检索结果-南通市图书馆

Improving the Transmission Security of Vein Images Using a Bezier Curve and Long Short-Term Memory

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 2024年第6期79卷 4825-4844页

作者： Ahmed H.Alhadethi Ikram Smaoui Ahmed Fakhfakh saad M.darwish Computer Science and School of Electronics and Telecommunications University of SfaxSfax3029Tunisia LETI Laboratory University of SfaxSfax3029Tunisia Digital Research Center of Sfax Technopark of SfaxSfax3029Tunisia Department of Information Technology Institute of Graduate Studies and ResearchAlexandria UniversityAlexandriaEgypt

The act of transmitting photos via the Internet has become a routine and significant *** the security measures to safeguard these images from counterfeiting and modifications is a critical domain that can still be further *** study presents a system that employs a range of approaches and algorithms to ensure the security of transmitted venous *** main goal of this work is to create a very effective system for compressing individual biometrics in order to improve the overall accuracy and security of digital photographs by means of image *** paper introduces a content-based image authentication mechanism that is suitable for usage across an untrusted network and resistant to data loss during *** employing scale attributes and a key-dependent parametric Long Short-Term Memory(LSTM),it is feasible to improve the resilience of digital signatures against image deterioration and strengthen their security against malicious ***,the successful implementation of transmitting biometric data in a compressed format over a wireless network has been *** applications involving the transmission and sharing of images across a *** suggested technique utilizes the scalability of a structural digital signature to attain a satisfactory equilibrium between security and picture *** effective adaptive compression strategy was created to lengthen the overall lifetime of the network by sharing the processing of *** scheme ensures a large reduction in computational and energy requirements while minimizing image quality *** approach employs multi-scale characteristics to improve the resistance of signatures against image *** proposed system attained a Gaussian noise value of 98%and a rotation accuracy surpassing 99%.

关键词： Image transmission image compression text hiding Bezier curve Histogram of Oriented Gradients(HOG) LSTM image enhancement Gaussian noise rotation

Database Recovery Technique for Mobile Computing:A Game Theory Approach

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 2022年第2期70卷 3205-3219页

作者： Magda M.Madbouly Yasser F.Mokhtar saad M.darwish Institute of Graduate Studies and Research Alexandria UniversityAlexandriaEgypt Assistant General Manager IT DepartmentEgyptian Petrochemicals Co.AlexandriaEgypt

Contact between mobile hosts and database servers presents many problems in theMobile Database System(MDS).It is harmed by a variety of causes,including handoff,inadequate capacity,frequent transaction updates,and repeated failures,both of which contribute to serious issues with the information system’s ***,error tolerance technicality allows devices to continue performing their functions in the event of a *** aim of this paper is to identify the optimal recovery approach from among the available state-of-the-art techniques in MDS by employing game *** of the presented recovery protocols are chosen and evaluated in order to determine the most critical factors affecting the recovery mechanism,such as the number of processes,the time required to deliver messages,and the number of messages logged-in ***,using the suggested payout matrix,the game theory strategy is adapted to choose the optimum recovery technique for the specified environmental *** NS2 simulatorwas used to carry out the tests and apply the chosen recovery *** experiments validate the proposed model’s usefulness in comparison to other methods.

关键词： Mobile computing game theory decision making mobile database recovery

Type-2 Neutrosophic Set and Their Applications in Medical Databases Deadlock Resolution

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 4417-4434页

作者： Marwan H.Hassan saad M.darwish Saleh M.Elkaffas Department of Advocacy and Public Speaking Imam Al-Adham University CollegeAnbar55431Iraq Department of Information Technology Institute of Graduate Studies and ResearchAlexandria UniversityAlexandria21526Egypt College of Computing and Information Technology Arab Academy for ScienceTechnology and Maritime TransportAlexandria1029Egypt

Electronic patient data gives many advantages,but also new *** may delay procedures like acquiring patient *** deadlock resolution solutions introduce uncertainty due to inaccurate transaction *** computing-based solutions have been developed to solve this *** a single framework,ambiguous,vague,incomplete,and inconsistent transaction attribute information has received minimal *** work presented in this paper employed type-2 neutrosophic logic,an extension of type-1 neutrosophic logic,to handle uncertainty in real-time deadlock-resolving *** proposed method is structured to reflect multiple types of knowledge and relations among transactions’features that include validation factor degree,slackness degree,degree of deadline-missed transaction based on the degree of membership of truthiness,degree ofmembership of indeterminacy,and degree ofmembership of ***,the footprint of uncertainty(FOU)for truth,indeterminacy,and falsity represents the level of uncertainty that exists in the value of a grade of *** employed a distributed real-time transaction processing simulator(DRTTPS)to conduct the simulations and conducted experiments using the benchmark Pima Indians diabetes dataset(PIDD).As the results showed,there is an increase in detection rate and a large drop in rollback rate when this new strategy is *** performance of Type-2 neutrosophicbased resolution is better than the Type-1 neutrosophic-based approach on the execution ratio *** improvement rate has reached 10%to 20%,depending on the number of arrived transactions.

关键词： Deadlock recovery type-2 neutrosophic set healthcare databases distributed deadlock detection

Realistic Smile Expression Recognition Approach Using Ensemble Classifier with Enhanced Bagging

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 2022年第2期70卷 2453-2469页

作者： Oday A.Hassen Nur Azman Abu Zaheera Zainal Abidin saad M.darwish University Technical Malaysia Melaka Department of Information TechnologyMelaka76100Malaysia Institute of Graduate Studies and Research University of AlexandriaAlexandriaEl Shatby21526Egypt

A robust smile recognition system could be widely used for many real-world *** of a facial smile in an unconstrained setting is difficult due to the invertible and wide variety in face *** this paper,an adaptive model for smile expression classification is suggested that integrates a fast features extraction algorithm and cascade *** model takes advantage of the intrinsic association between face detection,smile,and other face features to alleviate the over-fitting issue on the limited training set and increase classification *** features are extracted taking into account to exclude any unnecessary coefficients in the feature vector;thereby enhancing the discriminatory capacity of the extracted features and reducing the computational ***,the main causes of error in learning are due to noise,bias,and *** helps to minimize these *** of multiple classifiers decrease variance,especially in the case of unstable classifiers,and may produce a more reliable classification than a single ***,a shortcoming of bagging as the best ensemble classifier is its random selection,where the classification performance relies on the chance to pick an appropriate subset of training *** suggested model employs a modified form of bagging while creating training sets to deal with this challenge(error-based bootstrapping).The experimental results for smile classification on the JAFFE,CK+,and CK+48 benchmark datasets show the feasibility of our proposed model.

关键词： Ensemble classifier smile expression detection features extraction

An Optimized Convolutional Neural Network Architecture Based on Evolutionary Ensemble Learning

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 2021年第12期69卷 3813-3828页

作者： Qasim M.Zainel Murad B.K.horsheed saad darwish Amr A.Ahmed College of Physical Education and Sports Sciences University of KirkukKirkuk36001Iraq College of Administration&Economics University of KirkukKirkuk36001Iraq Department of Information Technology Institute of Graduate Studies and ResearchAlexandria UniversityAlexandriaEgypt Department of Computer Engineering Alexandria Higher Institute of Engineering&Technology(AIET)AlexandriaEgypt

Convolutional Neural Networks(CNNs)models succeed in vast *** are available in a variety of topologies and *** challenge in this area is to develop the optimal CNN architecture for a particular issue in order to achieve high results by using minimal computational resources to train the *** proposed framework to automated design is aimed at resolving this *** proposed framework is focused on a genetic algorithm that develops a population of CNN models in order to find the architecture that is the best *** comparison to the co-authored work,our proposed framework is concerned with creating lightweight architectures with a limited number of parameters while retaining a high degree of validity accuracy utilizing an ensemble learning *** architecture is intended to operate on low-resource machines,rendering it ideal for implementation in a number of *** common benchmark image datasets are used to test the proposed framework,and it is compared to peer competitors’work utilizing a range of parameters,including accuracy,the number of model parameters used,the number of GPUs used,and the number of GPU days needed to complete the *** experimental findings demonstrated a significant advantage in terms of GPU days,accuracy,and the number of parameters in the discovered model.

关键词： Convolutional neural networks genetic algorithm automatic model design ensemble learning

One-Class Arabic Signature Verification: A Progressive Fusion of Optimal Features

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4期75卷 219-242页

作者： Ansam A.Abdulhussien Mohammad F.Nasrudin saad M.darwish Zaid A.Alyasseri Centre of Artificial Intelligence Faculty of Information Sciences and TechnologyUniversity Kebangsaan MalaysiaBangi43600Malaysia Information Technology Center Iraqi Commission for Computers and InformaticsBaghdad10009Iraq Institute of Graduate Studies and Research University of Alexandria163 Horreya AvenueEl Shatby21526P.O.Box 832AlexandriaEgypt

Signature verification is regarded as the most beneficial behavioral characteristic-based biometric feature in security and fraud *** is also a popular biometric authentication technology in forensic and commercial transactions due to its various advantages,including noninvasiveness,user-friendliness,and social and legal *** to the literature,extensive research has been conducted on signature verification systems in a variety of languages,including English,Hindi,Bangla,and ***,the Arabic Offline Signature Verification(OSV)system is still a challenging issue that has not been investigated as much by researchers due to the Arabic script being distinguished by changing letter shapes,diacritics,ligatures,and overlapping,making verification more ***,signature verification systems have shown promising results for recognizing signatures that are genuine or forgeries;however,performance on skilled forgery detection is still *** existing methods require many learning samples to improve verification accuracy,which is a major drawback because the number of available signature samples is often limited in the practical application of signature verification *** study addresses these issues by presenting an OSV system based on multifeature fusion and discriminant feature selection using a genetic algorithm(GA).In contrast to existing methods,which use multiclass learning approaches,this study uses a oneclass learning strategy to address imbalanced signature data in the practical application of a signature verification *** proposed approach is tested on three signature databases(SID)-Arabic handwriting signatures,CEDAR(Center of Excellence for Document Analysis and Recognition),and UTSIG(University of Tehran Persian Signature),and experimental results show that the proposed system outperforms existing systems in terms of reducing the False Acceptance Rate(FAR),False Rejection Rate(FRR),and Equa

关键词： Offline signature verification biometric system feature fusion one-class classifier

Wireless Sensor Networks Routing Attacks Prevention with Blockchain and Deep Neural Network

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 2022年第3期70卷 6127-6140页

作者： Mohamed Ali Ibrahim A.Abd El-Moghith Mohamed N.El-Derini saad M.darwish Higher Institute for Tourism Hotels and ComputerAl-SeyoufAlexandria21533Egypt Department of Information Technology Institute of Graduate Studies and ResearchAlexandria University21526Egypt Department of Computer and Systems Engineering Faculty of EngineeringAlexandria UniversityAlexandria21544Egypt

Routing is a key function inWireless Sensor Networks(WSNs)since it facilitates data transfer to base *** attacks have the potential to destroy and degrade the functionality ofWSNs.A trustworthy routing system is essential for routing security andWSN *** methods have been implemented to build trust between routing nodes,including the use of cryptographic methods and centralized ***,the majority of routing techniques are unworkable in reality due to the difficulty of properly identifying untrusted routing node *** the moment,there is no effective way to avoid malicious node *** a consequence of these concerns,this paper proposes a trusted routing technique that combines blockchain infrastructure,deep neural networks,and Markov Decision Processes(MDPs)to improve the security and efficiency of WSN *** authenticate the transmission process,the suggested methodology makes use of a Proof of Authority(PoA)mechanism inside the blockchain *** validation group required for proofing is chosen using a deep learning approach that prioritizes each node’s *** are then utilized to determine the suitable next-hop as a forwarding node capable of securely transmitting *** to testing data,our routing system outperforms current routing algorithms in a 50%malicious node routing scenario.

关键词： Wireless sensor networks trusted routing deep neural network blockchain markov decision

An Adaptive Privacy Preserving Framework for Distributed Association Rule Mining in Healthcare Databases

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 4119-4133页

作者： Hasanien K.Kuba Mustafa A.Azzawi saad M.darwish Oday A.Hassen Ansam A.Abdulhussein University of Information Technology and Communication(UOITC) Baghdad10081Iraq Accenture Ling Karan TRXKuala Lumpur55188Malaysia Department of Information Technology Institute of Graduate Studies and ResearchUniversity of Alexandria21526Egypt Ministry of Education Wasit Education DirectorateKut52001Iraq Information Technology Center Iraqi Commission for Computers and InformaticsBaghdad10081Iraq

It is crucial,while using healthcare data,to assess the advantages of data privacy against the possible *** from several sources must be combined for use in many data mining *** medical practitioner may use the results of association rule mining performed on this aggregated data to better personalize patient care and implement preventive ***,numerous heuristics(e.g.,greedy search)and metaheuristics-based techniques(e.g.,evolutionary algorithm)have been created for the positive association rule in privacy preserving data mining(PPDM).When it comes to connecting seemingly unrelated diseases and drugs,negative association rules may be more informative than their positive *** is well-known that during negative association rules mining,a large number of uninteresting rules are formed,making this a difficult problem to *** this research,we offer an adaptive method for negative association rule mining in vertically partitioned healthcare datasets that respects users’*** applied approach dynamically determines the transactions to be interrupted for information hiding,as opposed to predefining *** study introduces a novel method for addressing the problem of negative association rules in healthcare data mining,one that is based on the Tabu-genetic optimization *** search is advantageous since it removes a huge number of unnecessary rules and item *** using benchmark healthcare datasets prove that the discussed scheme outperforms state-of-the-art solutions in terms of decreasing side effects and data distortions,as measured by the indicator of hiding failure.

关键词： Distributed data mining evolutionary computation sanitization process healthcare informatics

Nature-Inspired Level Set Segmentation Model for 3D-MRI Brain Tumor Detection

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 2021年第7期68卷 961-981页

作者： Oday Ali Hassen Sarmad Omar Abter Ansam A.Abdulhussein saad M.darwish Yasmine M.Ibrahim Walaa Sheta Department of Computer Techniques Engineering Imam Al-Kadhum College(IKC)WasitIraq University of Information Technology and Communications Media Technology Engineering DepartmentIraq University of Information Technology and Communications Baghdad10081Iraq Department of Information Technology Institute of Graduate Studies and ResearchAlexandria University63 Horreya AvenueEl–ShatbyAlexandria21526Egypt Informatics Research Institute City of Scientific Research and Technology ApplicationsBorg EL Arab21934Egypt

Medical image segmentation has consistently been a significant topic of research and a prominent goal,particularly in computer *** tumor research plays a major role in medical imaging applications by providing a tremendous amount of anatomical and functional knowledge that enhances and allows easy diagnosis and disease therapy *** prevent or minimize manual segmentation error,automated tumor segmentation,and detection became the most demanding process for radiologists and physicians as the tumor often has complex *** methods for detection and segmentation presently exist,but all lack high *** paper’s key contribution focuses on evaluating machine learning techniques that are supposed to reduce the effect of frequently found issues in brain tumor ***,attention concentrated on the challenges related to level set *** study proposed in this paper uses the Population-based Artificial Bee Colony Clustering(P-ABCC)methodology to reliably collect initial contour points,which helps minimize the number of iterations and segmentation errors of the level-set *** proposed model measures cluster centroids(ABC populations)and uses a level-set approach to resolve contour differences as brain tumors vary as they have irregular form,structure,and *** suggested model comprises of three major steps:first,pre-processing to separate the brain from the head and improves contrast ***,P-ABCC is used to obtain tumor edges that are utilized as an initial MRI sequence *** level-set segmentation is then used to detect tumor regions from all volume slices with fewer *** suggest improved model efficiency compared to state-of-the-art methods for both datasets BRATS 2019 and BRATS *** BRATS 2019,dice progress was achieved for Entire Tumor(WT),Tumor Center(TC),and Improved Tumor(ET)by 0.03%,0.03%,and 0.01%*** BRATS 2017,an increase in precision for WT was reac

关键词： 3D-MRI tumor diagnosis bio-inspired clustering ABC optimization multimodal detection