Vehicle detection is still challenging for intelligent transportation systems(ITS)to achieve satisfactory performance.The existing methods based on one stage and two-stage have intrinsic weakness in obtaining high veh...Vehicle detection is still challenging for intelligent transportation systems(ITS)to achieve satisfactory performance.The existing methods based on one stage and two-stage have intrinsic weakness in obtaining high vehicle detection performance.Due to advancements in detection technology,deep learning-based methods for vehicle detection have become more popular because of their higher detection accuracy and speed than the existing algorithms.This paper presents a robust vehicle detection technique based on Improved You Look Only Once(RVD-YOLOv5)to enhance vehicle detection accuracy.The proposed method works in three phases;in the first phase,the K-means algorithm performs data clustering on datasets to generate the classes of the objects.Subsequently,in the second phase,the YOLOv5 is applied to create the bounding box,and the Non-Maximum Suppression(NMS)technique is used to eliminate the overlapping of the bounding boxes of the vehicle.Then,the loss function CIoU is employed to obtain the accurate regression bounding box of the vehicle in the third phase.The simulation results show that the proposed method achieves better results when compared with other state-of-art techniques,namely LightweightDilated Convolutional Neural Network(LD-CNN),Single Shot Detector(SSD),YOLOv3 and YOLOv4 on the performance metric like precision,recall,mAP and F1-Score.The simulation and analysis are carried out on PASCAL VOC 2007,2012 and MS COCO 2017 datasets to obtain better performance for vehicle detection.Finally,the RVD-YOLOv5 obtains the results with an mAP of 98.6%and Precision,Recall,and F1-Score are 98%,96.2%and 97.09%,respectively.展开更多
The coronavirus,formerly known as COVID-19,has caused massive global disasters.As a precaution,most governments imposed quarantine periods ranging from months to years and postponed significantfinancial obligations.Furt...The coronavirus,formerly known as COVID-19,has caused massive global disasters.As a precaution,most governments imposed quarantine periods ranging from months to years and postponed significantfinancial obligations.Furthermore,governments around the world have used cutting-edge technologies to track citizens’activity.Thousands of sensors were connected to IoT(Internet of Things)devices to monitor the catastrophic eruption with billions of connected devices that use these novel tools and apps,privacy and security issues regarding data transmission and memory space abound.In this study,we suggest a block-chain-based methodology for safeguarding data in the billions of devices and sen-sors connected over the internet.Various trial secrecy and safety qualities are based on cutting-edge cryptography.To evaluate the proposed model,we recom-mend using an application of the system,a Raspberry Pi single-board computer in an IoT system,a laptop,a computer,cell phones and the Ethereum smart contract platform.The models ability to ensure safety,effectiveness and a suitable budget is proved by the Gowalla dataset results.展开更多
Deep learning is the process of determining parameters that reduce the cost function derived from the dataset.The optimization in neural networks at the time is known as the optimal parameters.To solve optimization,it...Deep learning is the process of determining parameters that reduce the cost function derived from the dataset.The optimization in neural networks at the time is known as the optimal parameters.To solve optimization,it initialize the parameters during the optimization process.There should be no variation in the cost function parameters at the global minimum.The momentum technique is a parameters optimization approach;however,it has difficulties stopping the parameter when the cost function value fulfills the global minimum(non-stop problem).Moreover,existing approaches use techniques;the learning rate is reduced during the iteration period.These techniques are monotonically reducing at a steady rate over time;our goal is to make the learning rate parameters.We present a method for determining the best parameters that adjust the learning rate in response to the cost function value.As a result,after the cost function has been optimized,the process of the rate Schedule is complete.This approach is shown to ensure convergence to the optimal parameters.This indicates that our strategy minimizes the cost function(or effective learning).The momentum approach is used in the proposed method.To solve the Momentum approach non-stop problem,we use the cost function of the parameter in our proposed method.As a result,this learning technique reduces the quantity of the parameter due to the impact of the cost function parameter.To verify that the learning works to test the strategy,we employed proof of convergence and empirical tests using current methods and the results are obtained using Python.展开更多
Suspicious mass traffic constantly evolves,making network behaviour tracing and structure more complex.Neural networks yield promising results by considering a sufficient number of processing elements with strong inte...Suspicious mass traffic constantly evolves,making network behaviour tracing and structure more complex.Neural networks yield promising results by considering a sufficient number of processing elements with strong interconnections between them.They offer efficient computational Hopfield neural networks models and optimization constraints used by undergoing a good amount of parallelism to yield optimal results.Artificial neural network(ANN)offers optimal solutions in classifying and clustering the various reels of data,and the results obtained purely depend on identifying a problem.In this research work,the design of optimized applications is presented in an organized manner.In addition,this research work examines theoretical approaches to achieving optimized results using ANN.It mainly focuses on designing rules.The optimizing design approach of neural networks analyzes the internal process of the neural networks.Practices in developing the network are based on the interconnections among the hidden nodes and their learning parameters.The methodology is proven best for nonlinear resource allocation problems with a suitable design and complex issues.The ANN proposed here considers more or less 46k nodes hidden inside 49 million connections employed on full-fledged parallel processors.The proposed ANN offered optimal results in real-world application problems,and the results were obtained using MATLAB.展开更多
This paper proposes a stable gain and a compact Antipodal Vivaldi Antenna(AVA)for a 38GHz band of 5G communication.A novel compact AVA is designed to provide constant gain,high front to back ratio(FBR),and very high e...This paper proposes a stable gain and a compact Antipodal Vivaldi Antenna(AVA)for a 38GHz band of 5G communication.A novel compact AVA is designed to provide constant gain,high front to back ratio(FBR),and very high efficiency.The performance of the proposed AVA is enhanced with the help of a dielectric lens(DL)and corrugations.A rectangular-shaped DL is incorporated in conventional AVA(CAVA)to enhance its gain up to 1 dBi and the bandwidth by 1.8 GHz.Next,the rectangular corrugations are implemented in CAVA with lens(CAVA-L)to further improve the gain and bandwidth.The proposed AVA with lens and corrugations(AVA-LC)gives a constant and high gain of 8.2 to 9 dBi.The designed AVA-LC operates from 34 to 45GHz frequency which covers 38GHz(37.5 to 43.5 GHz)band of 5G applications.Further,the presented AVA-LC mitigates the back lobe and sidelobe levels,resulting in FBR and efficiency improvement.The FBR is in the range of 12.2 to 22 dB,and efficiency is 99%,almost constant.The AVA-LC is fabricated on Roger’s RT/duroid 5880 substrate,and it is tested to verify the simulated results.The proposed compact AVA-LC with high gain,an improved FBR,excellent efficiency,and stable radiation patterns is suitable for the 38GHz band of 5G devices.展开更多
Asynchronous machines are predominantly preferred in industrial sectors for its reliability.Power quality perturbations have a greater impact on industries;among the different power quality events,voltage fluctuations...Asynchronous machines are predominantly preferred in industrial sectors for its reliability.Power quality perturbations have a greater impact on industries;among the different power quality events,voltage fluctuations are the most common and that may cause adverse effect on machine’s operation since they are longer enduring.The article discusses a numerical technique for evaluating asynchronous motors while taking into account magnetic saturation,losses,leakage flux,and voltage drop.A 2D linear analysis involving a multi-slice time stepping finite element model is used to predict the end effects.As an outcome,the magnetic saturation and losses are estimated using amodified 2D nonlinear time-stepping finite element formulation.The method takes the electromagnetic fields at the ends of the motor into account using limited computer resources.The proposed method will greatly reduce computation timewith limited computer resources for analyzing themachine’s performance with high precision.The analyzed findings assist in preventing voltage variance issues in the power network system and provide suggestions for developing a robust system.展开更多
Renewable electricity options, such as fuel cells, solar photovoltaic,and batteries, are being integrated, which has made DC micro-grids famous.For DC micro-grid systems, a multi input interleaved non-isolated dc-dcco...Renewable electricity options, such as fuel cells, solar photovoltaic,and batteries, are being integrated, which has made DC micro-grids famous.For DC micro-grid systems, a multi input interleaved non-isolated dc-dcconverter is suggested by the use of coupled inductor techniques. Since itcompensates for mismatches in photovoltaic devices and allows for separateand continuous power flow from these sources. The proposed converter hasthe benefits of high gain, a low ripple in the output voltage, minimal stressvoltage across the power semiconductor devices, a low ripple in inductorcurrent, high power density, and high efficiency. Soft-switching techniquesare used to realize that the reverse recovery issue of the diodes is moderated, the leakage energy is reused, and no new scheme is appropriated. Toreduce conduction losses, minimum voltage rating MOSFETs with a low ONresistance can be utilized. The converter can supply the required power fromthe load in the absence of one or two resources. Furthermore, due to the highgain of boosting voltage, the converter works in an Adaptive Neuro-FuzzyInference System (ANFIS). The operation principle, steady-state analysis ofthe proposed converter, is given and simulated utilizing MATLAB/Simulinksimulation software.展开更多
文摘Vehicle detection is still challenging for intelligent transportation systems(ITS)to achieve satisfactory performance.The existing methods based on one stage and two-stage have intrinsic weakness in obtaining high vehicle detection performance.Due to advancements in detection technology,deep learning-based methods for vehicle detection have become more popular because of their higher detection accuracy and speed than the existing algorithms.This paper presents a robust vehicle detection technique based on Improved You Look Only Once(RVD-YOLOv5)to enhance vehicle detection accuracy.The proposed method works in three phases;in the first phase,the K-means algorithm performs data clustering on datasets to generate the classes of the objects.Subsequently,in the second phase,the YOLOv5 is applied to create the bounding box,and the Non-Maximum Suppression(NMS)technique is used to eliminate the overlapping of the bounding boxes of the vehicle.Then,the loss function CIoU is employed to obtain the accurate regression bounding box of the vehicle in the third phase.The simulation results show that the proposed method achieves better results when compared with other state-of-art techniques,namely LightweightDilated Convolutional Neural Network(LD-CNN),Single Shot Detector(SSD),YOLOv3 and YOLOv4 on the performance metric like precision,recall,mAP and F1-Score.The simulation and analysis are carried out on PASCAL VOC 2007,2012 and MS COCO 2017 datasets to obtain better performance for vehicle detection.Finally,the RVD-YOLOv5 obtains the results with an mAP of 98.6%and Precision,Recall,and F1-Score are 98%,96.2%and 97.09%,respectively.
基金funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022TR140)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘The coronavirus,formerly known as COVID-19,has caused massive global disasters.As a precaution,most governments imposed quarantine periods ranging from months to years and postponed significantfinancial obligations.Furthermore,governments around the world have used cutting-edge technologies to track citizens’activity.Thousands of sensors were connected to IoT(Internet of Things)devices to monitor the catastrophic eruption with billions of connected devices that use these novel tools and apps,privacy and security issues regarding data transmission and memory space abound.In this study,we suggest a block-chain-based methodology for safeguarding data in the billions of devices and sen-sors connected over the internet.Various trial secrecy and safety qualities are based on cutting-edge cryptography.To evaluate the proposed model,we recom-mend using an application of the system,a Raspberry Pi single-board computer in an IoT system,a laptop,a computer,cell phones and the Ethereum smart contract platform.The models ability to ensure safety,effectiveness and a suitable budget is proved by the Gowalla dataset results.
基金funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022R79),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Deep learning is the process of determining parameters that reduce the cost function derived from the dataset.The optimization in neural networks at the time is known as the optimal parameters.To solve optimization,it initialize the parameters during the optimization process.There should be no variation in the cost function parameters at the global minimum.The momentum technique is a parameters optimization approach;however,it has difficulties stopping the parameter when the cost function value fulfills the global minimum(non-stop problem).Moreover,existing approaches use techniques;the learning rate is reduced during the iteration period.These techniques are monotonically reducing at a steady rate over time;our goal is to make the learning rate parameters.We present a method for determining the best parameters that adjust the learning rate in response to the cost function value.As a result,after the cost function has been optimized,the process of the rate Schedule is complete.This approach is shown to ensure convergence to the optimal parameters.This indicates that our strategy minimizes the cost function(or effective learning).The momentum approach is used in the proposed method.To solve the Momentum approach non-stop problem,we use the cost function of the parameter in our proposed method.As a result,this learning technique reduces the quantity of the parameter due to the impact of the cost function parameter.To verify that the learning works to test the strategy,we employed proof of convergence and empirical tests using current methods and the results are obtained using Python.
基金This research is funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022R 151)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Suspicious mass traffic constantly evolves,making network behaviour tracing and structure more complex.Neural networks yield promising results by considering a sufficient number of processing elements with strong interconnections between them.They offer efficient computational Hopfield neural networks models and optimization constraints used by undergoing a good amount of parallelism to yield optimal results.Artificial neural network(ANN)offers optimal solutions in classifying and clustering the various reels of data,and the results obtained purely depend on identifying a problem.In this research work,the design of optimized applications is presented in an organized manner.In addition,this research work examines theoretical approaches to achieving optimized results using ANN.It mainly focuses on designing rules.The optimizing design approach of neural networks analyzes the internal process of the neural networks.Practices in developing the network are based on the interconnections among the hidden nodes and their learning parameters.The methodology is proven best for nonlinear resource allocation problems with a suitable design and complex issues.The ANN proposed here considers more or less 46k nodes hidden inside 49 million connections employed on full-fledged parallel processors.The proposed ANN offered optimal results in real-world application problems,and the results were obtained using MATLAB.
基金This research was funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022R79)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia,S.Urooj,www.pnu.edu.sa.
文摘This paper proposes a stable gain and a compact Antipodal Vivaldi Antenna(AVA)for a 38GHz band of 5G communication.A novel compact AVA is designed to provide constant gain,high front to back ratio(FBR),and very high efficiency.The performance of the proposed AVA is enhanced with the help of a dielectric lens(DL)and corrugations.A rectangular-shaped DL is incorporated in conventional AVA(CAVA)to enhance its gain up to 1 dBi and the bandwidth by 1.8 GHz.Next,the rectangular corrugations are implemented in CAVA with lens(CAVA-L)to further improve the gain and bandwidth.The proposed AVA with lens and corrugations(AVA-LC)gives a constant and high gain of 8.2 to 9 dBi.The designed AVA-LC operates from 34 to 45GHz frequency which covers 38GHz(37.5 to 43.5 GHz)band of 5G applications.Further,the presented AVA-LC mitigates the back lobe and sidelobe levels,resulting in FBR and efficiency improvement.The FBR is in the range of 12.2 to 22 dB,and efficiency is 99%,almost constant.The AVA-LC is fabricated on Roger’s RT/duroid 5880 substrate,and it is tested to verify the simulated results.The proposed compact AVA-LC with high gain,an improved FBR,excellent efficiency,and stable radiation patterns is suitable for the 38GHz band of 5G devices.
基金This research was funded by the Deanship of Scientific Research at Princess Nourah bint Abdulrahman University through the Fast-track Research Funding Program.
文摘Asynchronous machines are predominantly preferred in industrial sectors for its reliability.Power quality perturbations have a greater impact on industries;among the different power quality events,voltage fluctuations are the most common and that may cause adverse effect on machine’s operation since they are longer enduring.The article discusses a numerical technique for evaluating asynchronous motors while taking into account magnetic saturation,losses,leakage flux,and voltage drop.A 2D linear analysis involving a multi-slice time stepping finite element model is used to predict the end effects.As an outcome,the magnetic saturation and losses are estimated using amodified 2D nonlinear time-stepping finite element formulation.The method takes the electromagnetic fields at the ends of the motor into account using limited computer resources.The proposed method will greatly reduce computation timewith limited computer resources for analyzing themachine’s performance with high precision.The analyzed findings assist in preventing voltage variance issues in the power network system and provide suggestions for developing a robust system.
文摘Renewable electricity options, such as fuel cells, solar photovoltaic,and batteries, are being integrated, which has made DC micro-grids famous.For DC micro-grid systems, a multi input interleaved non-isolated dc-dcconverter is suggested by the use of coupled inductor techniques. Since itcompensates for mismatches in photovoltaic devices and allows for separateand continuous power flow from these sources. The proposed converter hasthe benefits of high gain, a low ripple in the output voltage, minimal stressvoltage across the power semiconductor devices, a low ripple in inductorcurrent, high power density, and high efficiency. Soft-switching techniquesare used to realize that the reverse recovery issue of the diodes is moderated, the leakage energy is reused, and no new scheme is appropriated. Toreduce conduction losses, minimum voltage rating MOSFETs with a low ONresistance can be utilized. The converter can supply the required power fromthe load in the absence of one or two resources. Furthermore, due to the highgain of boosting voltage, the converter works in an Adaptive Neuro-FuzzyInference System (ANFIS). The operation principle, steady-state analysis ofthe proposed converter, is given and simulated utilizing MATLAB/Simulinksimulation software.