Nadia Mohamed Sarhan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nadia Mohamed Sarhan has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Emad Mahrous Awwad
Electrical Engineering Department, College of Engineering, King Saud University, Riyadh 11421, Saudi Arabia
5 shared publications Ahmad Yahiya Ahmadad Bani Ahmad
Department of Accounting and Finance, Faculty of Business, Middle East University, Amman, Jordan
1 shared publication- Amit Arora
Electrical Engineering Department, Engineering College Bikaner, Rajasthan, India
1 shared publication - Amjad Iqbal
Faculty of Materials Engineering, Silesian University of Technology, Gliwice 44-100, Poland
1 shared publication - Dekai Li
School of Information and communication Engineering, Hainan University, Haikou, China
1 shared publication Efaza Ahmad
Department of Sciences and Humanities, National University of Computer and Emerging Sciences, Lahore, Pakistan
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 17 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 5853-5865
CSTFNet: A CNN and Dual Swin-Transformer Fusion Network for Remote Sensing Hyperspectral Data Fusion and Classification of Coastal Areas
Hyperspectral imaging (HSI) can capture a large amount of spectral information at various wavelengths, enabling detailed material classification and identification, making it a key tool in remote sensing, particularly for coastal area monitoring. In recent years, the CNN framework and transformer models have demonstrated strong performance in HSI classification, especially in applications requiring precise change detection and analysis. However, due to the high dimensionality of HSI data and the complexity of spectral-spatial feature extraction, achieving accurate results in coastal areas remains challenging. This paper introduces a new hybrid model, CSTFNet, which combines an improved CNN module and dual-layer Swin Transformer (DLST) to tackle these challenges. CSTFNet integrates spectral and spatial processing capabilities, significantly reducing computational complexity while maintaining high classification accuracy. The improved CNN module employs one-dimensional convolutions to handle high-dimensional data, while the DLST module uses window-based multi-head attention to capture both local and global dependencies. Experiments conducted on four standard HSI datasets (Houston-2013, Samson, KSC, and Botswana) demonstrate that CSTFNet outperforms traditional and state-of-the-art algorithms, achieving overall classification accuracy exceeding 99%. In particular, on the Houston-2013 dataset, the results for OA and AA are 1.00 and the kappa coefficient is 0. 976.The results highlight the robustness and efficiency of the proposed model in coastal area applications, where accurate and reliable spectral-spatial classification is crucial for monitoring and environmental management.
- 17 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 5853-5865
Top Cited PapersOpen AccessCSTFNet: A CNN and Dual Swin-Transformer Fusion Network for Remote Sensing Hyperspectral Data Fusion and Classification of Coastal Areas
Hyperspectral imaging (HSI) can capture a large amount of spectral information at various wavelengths, enabling detailed material classification and identification, making it a key tool in remote sensing, particularly for coastal area monitoring. In recent years, the CNN framework and transformer models have demonstrated strong performance in HSI classification, especially in applications requiring precise change detection and analysis. However, due to the high dimensionality of HSI data and the complexity of spectral-spatial feature extraction, achieving accurate results in coastal areas remains challenging. This paper introduces a new hybrid model, CSTFNet, which combines an improved CNN module and dual-layer Swin Transformer (DLST) to tackle these challenges. CSTFNet integrates spectral and spatial processing capabilities, significantly reducing computational complexity while maintaining high classification accuracy. The improved CNN module employs one-dimensional convolutions to handle high-dimensional data, while the DLST module uses window-based multi-head attention to capture both local and global dependencies. Experiments conducted on four standard HSI datasets (Houston-2013, Samson, KSC, and Botswana) demonstrate that CSTFNet outperforms traditional and state-of-the-art algorithms, achieving overall classification accuracy exceeding 99%. In particular, on the Houston-2013 dataset, the results for OA and AA are 1.00 and the kappa coefficient is 0. 976.The results highlight the robustness and efficiency of the proposed model in coastal area applications, where accurate and reliable spectral-spatial classification is crucial for monitoring and environmental management.
- Open Access
- 30 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 110331-110352
A Secure and Efficient BlockChain and Distributed Ledger Technology-Based Optimal Resource Management in Digital Twin Beyond 5G Networks Using Hybrid Energy Valley and Levy Flight Distributer Optimization Algorithm
This paper aims to establish a virtual object management system, as well as optimal task scheduling using the foundation of Digital Twins (DT), to improve the user's experience with management and to accomplish the task efficiently. On the other hand, offloading tasks using IoT gadgets to edge computing, fails to speed up control by users. The capabilities of the DT are provided by executing processes such as visualization, virtualization, synchronization, and simulation. The optimal selection of the virtual objects for the DT is done by utilizing the implemented Hybrid Energy Valley with Lévy Flight Distribution Optimization (HEV-LFDO) in order to optimally offload the task by the edge devices. The optimal selection of the virtual objects is done with the aid of the HEV-LFDO in the DT by considering the total cost of executing all tasks using the selected virtual objects and the decision variables to determine whether a virtual object is taken for executing a task or not as the constraint. The data for performing resource management is secured using the blockchain or distributed ledger technology. This accounts for the minimization of the local loss function. Finally, the secured data is considered for optimal resource management tasks. The optimal resource management is done using the same HEV-LFDO. This optimal resource management is carried out by considering the constraints like the cost of assigning a virtual object for the task to the edge device, and the cost of assigning the task to the edge device. These two costs are analyzed by taking the network's bandwidth, energy consumption, and computational resources into consideration. Experimental verifications are conducted on the executed optimal resource management scheme to prove the ability of the implemented model to be integrated with the edge computing network. The overall processing time as well as the latency are also minimized by executing the optimal resource management scheme.
- 30 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 110331-110352
Open AccessA Secure and Efficient BlockChain and Distributed Ledger Technology-Based Optimal Resource Management in Digital Twin Beyond 5G Networks Using Hybrid Energy Valley and Levy Flight Distributer Optimization Algorithm
This paper aims to establish a virtual object management system, as well as optimal task scheduling using the foundation of Digital Twins (DT), to improve the user's experience with management and to accomplish the task efficiently. On the other hand, offloading tasks using IoT gadgets to edge computing, fails to speed up control by users. The capabilities of the DT are provided by executing processes such as visualization, virtualization, synchronization, and simulation. The optimal selection of the virtual objects for the DT is done by utilizing the implemented Hybrid Energy Valley with Lévy Flight Distribution Optimization (HEV-LFDO) in order to optimally offload the task by the edge devices. The optimal selection of the virtual objects is done with the aid of the HEV-LFDO in the DT by considering the total cost of executing all tasks using the selected virtual objects and the decision variables to determine whether a virtual object is taken for executing a task or not as the constraint. The data for performing resource management is secured using the blockchain or distributed ledger technology. This accounts for the minimization of the local loss function. Finally, the secured data is considered for optimal resource management tasks. The optimal resource management is done using the same HEV-LFDO. This optimal resource management is carried out by considering the constraints like the cost of assigning a virtual object for the task to the edge device, and the cost of assigning the task to the edge device. These two costs are analyzed by taking the network's bandwidth, energy consumption, and computational resources into consideration. Experimental verifications are conducted on the executed optimal resource management scheme to prove the ability of the implemented model to be integrated with the edge computing network. The overall processing time as well as the latency are also minimized by executing the optimal resource management scheme.
- Top Cited PapersOpen Access
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 51752-51771
An IoT and Blockchain-Based Secure and Transparent Supply Chain Management Framework in Smart Cities Using Optimal Queue Model
The process of controlling the flow of products and services from a company by encompassing each stage involved in transforming raw materials and parts into finished items, also delivering them to the final consumer is known as Supply Chain Management (SCM). The development of numerous smart city applications including smart grids, smart homes, smart supply chains, and smart healthcare has drawn attention to the Internet of Things (IoT). Nowadays, researchers are considering the smart healthcare system’s role as a Public Emergency Service (PES) to treat patients promptly. A distributed smart fire brigade system receives little attention like PES to save lives and property from catastrophic fire damage. The conventional PES methods are created using a centralized method that needs a lot of processing power and doesn’t offer timely services. The traditional systems developed for managing the supply chain have drawbacks like single-point failure issues, data integrity, transparency, and lack of trust. To alleviate the existing issues, in this paper, a Blockchain and IoT Enable Secure and Transparent Supply Chain Management framework is utilized for PES in the smart city environment. Further, two edge computing servers, like a service controller and an IoT controller are adapted. The local storage is handled by the service and IoT controller. Thus, it enhances the data processing speed of PES requests and PES fulfillment. The service controller utilizes the Optimal Queue Model to manage the PES requests based on the minimum service queue length. The efficiency of the network is improved by fine-tuning the parameters from the Queue model with the aid of a Revised Fitness-based Political Optimizer (RF-PO). The multi-objective constraints like queue length, utilization, actual arrival time, expected arrival time, and end-to-end delay are utilized for the efficient supply chain system. These stimulated results show the feasibility and effectiveness of the supply chain framework.
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 51752-51771
Top Cited PapersOpen AccessAn IoT and Blockchain-Based Secure and Transparent Supply Chain Management Framework in Smart Cities Using Optimal Queue Model
The process of controlling the flow of products and services from a company by encompassing each stage involved in transforming raw materials and parts into finished items, also delivering them to the final consumer is known as Supply Chain Management (SCM). The development of numerous smart city applications including smart grids, smart homes, smart supply chains, and smart healthcare has drawn attention to the Internet of Things (IoT). Nowadays, researchers are considering the smart healthcare system’s role as a Public Emergency Service (PES) to treat patients promptly. A distributed smart fire brigade system receives little attention like PES to save lives and property from catastrophic fire damage. The conventional PES methods are created using a centralized method that needs a lot of processing power and doesn’t offer timely services. The traditional systems developed for managing the supply chain have drawbacks like single-point failure issues, data integrity, transparency, and lack of trust. To alleviate the existing issues, in this paper, a Blockchain and IoT Enable Secure and Transparent Supply Chain Management framework is utilized for PES in the smart city environment. Further, two edge computing servers, like a service controller and an IoT controller are adapted. The local storage is handled by the service and IoT controller. Thus, it enhances the data processing speed of PES requests and PES fulfillment. The service controller utilizes the Optimal Queue Model to manage the PES requests based on the minimum service queue length. The efficiency of the network is improved by fine-tuning the parameters from the Queue model with the aid of a Revised Fitness-based Political Optimizer (RF-PO). The multi-objective constraints like queue length, utilization, actual arrival time, expected arrival time, and end-to-end delay are utilized for the efficient supply chain system. These stimulated results show the feasibility and effectiveness of the supply chain framework.
- 9 February 2024
- Published by World Scientific Pub Co Pte Ltd in Fluctuation and Noise Letters
- Vol. 23 (02)
Enhancing Economic Stability with Innovative Crude Oil Price Prediction and Policy Uncertainty Mitigation in USD Energy Stock Markets
In today’s globalized economic landscape, the assurance of economic stability is of paramount importance, necessitating precise financial decision-making and policy formulation. This assurance is significantly augmented by innovative approaches to predicting crude oil prices, particularly in the context of energy stock markets denominated in USD. This paper delves into the transformative effect of accurate crude oil price prediction on economic policy stability. It underscores the challenges and limitations posed by policy uncertainties and emphasizes the pivotal role of innovative solutions in mitigating these challenges. Moreover, it recognizes the imperative need for secure data storage to facilitate the application of machine learning in this domain. Furthermore, effective management and regulation of power grid systems are explored as indispensable strategies for tempering the volatility introduced by fluctuations in energy stock markets. As we work to address these gaps in knowledge, the potential for sustainable power systems to supersede fossil fuels emerges as a driving force behind the maintenance of stable economic policies.
- 9 February 2024
- Published by World Scientific Pub Co Pte Ltd in Fluctuation and Noise Letters
- Vol. 23 (02)
Enhancing Economic Stability with Innovative Crude Oil Price Prediction and Policy Uncertainty Mitigation in USD Energy Stock Markets
In today’s globalized economic landscape, the assurance of economic stability is of paramount importance, necessitating precise financial decision-making and policy formulation. This assurance is significantly augmented by innovative approaches to predicting crude oil prices, particularly in the context of energy stock markets denominated in USD. This paper delves into the transformative effect of accurate crude oil price prediction on economic policy stability. It underscores the challenges and limitations posed by policy uncertainties and emphasizes the pivotal role of innovative solutions in mitigating these challenges. Moreover, it recognizes the imperative need for secure data storage to facilitate the application of machine learning in this domain. Furthermore, effective management and regulation of power grid systems are explored as indispensable strategies for tempering the volatility introduced by fluctuations in energy stock markets. As we work to address these gaps in knowledge, the potential for sustainable power systems to supersede fossil fuels emerges as a driving force behind the maintenance of stable economic policies.
- 1 January 2024
- Published by World Scientific Pub Co Pte Ltd in Fractals
- Vol. 32 (07n08)
DESIGN AND IMPLEMENTATION OF FUZZY-FRACTIONAL WU–ZHANG SYSTEM USING HE–MOHAND ALGORITHM
In recent years, fuzzy and fractional calculus are utilized for simulating complex models with uncertainty and memory effects. This study is focused on fuzzy-fractional modeling of (2+1)-dimensional Wu–Zhang (WZ) system. Caputo-type time-fractional derivative and triangular fuzzy numbers are employed in the model to observe uncertainties in the presence of non-local and memory effects. The extended He–Mohand algorithm is proposed for the solution and analysis of the current model. This approach is based on homotopy perturbation method along with Mohand transformation. Effectiveness of proposed methodology at upper and lower bounds is confirmed through residual errors. The theoretical convergence of proposed algorithm is proved alongside numerical computations. Existence and uniqueness of solution are also theoretically proved in the given paper. Current investigation considers three types of fuzzifications i.e. fuzzified equations, fuzzified conditions, and finally fuzzification in both model and conditions. Different physical aspects of WZ system profiles are analyzed through 2D and 3D illustrations at upper and lower bounds. The obtained results highlight the impact of uncertainty on WZ system in fuzzy-fractional space. Hence, the proposed methodology can be used for other fuzzy-fractional systems for better accuracy with lesser computational cost.
- 1 January 2024
- Published by World Scientific Pub Co Pte Ltd in Fractals
- Vol. 32 (07n08)
DESIGN AND IMPLEMENTATION OF FUZZY-FRACTIONAL WU–ZHANG SYSTEM USING HE–MOHAND ALGORITHM
In recent years, fuzzy and fractional calculus are utilized for simulating complex models with uncertainty and memory effects. This study is focused on fuzzy-fractional modeling of (2+1)-dimensional Wu–Zhang (WZ) system. Caputo-type time-fractional derivative and triangular fuzzy numbers are employed in the model to observe uncertainties in the presence of non-local and memory effects. The extended He–Mohand algorithm is proposed for the solution and analysis of the current model. This approach is based on homotopy perturbation method along with Mohand transformation. Effectiveness of proposed methodology at upper and lower bounds is confirmed through residual errors. The theoretical convergence of proposed algorithm is proved alongside numerical computations. Existence and uniqueness of solution are also theoretically proved in the given paper. Current investigation considers three types of fuzzifications i.e. fuzzified equations, fuzzified conditions, and finally fuzzification in both model and conditions. Different physical aspects of WZ system profiles are analyzed through 2D and 3D illustrations at upper and lower bounds. The obtained results highlight the impact of uncertainty on WZ system in fuzzy-fractional space. Hence, the proposed methodology can be used for other fuzzy-fractional systems for better accuracy with lesser computational cost.