检索结果-南通市图书馆

Optimized Generative Adversarial Networks for Adversarial Sample Generation

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8期72卷 3877-3897页

作者： Daniyal M.Alghazzawi Syed Hamid Hasan surbhi bhatia Faculty of Computing and Information Technology King Abdulaziz UniversityJeddah21589Saudi Arabia Department of Information Systems College of Computer Sciences and Information TechnologyKing Faisal UniversitySaudi Arabia

Detecting the anomalous entity in real-time network traffic is a popular area of research in recent *** few researches have focused on creating malware that fools the intrusion detection system and this paper focuses on this *** are using Deep Convolutional Generative Adversarial Networks(DCGAN)to trick the malware classifier to believe it is a normal *** this work,a new dataset is created to fool the Artificial Intelligence(AI)based malware detectors,and it consists of different types of attacks such as Denial of Service(DoS),scan 11,scan 44,botnet,spam,User Datagram Portal(UDP)scan,and ssh *** discriminator used in the DCGAN discriminates two different attack classes(anomaly and synthetic)and one normal *** model collapse,instability,and vanishing gradient issues associated with the DCGAN are overcome using the proposed hybrid Aquila optimizer-based Mine blast harmony search algorithm(AO-MBHS).This algorithm helps the generator to create realistic malware samples to be undetected by the *** performance of the proposed methodology is evaluated using different performance metrics such as training time,detection rate,F-Score,loss function,Accuracy,False alarm rate,*** superiority of the hybrid AO-MBHS based DCGAN model is noticed when the detection rate is changed to 0 after the retraining method to make the defensive technique hard to be noticed by the malware detection *** support vector machines(SVM)is used as the malicious traffic detection application and its True positive rate(TPR)goes from 80%to 0%after retraining the proposed model which shows the efficiency of the proposed model in hiding the samples.

关键词： Aquila optimizer convolutional generative adversarial networks mine blast harmony search algorithm network traffic dataset adversarial artificial intelligence techniques

Proportional Fairness Based Energy Efficient Routing in Wireless Sensor 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

Computer Systems Science & Engineering 2022年第6期41卷 1071-1082页

作者： Abolfazl Mehbodniya surbhi bhatia Arwa Mashat Mohanraj Elangovan Sudhakar Sengan Department of Electronics and Communications Engineering Kuwait College of Science and TechnologyKuwait Department of Information Systems College of Computer Sciences and Information TechnologyKing Faisal UniversitySaudi Arabia Department of Information Systems College of Computing and Information TechnologyKing Abdulaziz UniversityRabighSaudi Arabia Department of Computer Science and Engineering K.S.Rangasamy College of TechnologyTiruchengode637215Tamil NaduIndia Department of Computer Science and Engineering PSN College of Engineering and TechnologyTirunelveli627152Tamil NaduIndia

Wireless Sensor Network (WSN) is an independent device that comprises a discrete collection of Sensor Nodes (SN) to sense environmental positions,device monitoring, and collection of information. Due to limited energy resourcesavailable at SN, the primary issue is to present an energy-efficient framework andconserve the energy while constructing a route path along with each sensor ***, many energy-efficient techniques focused drastically on energy harvesting and reduced energy consumption but failed to support energy-efficient routingwith minimal energy consumption in WSN. This paper presents an energy-efficientrouting system called Energy-aware Proportional Fairness Multi-user Routing(EPFMR) framework in WSN. EPFMR is deployed in the WSN environment usingthe instance time. The request time sent for the route discovery is the foremost stepdesigned in the EPFMR framework to reduce the energy consumption rate. Theproportional fairness routing in WSN selects the best route path for the packet flowbased on the relationship between the periods of requests between different *** path discovered for packet flow also measure energy on multi-user route pathusing the Greedy Instance Fair Method (GIFM). The GIFM in EPFMR developsnode dependent energy-efficient localized route path, improving the *** energy-aware framework maximizes the throughput rate and performs experimental evaluation on factors such as energy consumption rate during routing,Throughput, RST, node density and average energy per packet in WSN. The RouteSearching Time (RST) is reduced using the Boltzmann Distribution (BD), and as aresult, the energy is minimized on multi-user WSN. Finally, GIFM applies aninstance time difference-based route searching on WSN to attain an optimal energyminimization system. Experimental analysis shows that the EPFMR framework canreduce the RST by 23.47% and improve the throughput by 6.79% compared withthe state-of-the-art works.

关键词： Wireless sensor network proportional fairness multi-user routing energy consumption greedy instance fair Boltzmann distribution

Improved Multi-Path Routing for QoS on MANET

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6期45卷 2521-2536页

作者： M.Vargheese surbhi bhatia Shakila Basheer Pankaj Dadheech Department of Computer Science and Engineering PSN College of Engineering and TechnologyTirunelveli627152Tamil NaduIndia Department of Information Systems College of Computer Sciences and Information TechnologyKing Faisal UniversityAl HasaSaudi Arabia Department of Information Systems College of Computer and Information SciencePrincess Nourah bint Abdulrahman UniversityP.O.BOX 84428Riyadh11671Saudi Arabia Department of Computer Science&Engineering Swami Keshvanand Institute of TechnologyManagement&Gramothan(SKIT)Jaipur302017RajasthanIndia

A Mobile Ad hoc NETwork(MANET)is a self-configuring network that is not reliant on *** paper introduces a new multipath routing method based on the Multi-Hop Routing(MHR)*** is the consecutive selection of suitable relay nodes to send information across nodes that are not within direct range of each *** to ensure good MHR leads to several negative consequences,ultimately causing unsuccessful data transmission in a *** research work consists of three *** first to attempt to propose an efficient MHR protocol is the design of Priority Based Dynamic Routing(PBDR)to adapt to the dynamic MANET environment by reducing Node Link Failures(NLF)in the *** is achieved by dynamically considering a node’s mobility parameters like relative velocity and link duration,which enable the next-hop *** method works more efficiently than the traditional *** the second stage is the Improved Multi-Path Dynamic Routing(IMPDR).The enhancement is mainly focused on further improving the Quality of Service(QoS)in MANETs by introducing a QoS timer at every node to help in the QoS routing of *** QoS is the most vital metric that assesses a protocol,its dynamic estimation has improved network performance *** method uses distance,linkability,trust,and QoS as the four parameters for the next-hop *** is compared against traditional routing *** Network Simulator-2(NS2)is used to conduct a simulation analysis of the protocols under *** proposed tests are assessed for the Packet Delivery Ratio(PDR),Packet Loss Rate(PLR),End-to-End Delay(EED),and Network Throughput(NT).

关键词： Multi-path routing quality of service node-link failure packet delivery ratio

Optimized Resource Allocation and Queue Management for Traffic Control in MANET

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5期45卷 1323-1342页

作者： I.Ambika surbhi bhatia Shakila Basheer Pankaj Dadheech Department of Computer Science and Engineering PSN College of Engineering and TechnologyTirunelveli627152Tamil NaduIndia Department of Information College of Computer Science and Information TechnologyKing Faisal University36362Saudi Arabia Department of Information Systems College of Computer and Information SciencePrincess Nourah Bint Abdulrahman UniversityP.O.BOX 84428Riyadh11671Saudi Arabia Department of Computer Science&Engineering Swami Keshvanand Institute of TechnologyManagement&Gramothan(SKIT)Jaipur302017RajasthanIndia

A set of mobile devices that employs wireless transmission for communication is termed Mobile Ad hoc Networks(MANETs).Offering better communication services among the users in a centralized organization is the primary objective of the *** to the features of MANET,this can directly End-to-End Delay(EED)the Quality of Service(QoS).Hence,the implementation of resource management becomes an essential issue in *** paper focuses on the efficient Resource Allocation(RA)for many types of Traffic Flows(TF)in *** Mobile Ad hoc Networks environments,the main objective of Resource Allocation(RA)is to process consistently available resources among terminals required to address the service requirements of the *** three categories improve performance metrics by varying transmission rates and simulation *** solving that problem,the proposed work is divided into Queue Management(QM),Admission Control(AC)and *** effective QM,this paper develops a QM model for elastic(EL)and inelastic(IEL)Traffic *** research paper presents an AC mechanism for multiple TF for effective *** work presents a Resource Allocation Using Tokens(RAUT)for various priority TF for effective ***,nodes have three cycles which are:Non-Critical Section(NCS),Entry Section(ES)and Critical Section(CS).When a node requires any resources,it sends Resource Request Message(RRM)to the *** and inelastic TF priority is determined using Fuzzy Logic(FL).The token holder selects the node from the inelastic queue with high priority for allocating the *** Network Simulator-2(NS-2),simulations demonstrate that the proposed design increases Packet Delivery Ratio(PDR),decrease Packet Loss Ratio(PLR),minimise the Fairness and reduce the EED.

关键词： MANET resource allocation end-to-end delay fuzzy logic QoS

Fusion of Infrared and Visible Images Using Fuzzy Based Siamese Convolutional 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 5503-5518页

作者： Kanika Bhalla Deepika Koundal surbhi bhatia Mohammad Khalid Imam Rahmani Muhammad Tahir Department of Electrical Engineering National Taipei University of TechnologyTaipei10608Taiwan Department Virtualization School of Computer ScienceUniversity of Petroleum&Energy StudiesDehradunIndia College of Computer Science and Information technology King Faisal University36362Saudi Arabia College of Computing and Informatics Saudi Electronic UniversityRiyadh11673Saudi Arabia

Traditional techniques based on image fusion are arduous in integrating complementary or heterogeneous infrared(IR)/visible(VS)*** in various kind of features in these images are vital to preserve in the single fused ***,simultaneous preservation of both the aspects at the same time is a challenging ***,most of the existing methods utilize the manual extraction of features;and manual complicated designing of fusion rules resulted in a blurry artifact in the fused ***,this study has proposed a hybrid algorithm for the integration of multi-features among two heterogeneous ***,fuzzification of two IR/VS images has been done by feeding it to the fuzzy sets to remove the uncertainty present in the background and object of interest of the ***,images have been learned by two parallel branches of the siamese convolutional neural network(CNN)to extract prominent features from the images as well as high-frequency information to produce focus maps containing source image ***,the obtained focused maps which contained the detailed integrated information are directly mapped with the source image via pixelwise strategy to result in fused *** parameters have been used to evaluate the performance of the proposed image fusion by achieving 1.008 for mutual information(MI),0.841 for entropy(EG),0.655 for edge information(EI),0.652 for human perception(HP),and 0.980 for image structural similarity(ISS).Experimental results have shown that the proposed technique has attained the best qualitative and quantitative results using 78 publically available images in comparison to the existing discrete cosine transform(DCT),anisotropic diffusion&karhunen-loeve(ADKL),guided filter(GF),random walk(RW),principal component analysis(PCA),and convolutional neural network(CNN)methods.

关键词： Convolutional neural network fuzzy sets infrared and visible image fusion deep learning

Machine Learning Based Diagnosis for Diabetic Retinopathy for SKPD-PSC

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5期36卷 1767-1782页

作者： M.P.Thiruvenkatasuresh surbhi bhatia Shakila Basheer Pankaj Dadheech Department of Computer Science and Engineering Erode Sengunthar Engineering CollegePerunduraiErode638057Tamil NaduIndia Department of Information Systems College of Computer Sciences and Information TechnologyKing Faisal UniversityAl HasaSaudi Arabia Department of Information Systems College of Computer and Information SciencePrincess Nourah bint Abdulrahman UniversityP.O.BOX 84428Riyadh11671Saudi Arabia Department of Computer Science&Engineering Swami Keshvanand Institute of TechnologyManagement&Gramothan(SKIT)Jaipur302017RajasthanIndia Corresponding

The study aimed to apply to Machine Learning(ML)researchers working in image processing and biomedical analysis who play an extensive role in compre-hending and performing on complex medical data,eventually improving patient *** a novel ML algorithm speciﬁc to Diabetic Retinopathy(DR)is a chal-lenge and need of the *** images include several challenges,including relevant feature selection,class variations,and robust classiﬁ*** the cur-rent research in DR has yielded favourable results,several research issues need to be *** is a requirement to look at novel pre-processing methods to discard irrelevant features,balance the obtained relevant features,and obtain a robust classi-ﬁ*** is performed using the Steerable Kernalized Partial Derivative and Platt Scale Classiﬁer(SKPD-PSC)*** novelty of this method relies on the appropriate non-linear classiﬁcation of exclusive image processing models in har-mony with the Platt Scale Classiﬁer(PSC)to improve the accuracy of DR ***,a Steerable Filter Kernel Pre-processing(SFKP)model is applied to the Retinal Images(RI)to remove irrelevant and redundant features and extract more meaningful pathological features through Directional Derivatives of Gaussians(DDG).Next,the Partial Derivative Image Localization(PDIL)model is applied to the extracted fea-tures to localize candidate features and suppress the background ***,a Platt Scale Classiﬁer(PSC)is applied to the localized features for robust classiﬁ*** the experiments,we used the publicly available DR detection database provided by Standard Diabetic Retinopathy(SDR),called DIARETDB0.A database of 130 image samples has been collected to train and test the ML-based classiﬁ*** results show that the proposed method that combines the image processing and ML models can attain good detection performance with a high DR detection accu-racy rate with minimum time and complexity compared to

关键词： Diabetic retinopathy retinal images machine learning image localization Platt Scale classiﬁer accuracy

Simulation and Modelling of Water Injection for Reservoir Pressure Maintenance

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9期72卷 5761-5776页

作者： Rishi Dewan Adarsh Kumar Mohammad Khalid Imam Rahmani surbhi bhatia Md Ezaz Ahmed Department of Physics University of Petroleum&Energy StudiesDehradun 248007UttarakhandIndia Department of Computer Science University of Petroleum&Energy StudiesDehradun 248007UttarakhandIndia College of Computing and Informatics Saudi Electronic UniversityRiyadh 11673Saudi Arabia Department of Information Systems College of Computer Science and Information TechnologyKing Faisal UniversityAl Hasa 36362Saudi Arabia

Water injection has shown to be one of the most successful,efficient,and cost-effective reservoir management *** re-injecting treated and filtered water into reservoirs,this approach can help maintain reservoir pressure,increase hydrocarbon output,and reduce the environmental *** goal of this project is to create a water injection model utilizing Eclipse reservoir simulation software to better understand water injection methods for reservoir pressure maintenance.A basic reservoir model is utilized in this *** simulation designs,the reservoir length,breadth,and thickness may be changed to different *** water-oil contact was discovered at 7000 feet,and the reservoir pressure was recorded at 3000 pounds per square inch at a depth of 6900 *** aquifer chosen was of the Fetkovich type and was linked to the reservoir in the j+*** porosity was estimated to be varied,ranging from 9%to 16%.The residual oil saturation was set to 25%and the irreducible water saturation was set at 20%.The vertical permeability was set at 50 md as a *** Volume Temperature(PVT)data was used to estimate the gas and water characteristics.

关键词： Eclipse water injection reservoir modeling simulation oil saturation

Support Vector Machine Based Handwritten Hindi Character Recognition and Summarization

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 2022年第10期43卷 397-412页

作者： Sunil Dhankhar Mukesh Kumar Gupta Fida Hussain Memon surbhi bhatia Pankaj Dadheech Arwa Mashat Department of Computer Science&Engineering Swami Keshvanand Institute of TechnologyManagement&GramothanJaipurRajasthan302017India Department of Electrical Engineering Sukkur IBA UniversityPakistan Department of Mechatronics Engineering Jeju National UniversityJeju63243Korea Department of Information Systems College of Computer Science and Information TechnologyKing Faisal UniversitySaudi Arabia Faculty of Computing&Information Technology King Abdulaziz UniversityRabigh21911Saudi Arabia

In today’s digital era,the text may be in form of *** research aims to deal with the problem by recognizing such text and utilizing the support vector machine(SVM).A lot of work has been done on the English language for handwritten character recognition but very less work on the under-resourced Hindi language.A method is developed for identifying Hindi language characters that use morphology,edge detection,histograms of oriented gradients(HOG),and SVM classes for summary *** rank employs the summary to extract essential phrases based on paragraph position,phrase position,numerical data,inverted comma,sentence length,and keywords *** primary goal of the SVM optimization function is to reduce the number of features by eliminating unnecessary and redundant *** second goal is to maintain or improve the classification system’s *** experiment included news articles from various genres,such as Bollywood,politics,and *** proposed method’s accuracy for Hindi character recognition is 96.97%,which is good compared with baseline approaches,and system-generated summaries are compared to human *** evaluated results show a precision of 72%at a compression ratio of 50%and a precision of 60%at a compression ratio of 25%,in comparison to state-of-the-art methods,this is a decent result.

关键词： Support vector machine(SVM) optimization precision Hindi character recognition optical character recognition(OCR) automatic summarization and compression ratio

An Improved Optimized Model for Invisible Backdoor Attack Creation Using Steganography

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7期72卷 1173-1193页

作者： Daniyal M.Alghazzawi Osama Bassam J.Rabie surbhi bhatia Syed Hamid Hasan Faculty of Computing and Information Technology King Abdulaziz UniversityJeddah21589Saudi Arabia Department of Information Systems College of Computer Sciences and Information TechnologyKing Faisal UniversitySaudi Arabia

The Deep Neural Networks(DNN)training process is widely affected by backdoor *** backdoor attack is excellent at concealing its identity in the DNN by performing well on regular samples and displaying malicious behavior with data poisoning *** state-of-art backdoor attacks mainly follow a certain assumption that the trigger is sample-agnostic and different poisoned samples use the same *** overcome this problem,in this work we are creating a backdoor attack to check their strength to withstand complex defense strategies,and in order to achieve this objective,we are developing an improved Convolutional Neural Network(ICNN)model optimized using a Gradient-based Optimization(GBO)(ICNN-GBO)*** the ICNN-GBO model,we are injecting the triggers via a steganography and regularization *** are generating triggers using a single-pixel,irregular shape,and different *** performance of the proposed methodology is evaluated using different performance metrics such as Attack success rate,stealthiness,pollution index,anomaly index,entropy index,and *** the CNN-GBO model is trained with the poisoned dataset,it will map the malicious code to the target *** proposed scheme’s effectiveness is verified by the experiments conducted on both the benchmark datasets namely CIDAR-10 andMSCELEB 1M *** results demonstrate that the proposed methodology offers significant defense against the conventional backdoor attack detection frameworks such as STRIP and Neutral cleanse.

关键词： Convolutional neural network gradient-based optimization steganography backdoor attack and regularization attack