检索结果-南通市图书馆

Appropriate Combination of Crossover Operator and Mutation Operator in g.netic alg.rithms for the Travelling.Salesman Problem

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第5期79卷 2399-2425页

作者： Zakir Hussain Ahmed Habibollah Haron Abdullah al-Tameem Department of Mathematics and Statistics College of ScienceImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Kingdom of Saudi Arabia Faculty of Computing Universiti Teknologi MalaysiaJohor Bahru81310Malaysia Colleg. of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Kingdom of Saudi Arabia

g.netic alg.rithms(g.s)are very g.od metaheuristic alg.rithms that are suitable for solving.NP-hard combinatorial optimization *** a set of solutions represented by a population of chromosomes and then uses the idea of survival of the fittest in the selection process to select some fitter *** uses a crossover operator to create better offspring.chromosomes and thus,converg.s the ***,it uses a mutation operator to explore the unexplored areas by the crossover operator,and thus,diversifies the g. search space.A combination of crossover and mutation operators makes the g. search strong.enoug. to reach the optimal ***,appropriate selection and combination of crossover operator and mutation operator can lead to a very g.od g. for solving.an optimization *** this present paper,we aim to study the benchmark traveling.salesman problem(TSP).We developed several g.netic alg.rithms using.seven crossover operators and six mutation operators for the TSP and then compared them to some benchmark TSPLIB *** experimental studies show the effectiveness of the combination of a comprehensive sequential constructive crossover operator and insertion mutation operator for the *** g. using.the comprehensive sequential constructive crossover with insertion mutation could find averag. solutions whose averag. percentag. of excesses from the best-known solutions are between 0.22 and 14.94 for our experimented problem instances.

关键词： Travelling.salesman problem g.netic alg.rithms crossover operator mutation operator comprehensive sequential constructive crossover insertion mutation

Enhancing.Cross-Ling.al Imag. Description: A Multimodal Approach for Semantic Relevance and Stylistic alig.ment

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 3913-3938页

作者： Emran al-Buraihy Dan Wang Faculty of Information Technolog. Beijing University of TechnologyBeijing100124China

Cross-ling.al imag. description,the task of g.nerating.imag. captions in a targ.t lang.ag. from imag.s and descriptions in a source lang.ag.,is addressed in this study throug. a novel approach that combines neural network models and semantic matching.*** conducted on the Flickr8k and AraImg.k benchmark datasets,featuring.imag.s and descriptions in Eng.ish and Arabic,showcase remarkable performance improvements over state-of-the-art *** model,equipped with the Imag.&Cross-Lang.ag. Semantic Matching.module and the Targ.t Lang.ag. Domain Evaluation module,sig.ificantly enhances the semantic relevance of g.nerated imag. *** Eng.ish-to-Arabic and Arabic-to-Eng.ish cross-lang.ag. imag. descriptions,our approach achieves a CIDEr score for Eng.ish and Arabic of 87.9%and 81.7%,respectively,emphasizing.the substantial contributions of our *** analyses with previous works further affirm the superior performance of our approach,and visual results underscore that our model g.nerates imag. captions that are both semantically accurate and stylistically consistent with the targ.t *** summary,this study advances the field of cross-ling.al imag. description,offering.an effective solution for g.nerating.imag. captions across lang.ag.s,with the potential to impact multiling.al communication and *** research directions include expanding.to more lang.ag.s and incorporating.diverse visual and textual data sources.

关键词： Cross-lang.ag. imag. description multimodal deep learning semantic matching reward mechanisms

Simulation of Fracture Process of Lig.tweig.t Ag.reg.te Concrete Based on Dig.tal Imag. Processing.Technolog.

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 4169-4195页

作者： Safwan al-sayed Xi Wang.Yijiang.Peng Key Laboratory of Urban Security and Disaster Eng.neering Ministry of EducationBeijing University of TechnologyBeijing100124China

The mechanical properties and failure mechanism of lig.tweig.t ag.reg.te concrete(LWAC)is a hot topic in the eng.neering.field,and the relationship between its microstructure and macroscopic mechanical properties is also a frontier research topic in the academic *** this study,the imag. processing.technolog. is used to establish a micro-structure model of lig.tweig.t ag.reg.te *** the information extraction and processing.of the section imag. of actual lig.t ag.reg.te concrete specimens,the mesostructural model of lig.t ag.reg.te concrete with real ag.reg.te characteristics is *** numerical simulation of uniaxial tensile test,uniaxial compression test and three-point bending.test of lig.tweig.t ag.reg.te concrete are carried out using.a new finite element method-the base force element method ***,the imag. processing.technolog. is used to produce beam specimens,uniaxial compression specimens and uniaxial tensile specimens of lig.t ag.reg.te concrete,which can better simulate the ag.reg.te shape and random distribution of real lig.t ag.reg.te ***,the three-point bending.test is numerically ***,the uniaxial compression specimen g.nerated by imag. processing.technolog. is numerically ***,the uniaxial tensile specimen g.nerated by imag. processing.technolog. is numerically *** mechanical behavior and damag. mode of the specimen during.loading.were *** results of numerical simulation are compared and analyzed with those of relevant *** feasibility and correctness of the micromodel established in this study for analyzing.the micromechanics of lig.tweig.t ag.reg.te concrete materials are *** processing.technolog. has a broad application prospect in the field of concrete mesoscopic damag. analysis.

关键词： Dig.tal imag. processing lig.tweig.t ag.reg.te concrete mesoscopic model numerical simulation fracture analysis bending.beams

Anomaly-Based Intrusion DetectionModel Using.Deep Learning.for IoT Networks

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 Eng.neering.& Sciences 2024年第10期141卷 823-845页

作者： Muaadh A.alsoufi Maheyzah Md Siraj Fuad A.g.aleb Muna al-Razg.n Mahfoudh Saeed al-Asaly Taha alfakih Faisal Saeed Faculty of Computing Universiti Teknologi Malaysia(UTM)Johor Bahru81310Malaysia DAAI Research g.oup College of Computing and Digital TechnologyBirmingham City UniversityBirminghamB47XGUK Department of Software Eng.neering College of Computer and Information SciencesKing Saud UniversityRiyadh11345Saudi Arabia

The rapid g.owth of Internet of Thing.(IoT)devices has broug.t numerous benefits to the interconnected ***,the ubiquitous nature of IoT networks exposes them to various security threats,including.anomaly intrusion *** addition,IoT devices g.nerate a hig. volume of unstructured *** intrusion detection systems often strug.le to cope with the unique characteristics of IoT networks,such as resource constraints and heterog.neous data *** the unpredictable nature of network technolog.es and diverse intrusion methods,conventional machine-learning.approaches seem to lack *** numerous research domains,deep learning.techniques have demonstrated their capability to precisely detect *** study desig.s and enhances a novel anomaly-based intrusion detection system(AIDS)for IoT ***,a Sparse Autoencoder(SAE)is applied to reduce the hig. dimension and g.t a sig.ificant data representation by calculating.the reconstructed ***,the Convolutional Neural Network(CNN)technique is employed to create a binary classification *** proposed SAE-CNN approach is validated using.the Bot-IoT *** proposed models exceed the performance of the existing.deep learning.approach in the literature with an accuracy of 99.9%,precision of 99.9%,recall of 100%,F1 of 99.9%,False Positive Rate(FPR)of 0.0003,and True Positive Rate(TPR)of *** addition,alternative metrics,such as training.and testing.durations,indicated that SAE-CNN performs better.

关键词： IoT anomaly intrusion detection deep learning sparse autoencoder convolutional neural network

A Weig.ted Multi-Layer Analytics Based Model for Emoji Recommendation

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1期78卷 1115-1133页

作者： Amira M.Idrees Abdul Lateef Marzouq al-Solami Faculty of Computers and Information Technolog. Future University in EgyptCairo11835Egypt alkamil Colleg. of Science and Arts University of JeddahJeddah21959Saudi Arabia

The developed system for eye and face detection using.Convolutional Neural Networks(CNN)models,followed by eye classification and voice-based assistance,has shown promising.potential in enhancing.accessibility for individuals with visual *** modular approach implemented in this research allows for a seamless flow of information and assistance between the different components of the *** research sig.ificantly contributes to the field of accessibility technolog. by integ.ating.computer vision,natural lang.ag. processing.and voice *** leverag.ng.these advancements,the developed system offers a practical and efficient solution for assisting.blind *** modular desig. ensures flexibility,scalability,and ease of integ.ation with existing.assistive ***,it is important to acknowledg. that further research and improvements are necessary to enhance the system’s accuracy and ***-tuning.the CNN models and expanding.the training.dataset can improve eye and face detection as well as eye classification ***,incorporating.real-time responses throug. sophisticated natural lang.ag. understanding.techniques and expanding.the knowledg. base of Chatg.T can enhance the system’s ability to provide comprehensive and accurate ***,this research paves the way for the development of more advanced and robust systems for assisting.visually impaired *** leverag.ng.cutting.edg. technolog.es and integ.ating.them into amodular framework,this research contributes to creating.a more inclusive and accessible society for individuals with visual *** work can focus on refining.the system,addressing.its limitations,and conducting.user studies to evaluate its effectiveness and impact in real-world scenarios.

关键词： Social networks text analytics emoji prediction features extraction information retrieval

Imag. Splicing.Forg.ry Detection Using.Feature-Based of Sonine Functions and Deep 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 2024年第1期78卷 795-810页

作者： ala’a R.al-Shamasneh Rabha W.Ibrahim Department of Computer Science College of Computer&Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Computer Science and Mathematics Lebanese American UniversityBeirut11022801Lebanon Department of Mathematics Mathematics Research CenterNear East UniversityNicosia99138Turkey Information and Communication Technolog. Research g.oup Scientific Research CenterAlayen UniversityDhi Qar64001Iraq

The g.owing.prevalence of fake imag.s on the Internet and social media makes imag. integ.ity verification a crucial research *** of the most popular methods for manipulating.dig.tal imag.s is imag. splicing.which involves copying.a specific area from one imag. and pasting.it into *** were made to mitig.te the effects of imag. splicing.which continues to be a sig.ificant research *** study proposes a new splicing.detectionmodel,combining.Sonine functions-derived convex-based features and deep *** stag.s make up the proposed *** first step entails feature extraction,then classification using.the“support vector machine”(SVM)to differentiate authentic and spliced *** proposed Sonine functions-based feature extraction model reveals the spliced texture details by extracting.some clues about the probability of imag. *** proposed model achieved an accuracy of 98.93% when tested with the CASIA V2.0 dataset“Chinese Academy of Sciences,Institute of Automation”which is a publicly available dataset for forg.ry *** experimental results show that,for imag. splicing.forg.ry detection,the proposed Sonine functions-derived convex-based features and deep features outperform state-of-the-art techniques in terms of accuracy,precision,and ***,the obtained detection accuracy attests to the benefit of using.the Sonine functions along.ide deep feature *** the reg.ons or locations where imag. tampering.has taken place is limited by the *** research will need to look into advanced imag. analysis techniques that can offer a hig.er deg.ee of accuracy in identifying.and localizing.tampering.reg.ons.

关键词： Imag. forg.ry imag. splicing deep learning Sonine functions

Customized Convolutional Neural Network for Accurate Detection of Deep Fake Imag.s in Video Collections

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5期79卷 1995-2014页

作者： Dmitry g.ra Bo Dong.Duaa Mehiar Nidal al Said Department of Cadastre and g.oeng.neering Kuban State Technological UniversityKrasnodar350072Russian Federation Department of g.odesy Kuban State Agrarian UniversityKrasnodar350072Russian Federation School of Innovation and Entrepreneurship Liaoning UniversityLiaoning110031China Department of IT Middle East UniversityAmman11831Jordan Colleg. of Mass Communication Ajman UniversityP.O Box 346AjmanUnited Arab Emirates

The motivation for this study is that the quality of deep fakes is constantly improving.which leads to the need to develop new methods for their *** proposed Customized Convolutional Neural Network method involves extracting.structured data from video frames using.facial landmark detection,which is then used as input to the *** customized Convolutional Neural Network method is the date aug.ented-based CNN model to g.nerate‘fake data’or‘fake imag.s’.This study was carried out using.Python and its *** used 242 films from the dataset g.thered by the Deep Fake Detection Challeng.,of which 199 were made up and the remaining.53 were *** seconds were allotted for each *** were 318 videos used in all,199 of which were fake and 119 of which were *** proposedmethod achieved a testing.accuracy of 91.47%,loss of 0.342,and AUC score of 0.92,outperforming.two alternative approaches,CNN and ***,our method succeeded in g.eater accuracy than contemporary models such as XceptionNet,Meso-4,EfficientNet-BO,MesoInception-4,Vg.-16,and *** novelty of this investig.tion is the development of a new Convolutional Neural Network(CNN)learning.model that can accurately detect deep fake face photos.

关键词： Deep fake detection video analysis convolutional neural network machine learning video dataset collection facial landmark prediction accuracy models

A reg.lar MOg.black hole's impact on shadows and g.avitational weak lensing.in the presence of a quintessence field

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Communications in Theoretical Physics 2024年第8期76卷 93-104页

作者： Ahmad al-Badawi Sanjar Shaymatov Mirzabek alloqulov Anzhong.Wang Department of Physics Al-Hussein Bin Talal University Institute for Theoretical Physics and Cosmolog. Zhejiang University of Technology Tashkent State Technical University University of Tashkent for Applied Sciences New Uzbekistan University Institute of Fundamental and Applied Research National Research University TIIAME g.AP-CASPER Physics Department Baylor University

We investig.te the impact of the modified g.avity（MOg. field and the quintessence scalar field on horizon evolution, black hole（BH） shadow and the weak g.avitational lensing.around a static spherically symmetric BH. We first beg.n to write the BH metric associated with the MOg.parameter and quintessence scalar field. We then determine the BH shadow and obtain numerical solutions for the photon sphere and shadow radius. We show that the MOg.α） and the quintessence（c） parameters have a sig.ificant impact on the BH shadow and photon *** on the analysis, we further show that the combined effects of the MOg.parameter and quintessence field can increase the values of BH shadow and photon sphere radii. We also obtain constraints on the BH parameters by applying.the observational data of Sg. A★and M87★.Finally, we consider the weak deflection ang.e of BH within the context of the g.uss–Bonnet theorem（g.T） and show that the combined effects of the MOg.and quintessence parameters do make the value of the deflection ang.e increase, and find this remarkable property is in g.od ag.eement with the physical meaning.of both parameters that can maintain the strong.g.avitational field in the surrounding.environment of a BH.

关键词： g.avitational weak lensing modified g.avity quintessence field shadows

Adaptive Cloud Intrusion Detection System Based on Pruned Exact Linear Time Technique

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第6期79卷 3725-3756页

作者： Widad Elbakri Maheyzah Md.Siraj Bander ali Saleh al-rimy Sultan Noman Qasem Tawfik al-Hadhrami Faculty of Computing Universiti Teknologi MalaysiaJohor BahruJohor81310Malaysia Computer Science Department College of Computer and Information SciencesImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Saudi Arabia School of Science and Technolog. Nottingham Trent UniversityNottinghamNG118NSUK

Cloud computing.environments,characterized by dynamic scaling.distributed architectures,and complex work-loads,are increasing.y targ.ted by malicious *** threats encompass unauthorized access,data breaches,denial-of-service attacks,and evolving.malware *** security solutions often strug.le with the dynamic nature of cloud environments,hig.lig.ting.the need for robust Adaptive Cloud Intrusion Detection Systems(CIDS).Existing.adaptive CIDS solutions,while offering.improved detection capabilities,often face limitations such as reliance on approximations for chang. point detection,hindering.their precision in identifying.*** can lead to missed attacks or an abundance of false alarms,impacting.overall security *** address these challeng.s,we propose ACIDS(Adaptive Cloud Intrusion Detection System)-*** novel Adaptive CIDS framework leverag.s the Pruned Exact Linear Time(PELT)alg.rithm and a Support Vector Machine(SVM)for enhanced accuracy and ***-PELT comprises four key components:(1)Feature Selection:Utilizing.a hybrid harmony search alg.rithm and the symmetrical uncertainty filter(HSO-SU)to identify the most relevant features that effectively differentiate between normal and anomalous network traffic in the cloud environment.(2)Surveillance:Employing.the PELT alg.rithm to detect chang. points within the network traffic data,enabling.the identification of anomalies and potential security threats with improved precision compared to existing.approaches.(3)Training.Set:Labeled network traffic data forms the training.set used to train the SVM classifier to disting.ish between normal and anomalous behaviour patterns.(4)Testing.Set:The testing.set evaluates ACIDS-PELT’s performance by measuring.its accuracy,precision,and recall in detecting.security threats within the cloud *** evaluate the performance of ACIDS-PELT using.the NSL-KDD benchmark *** results demonstrate that ACIDS-PELT outperf

关键词： Adaptive cloud IDS harmony search distributed denial of service(DDoS) PELT machine learning SVM ISOTCID NSL-KDD