检索结果-南通市图书馆

Robust Vehicle Detection Based on Improved You Look Only Once

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第2期74卷 3561-3577页

作者： Sunil Kumar Manisha Jailia Sudeep Varshney nitish pathak Shabana Urooj Nouf Abd Elmunim Department of Computer Science Banasthali VidyapithRajasthan304022India Department of Computer Science&Engineering School of Engineering&TechnologySharda UniversityGreater Noida201310India Department of Information Technology Bhagwan Parshuram Institute of Technology(BPIT)GGSIPUNew Delhi110078India Department of Electrical Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.BOX 84428Riyadh11671Saudi Arabia

Vehicle detection is still challenging for intelligent transportation systems(ITS)to achieve satisfactory *** existing methods based on one stage and two-stage have intrinsic weakness in obtaining high vehicle detection *** 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 *** paper presents a robust vehicle detection technique based on Improved You Look Only Once(RVD-YOLOv5)to enhance vehicle detection *** 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 ***,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 ***,the loss function CIoU is employed to obtain the accurate regression bounding box of the vehicle in the third *** 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 *** simulation and analysis are carried out on PASCAL VOC 2007,2012 and MS COCO 2017 datasets to obtain better performance for vehicle ***,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.

关键词： Image-processing K-means clustering CNN YOLOv5 loss function deep-learning

Performance Enhancement of Adaptive Neural Networks Based on Learning Rate

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第1期74卷 2005-2019页

作者： Swaleha Zubair Anjani Kumar Singha nitish pathak Neelam Sharma Shabana Urooj Samia Rabeh Larguech Department of Computer Science Aligarh Muslim UniversityAligarh202002Uttar PradeshIndia Department of Information Technology Bhagwan Parshuram Institute of Technology(BPIT)GGSIPUNew Delhi110089India Department of Computer Science and Engineering Maharaja Agrasen Institute of Technology(MAIT)GGSIPUNew DelhiIndia Department of Electrical Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia

Deep learning is the process of determining parameters that reduce the cost function derived from the *** optimization in neural networks at the time is known as the optimal *** solve optimization,it initialize the parameters during the optimization *** should be no variation in the cost function parameters at the global *** 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 *** techniques are monotonically reducing at a steady rate over time;our goal is to make the learning rate *** present a method for determining the best parameters that adjust the learning rate in response to the cost function *** a result,after the cost function has been optimized,the process of the rate Schedule is *** approach is shown to ensure convergence to the optimal *** indicates that our strategy minimizes the cost function(or effective learning).The momentum approach is used in the proposed *** solve the Momentum approach non-stop problem,we use the cost function of the parameter in our proposed *** a result,this learning technique reduces the quantity of the parameter due to the impact of the cost function *** 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.

关键词： Deep learning optimization convergence stochastic gradient methods

Design of ANN Based Non-Linear Network Using Interconnection of Parallel Processor

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第9期46卷 3491-3508页

作者： Anjani Kumar Singha Swaleha Zubair Areej Malibari nitish pathak Shabana Urooj Neelam Sharma Department of Computer Science Aligarh Muslim UniversityAligarh202002India Department of Industrial and Systems Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Technology Bhagwan Parshuram Institute of Technology(BPIT)GGSIPUNew Delhi110078India Department of Electrical Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Artificial Intelligence&Machine Learning Maharaja Agrasen Institute of Technology(MAIT)GGSIPUNew Delhi110086India

Suspicious mass traffic constantly evolves,making network behaviour tracing and structure more *** networks yield promising results by considering a sufficient number of processing elements with strong interconnections between *** offer efficient computational Hopfield neural networks models and optimization constraints used by undergoing a good amount of parallelism to yield optimal *** neural network(ANN)offers optimal solutions in classifying and clustering the various reels of data,and the results obtained purely depend on identifying a *** this research work,the design of optimized applications is presented in an organized *** addition,this research work examines theoretical approaches to achieving optimized results using *** mainly focuses on designing *** optimizing design approach of neural networks analyzes the internal process of the neural *** in developing the network are based on the interconnections among the hidden nodes and their learning *** methodology is proven best for nonlinear resource allocation problems with a suitable design and complex *** ANN proposed here considers more or less 46k nodes hidden inside 49 million connections employed on full-fledged parallel *** proposed ANN offered optimal results in real-world application problems,and the results were obtained using MATLAB.

关键词： Artificial neural network(ANN) multiprocessor hidden node nonlinear optimization parallel processing

Smart Quarantine Environment Privacy through IoT Gadgets Using Blockchain

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第3期35卷 3021-3036页

作者： nitish pathak Shams Tabrez Siddiqui Anjani Kumar Singha Heba G Mohamed Shabana Urooj Abhinandan R Patil Department of Information Technology Bhagwan Parshuram Institute of Technology(BPIT)GGSIPUNew Delhi110078India Department of Computer Science Jazan UniversityJazan45142Saudi Arabia Department of Computer Science Aligarh Muslim UniversityAligarh202002India Department of Electrical Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP O Box 84428Riyadh11671Saudi Arabia Sanjay Ghodawat University KolhapurMaharashtra416118India

The coronavirus,formerly known as COVID-19,has caused massive global *** a precaution,most governments imposed quarantine periods ranging from months to years and postponed signiﬁcantﬁnancial ***,governments around the world have used cutting-edge technologies to track citizens’*** 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 *** this study,we suggest a block-chain-based methodology for safeguarding data in the billions of devices and sen-sors connected over the *** trial secrecy and safety qualities are based on cutting-edge *** 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 *** models ability to ensure safety,effectiveness and a suitable budget is proved by the Gowalla dataset results.

关键词： Ring signature blockchain IoT encryption smart contract decryption authentication privacy-preserving

An Analysis of Integrating Machine Learning in Healthcare for Ensuring Confidentiality of the Electronic Records

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2022年第3期130卷 1387-1422页

作者： Adil Hussain Seh Jehad F.Al-Amri Ahmad F.Subahi Alka Agrawal nitish pathak Rajeev Kumar Raees Ahmad Khan Department of Information Technology Babasaheb Bhimrao Ambedkar UniversityLucknow226025India Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Computer Science Umm Al-Qura UniversityMakkah21421Saudi Arabia Department of Information Technology Guru Gobind Singh Indraprastha UniversityDelhi110078India Department of Computer Applications Shri Ramswaroop Memorial UniversityBarabanki225003India Department of Computer Science and Engineering Babu Banarasi Das UniversityLucknow226028India

The adoption of sustainable electronic healthcare infrastructure has revolutionized healthcare services and ensured that E-health technology caters efficiently and promptly to the needs of the stakeholders associated with *** the phenomenal advancement in the present healthcare services,the major obstacle that mars the success of E-health is the issue of ensuring the confidentiality and privacy of the patients’data.A thorough scan of several research studies reveals that healthcare data continues to be the most sought after entity by cyber *** approaches and methods have been practiced by researchers to secure healthcare digital ***,there are very few from the Machine learning(ML)domain even though the technique has the proactive ability to detect suspicious accesses against Electronic Health Records(EHRs).The main aim of this work is to conduct a systematic analysis of the existing research studies that address healthcare data confidentiality issues through ML *** guidelines have been practiced as a manual to conduct this *** well-known digital libraries namely IEEE Xplore,Science Direct,Springer Link,ACM Digital Library,Willey Online Library,PubMed(Medical and Bio-Science),and MDPI have been included to performan exhaustive search for the existing pertinent *** of this study depict that machine learning provides a more robust security mechanism for sustainable management of the EHR systems in a proactive fashion,yet the specified area has not been fully explored by the researchers.K-nearest neighbor algorithm and KNIEM implementation tools are mostly used to conduct experiments on EHR systems’log *** and performance measure of practiced techniques are not sufficiently outlined in the primary *** research endeavour depicts that there is a need to analyze the dynamic digital healthcare environment more *** accuracy and effective implementation of

关键词： EHRs healthcare machine learning systematic analysis