Deep Neural Networks in Recognition of Sign Language SK Taha, A Alshanqiti, F Noor, W Nawaz, TA Syed International Conference for Emerging Technologies in Computing, 125-139 , 2024 2024 Citations: 1
A certificate-based ring signcryption scheme for securing UAV-enabled private edge computing systems MA Khan, I Ullah, N Kumar, F Afghah, G Barb, F Noor, S Alqahtany IEEE Access 12, 83466-83479 , 2024 2024 Citations: 9
An efficient and secure certificateless aggregate signature scheme for vehicular ad hoc networks A Iqbal, M Zubair, MA Khan, I Ullah, G Ur-Rehman, AV Shvetsov, F Noor Future Internet 15 (8), 266 , 2023 2023 Citations: 16
A novel monopole ultra-wide-band multiple-input multiple-output antenna with triple-notched characteristics for enhanced wireless communication and portable systems S Basir, UUR Qureshi, F Subhan, MA Khan, SAH Mohsan, YY Ghadi, ... Sensors 23 (15), 6985 , 2023 2023 Citations: 9
Enabling secure communication in wireless body area networks with heterogeneous authentication scheme I Ullah, MA Khan, AM Abdullah, F Noor, N Innab, CM Chen Sensors 23 (3), 1121 , 2023 2023 Citations: 23
An efficient and conditional privacy-preserving heterogeneous signcryption scheme for the Internet of drones MA Khan, I Ullah, AM Abdullah, SAH Mohsan, F Noor Sensors 23 (3), 1063 , 2023 2023 Citations: 13
Dataset of large gathering images for person identification and tracking A Nadeem, A Mehmood, K Rizwan, M Ashraf, N Qadeer, A Alzahrani, ... CMC Comput. Mater. Continua 74 (3), 6065-6080 , 2023 2023 Citations: 2
A conditional privacy preserving generalized ring signcryption scheme for micro aerial vehicles I Ullah, MA Khan, AM Abdullah, SAH Mohsan, F Noor, F Algarni, N Innab Micromachines 13 (11), 1926 , 2022 2022 Citations: 9
A conditional privacy preserving heterogeneous signcryption scheme for Internet of Vehicles I Ullah, MA Khan, N Kumar, AM Abdullah, AA AlSanad, F Noor IEEE Transactions on Vehicular Technology 72 (3), 3989-3998 , 2022 2022 Citations: 35
A privacy-preserved internet-of-medical-things scheme for eradication and control of dengue using UAV A Ali, S Nisar, MA Khan, SAH Mohsan, F Noor, H Mostafa, M Marey Micromachines 13 (10), 1702 , 2022 2022 Citations: 19
Certificate-based signcryption scheme for securing wireless communication in industrial Internet of Things I Ullah, A Alomari, AM Abdullah, N Kumar, A Alsirhani, F Noor, S Hussain, ... IEEE Access 10, 105182-105194 , 2022 2022 Citations: 19
A Malware Detection Scheme via Smart Memory Forensics for Windows Devices SR M R Naeem , M Khan , Ako MAbdullah , Fazal Noor , M I Khan, M Asghar Khan ... https://doi.org/10.1155/2022/9156514 , 2022 2022
MOST CITED SCHOLAR PUBLICATIONS
Towards the unmanned aerial vehicles (UAVs): A comprehensive review SAH Mohsan, MA Khan, F Noor, I Ullah, MH Alsharif Drones 6 (6), 147 , 2022 2022 Citations: 1166
Realizing an efficient IoMT-assisted patient diet recommendation system through machine learning model C Iwendi, S Khan, JH Anajemba, AK Bashir, F Noor IEEE access 8, 28462-28474 , 2020 2020 Citations: 298
A review on communications perspective of flying ad-hoc networks: key enabling wireless technologies, applications, challenges and open research topics F Noor, MA Khan, A Al-Zahrani, I Ullah, KA Al-Dhlan Drones 4 (4), 65 , 2020 2020 Citations: 143
An efficient and provably secure certificateless key-encapsulated signcryption scheme for flying ad-hoc network MA Khan, I Ullah, S Nisar, F Noor, IM Qureshi, FU Khanzada, NU Amin IEEe Access 8, 36807-36828 , 2020 2020 Citations: 90
Crop Yield Maximization Using an IoT-Based Smart Decision A Ikram, W Aslam, RHH Aziz, F Noor Journal of Sensors 2022 (2022923), 15 , 2022 2022 Citations: 88
An efficient and secure certificate-based access control and key agreement scheme for flying ad-hoc networks MA Khan, I Ullah, N Kumar, OS Oubbati, IM Qureshi, F Noor, ... IEEE Transactions on Vehicular Technology 70 (5), 4839-4851 , 2021 2021 Citations: 87
An efficient authentication scheme using blockchain as a certificate authority for the internet of drones S Javed, MA Khan, AM Abdullah, A Alsirhani, A Alomari, F Noor, I Ullah Drones 6 (10), 264 , 2022 2022 Citations: 67
Multiaccess edge computing empowered flying ad hoc networks with secure deployment using identity‐based generalized signcryption MA Khan, I Ullah, S Nisar, F Noor, IM Qureshi, F Khanzada, H Khattak, ... Mobile Information Systems 2020 (1), 8861947 , 2020 2020 Citations: 61
An Efficient and Provably Secure Certificateless Blind Signature Scheme for Flying Ad-Hoc Network Based on Multi-Access Edge Computing M. A. Khan, I.M. Qureshi, I Ullah, S. Khan, F. Khanzada, Fazal Noor Electronics 2020, Network 9 (1), 30 , 2019 2019 Citations: 53
Security and privacy issues and solutions for UAVs in B5G networks: A review MA Khan, N Kumar, SH Alsamhi, G Barb, J Zywiołek, I Ullah, F Noor, ... IEEE Transactions on Network and Service Management 22 (1), 892-912 , 2024 2024 Citations: 52
Towards the unmanned aerial vehicles (UAVs): A comprehensive review. Drones, 6 (6), 147 SAH Mohsan, MA Khan, F Noor, I Ullah, MH Alsharif 2022 Citations: 48
A conditional privacy preserving heterogeneous signcryption scheme for Internet of Vehicles I Ullah, MA Khan, N Kumar, AM Abdullah, AA AlSanad, F Noor IEEE Transactions on Vehicular Technology 72 (3), 3989-3998 , 2022 2022 Citations: 35
A Hermitian Toeplitz matrix is unitarily similar to a real Toeplitz-plus-Hankel matrix DM Wilkes, SD Morgera, F Noor, MH Hayes IEEE Transactions on signal processing 39 (9), 2146-2148 , 2002 2002 Citations: 31
March DSS: A new diagnostic march test for all memory simple static faults SM Al-Harbi, F Noor, FM Al-Turjman IEEE transactions on computer-aided design of integrated circuits and … , 2007 2007 Citations: 29
Recursive and iterative algorithms for computing eigenvalues of Hermitian Toeplitz matrices F Noor, SD Morgera IEEE transactions on signal processing 41 (3), 1272-1280 , 1993 1993 Citations: 29
Applications of modern high performance networks JA Zubairi Bentham Science Publishers , 2009 2009 Citations: 28
Securing wireless body area network with efficient secure channel free and anonymous certificateless signcryption F Noor, TA Kordy, AB Alkhodre, O Benrhouma, A Nadeem, A Alzahrani Wireless Communications and Mobile Computing 2021 (1), 5986469 , 2021 2021 Citations: 24
Enabling secure communication in wireless body area networks with heterogeneous authentication scheme I Ullah, MA Khan, AM Abdullah, F Noor, N Innab, CM Chen Sensors 23 (3), 1121 , 2023 2023 Citations: 23
Tracking missing person in large crowd gathering using intelligent video surveillance A Nadeem, M Ashraf, N Qadeer, K Rizwan, A Mehmood, A AlZahrani, ... Sensors 22 (14), 5270 , 2022 2022 Citations: 22
A malware detection scheme via smart memory forensics for windows devices MR Naeem, M Khan, AM Abdullah, F Noor, MI Khan, MA Khan, I Ullah, ... Mobile Information Systems 2022 (1), 9156514 , 2022 2022 Citations: 21
RESEARCH OUTPUTS (PATENTS, SOFTWARE, PUBLICATIONS, PRODUCTS)