检索结果-南通市图书馆

Reducing Dataset Specificity for Deepfakes Using 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 2023年第2期74卷 4261-4276页

作者： qaiser abbas Turki Alghamdi Yazed Alsaawy Tahir Alyas Ali Alzahrani Khawar Iqbal Malik Saira Bibi Faculty of Computer and Information Systems Islamic University Madinah Madinah42351Saudi Arabia Department of Computer Science Lahore Garrison UniversityLahore54000Pakistan The University of Lahore Sargodha40100Pakistan University of Sargodha Department of Computer Science&ITSargodha40100Pakistan

The emergence of deep fake videos in recent years has made image falsification a real danger.A person’s face and emotions are deep-faked in a video or speech and are substituted with a different face or voice employing deep learning to analyze speech or emotional content.Because of how clever these videos are frequently,Manipulation is challenging to spot.Social media are the most frequent and dangerous targets since they are weak outlets that are open to extortion or slander a human.In earlier times,it was not so easy to alter the videos,which required expertise in the domain and time.Nowadays,the generation of fake videos has become easier and with a high level of realism in the video.Deepfakes are forgeries and altered visual data that appear in still photos or video footage.Numerous automatic identification systems have been developed to solve this issue,however they are constrained to certain datasets and performpoorly when applied to different datasets.This study aims to develop an ensemble learning model utilizing a convolutional neural network(CNN)to handle deepfakes or Face2Face.We employed ensemble learning,a technique combining many classifiers to achieve higher prediction performance than a single classifier,boosting themodel’s accuracy.The performance of the generated model is evaluated on Face Forensics.This work is about building a new powerful model for automatically identifying deep fake videos with the DeepFake-Detection-Challenges(DFDC)dataset.We test our model using the DFDC,one of the most difficult datasets and get an accuracy of 96%.

关键词： Deep machine learning deep fake CNN DFDC ensemble learning

Intrusion Detection in 5G Cellular Network Using Machine 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

Computer Systems Science & Engineering 2023年第11期47卷 2439-2453页

作者： Ishtiaque Mahmood Tahir Alyas Sagheer abbas Tariq Shahzad qaiser abbas Khmaies Ouahada Knowledge Unit of Systems and Technology UMT Sialkot CampusSialkot51040Pakistan Department of Computer Science Lahore Garrison UniversityLahore54000Pakistan Faculty of Computer Science National College of Business Administration and EconomicsLahore54660Pakistan Department of Electrical and Computer Engineering COMSATS University IslamabadSahiwal CampusSahiwal57000Pakistan Faculty of Computer and Information Systems Islamic University of Madinah Madinah42351Saudi Arabia Department of Computer Science&IT University of SargodhaSargodha40100Pakistan Department of Electrical and Electronic Engineering Science University of JohannesburgP.O Box 524Auckland ParkJohannesburg2006South Africa

Attacks on fully integrated servers,apps,and communication networks via the Internet of Things(IoT)are growing exponentially.Sensitive devices’effectiveness harms end users,increases cyber threats and identity theft,raises costs,and negatively impacts income as problems brought on by the Internet of Things network go unnoticed for extended periods.Attacks on Internet of Things interfaces must be closely monitored in real time for effective safety and security.Following the 1,2,3,and 4G cellular networks,the 5th generation wireless 5G network is indeed the great invasion of mankind and is known as the global advancement of cellular networks.Even to this day,experts are working on the evolution’s sixth generation(6G).It offers amazing capabilities for connecting everything,including gadgets and machines,with wavelengths ranging from 1 to 10 mm and frequencies ranging from 300 MHz to 3 GHz.It gives you the most recent information.Many countries have already established this technology within their border.Security is the most crucial aspect of using a 5G network.Because of the absence of study and network deployment,new technology first introduces new gaps for attackers and *** Protocol(IP)attacks and intrusion will become more prevalent in this system.An efficient approach to detect intrusion in the 5G network using a Machine Learning algorithm will be provided in this research.This research will highlight the high accuracy rate by validating it for unidentified and suspicious circumstances in the 5G network,such as intruder hackers/attackers.After applying different machine learning algorithms,obtained the best result on Linear Regression Algorithm’s implementation on the dataset results in 92.12%on test data and 92.13%on train data with 92%precision.

关键词： Intrusion detection system machine learning confidentiality integrity availability

Optimizing Resource Allocation Framework for Multi-Cloud Environment

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5期75卷 4119-4136页

作者： Tahir Alyas Taher M.Ghazal Badria Sulaiman Alfurhood Ghassan F.Issa Osama Ali Thawabeh qaiser abbas Department of Computer Science Lahore Garrison UniversityLahore54000Pakistan School of Information Technology Skyline University CollegeUniversity City Sharjah1797SharjahUAE Center for Cyber Security Faculty of Information Science and TechnologyUniversiti Kebansaan Malaysia(UKM)43600BangiSelangorMalaysia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11564Saudi Arabia Skyline University College University City Sharjah1797SharjahUAE Faculty of Computer and Information Systems Islamic University of Madinah Madinah42351Saudi Arabia

Cloud computingmakes dynamic resource provisioning more accessible.Monitoring a functioning service is crucial,and changes are made when particular criteria are surpassed.This research explores the decentralized multi-cloud environment for allocating resources and ensuring the Quality of Service(QoS),estimating the required resources,and modifying allotted resources depending on workload and parallelism due to resources.Resource allocation is a complex challenge due to the versatile service providers and resource providers.The engagement of different service and resource providers needs a cooperation strategy for a sustainable quality of service.The objective of a coherent and rational resource allocation is to attain the quality of service.It also includes identifying critical parameters to develop a resource allocation mechanism.A framework is proposed based on the specified parameters to formulate a resource allocation process in a decentralized multi-cloud environment.The three main parameters of the proposed framework are data accessibility,optimization,and collaboration.Using an optimization technique,these three segments are further divided into subsets for resource allocation and long-term service quality.The CloudSim simulator has been used to validate the suggested framework.Several experiments have been conducted to find the best configurations suited for enhancing collaboration and resource allocation to achieve sustained QoS.The results support the suggested structure for a decentralized multi-cloud environment and the parameters that have been determined.

关键词： Multi-cloud query optimization cloud resources allocation modelling virtualization

Performance Framework for Virtual Machine Migration in Cloud Computing

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3期74卷 6289-6305页

作者： Tahir Alyas Taher M.Ghazal Badria Sulaiman Alfurhood Munir Ahmad Ossma Ali Thawabeh Khalid Alissa qaiser abbas Department of Computer Science Lahore Garrison UniversityLahore54000Pakistan School of Information Technology Skyline University CollegeUniversity City SharjahSharjah1797UAE Center for Cyber Security Faculty of Information Science and TechnologyUniversiti Kebansaan Malaysia(UKM)Bangi43600SelangorMalaysia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversitySaudi Arabia School of Computer Science National College of Business Administration&EconomicsLahore54000Pakistan Dean of Student Affairs Skyline University CollegeUniversity City SharjahSharjah1797UAE Networks and Communications Department College of Computer Science and Information TechnologyImam Abdulrahman Bin Faisal UniversityDammam31441Saudi Arabia Faculty of Computer and Information Systems Islamic University Madinah Madinah42351Saudi Arabia

In the cloud environment,the transfer of data from one cloud server to another cloud server is called migration.Data can be delivered in various ways,from one data centre to another.This research aims to increase the migration performance of the virtual machine(VM)in the cloud environment.VMs allow cloud customers to store essential data and resources.However,server usage has grown dramatically due to the virtualization of computer systems,resulting in higher data centre power consumption,storage needs,and operating expenses.Multiple VMs on one data centre manage share resources like central processing unit(CPU)cache,network bandwidth,memory,and application bandwidth.Inmulti-cloud,VMmigration addresses the performance degradation due to cloud server configuration,unbalanced traffic load,resource load management,and fault situations during data transfer.VMmigration speed is influenced by the size of the VM,the dirty rate of the running application,and the latency ofmigration iterations.As a result,evaluating VM migration performance while considering all of these factors becomes a difficult task.Themain effort of this research is to assess migration problems on performance.The simulation results in Matlab show that if the VMsize grows,themigration time of VMs and the downtime can be impacted by three orders ofmagnitude.The dirty page rate decreases,themigration time and the downtime grow,and the latency time decreases as network bandwidth increases during the migration time and post-migration overhead calculation when the VMtransfer is completed.All the simulated cases of VMs migration were performed in a fuzzy inference system with performance graphs.

关键词： Latency cloud computing dirty page ratio storage migration performance

Acral melanoma detection using dermoscopic images and convolutional neural 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

Visual Computing for Industry,Biomedicine,and Art 2021年第1期4卷 246-257页

作者： qaiser abbas Farheen Ramzan Muhammad Usman Ghani Department of Computer Science University of Engineering and Technology54890 LahorePakistan

Acral melanoma(AM)is a rare and lethal type of skin cancer.It can be diagnosed by expert dermatologists,using dermoscopic imaging.It is challenging for dermatologists to diagnose melanoma because of the very minor differences between melanoma and non-melanoma cancers.Most of the research on skin cancer diagnosis is related to the binary classification of lesions into melanoma and non-melanoma.However,to date,limited research has been conducted on the classification of melanoma subtypes.The current study investigated the effectiveness of dermoscopy and deep learning in classifying melanoma subtypes,such as,AM.In this study,we present a novel deep learning model,developed to classify skin cancer.We utilized a dermoscopic image dataset from the Yonsei University Health System South Korea for the classification of skin lesions.Various image processing and data augmentation techniques have been applied to develop a robust automated system for AM detection.Our custombuilt model is a seven-layered deep convolutional network that was trained from scratch.Additionally,transfer learning was utilized to compare the performance of our model,where AlexNet and ResNet-18 were modified,fine-tuned,and trained on the same dataset.We achieved improved results from our proposed model with an accuracy of more than 90%for AM and benign nevus,respectively.Additionally,using the transfer learning approach,we achieved an average accuracy of nearly 97%,which is comparable to that of state-of-the-art methods.From our analysis and results,we found that our model performed well and was able to effectively classify skin cancer.Our results show that the proposed system can be used by dermatologists in the clinical decision-making process for the early diagnosis of AM.

关键词： Deep learning Acral melanoma Skin cancer detection Convolutional networks Dermoscopic images Medical image analysis Computer based diagnosis

High-Performanceα-Diimine Nickel Complexes for Facile Access of PE Elastomers with Exceptional Material Properties

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Polymer Science 2024年第5期42卷 620-635,I0008页

作者： Li-Dong Qin Xin-Yu Wang qaiser Mahmood Zhi-Xin Yu Yi-Zhou Wang Song Zou Tong-Ling Liang Wen-Hua Sun School of Pharmaceutical Sciences Changchun University of Chinese MedicineChangchun130117China Chemistry and Chemical Engineering Guangdong Laboratory Shantou515031China Key Laboratory of Engineering Plastics and Beijing National Laboratory for Molecular Science Institute of ChemistryChinese Academy of SciencesBeijing100190China

For practicable elastomeric polyethylene,achieving high catalyst thermal stability and activity,along with precise control of polymer properties such as branching density,molecular weights,and distribution,is crucial but challenging.In this study,two sets of symmetricalα-diimine nickel complexes,each comprising four nickel bromide or chloride complexes,were synthesized and investigated their performance for ethylene polymerization under various reaction conditions.Upon activation with either Et2AlCl or MMAO cocatalysts,these complexes displayed not only high activity but also generated high molecular weight polyethylenes with controlled polydispersity and a substantial number of branches.The catalyst with the least steric hindrance displayed the remarkable high activity(up to 1.2×10^(7) g·mol^(-1)·h^(-1)).Notably,nickel bromides demonstrated higher activity compared to their chloride counterparts.The investigation into the effect of reaction temperature on catalytic performance revealed that NiBrMe-MMAO system displayed high thermal stability(activity up to 2.51×10^(6) g·mol^(-1)·h^(-1) at 100℃)and consistently yielded high polymer molecular weights with narrow polydispersity over a broad temperature range of 30-100℃.Of significant note,mechanical analysis of the resulting polyethylene demonstrated excellent ultimate tensile strength and high strain at break.Particularly,the polyethylene sample prepared at 100℃exhibited ultimate tensile strength up to 10 MPa with 1863%maximum strain at break and a strain recovery of up to 54.9%after ten cycles at a fixed strain of 300%,indicating excellent material properties of prepared thermoplastic polyethylene elastomers(TPE).

关键词： Thermoplastic polyethylene elastomers α-Diimine nickel pre-catalysts Ethylene polymerization Mechanical properties Highly branched polyethylene

Efficient Process Monitoring Under General Weibull Distribution

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2022年第1期40卷 287-297页

作者： Saman Hanif Shahbaz Muhammad qaiser Shahbaz Department of Statistics King Abdulaziz UniversityJeddahKingdom of Saudi Arabia

Product testing is a key ingredient in maintaining the quality of a pro-duction process.The production process is considered an efficient process if it is capable of quick identification of faulty products.The items produced by any production process are usually packed and acceptance or rejection of the pack depends upon its conformity to some specified quality level.Generally,the specified quality level is based upon the number of defective items found in the inspected number of items.Such decisions are based upon some rules and usually acceptance of the pack is based upon a fewer number of defective items in the pack.Such questions can be answered by using acceptance sampling plans.The acceptance sampling plans assume the fact that the quality level of the item follows some probability distribution.The sampling plans based upon some classical probability distributions are available but often it happens that the quality behavior of the product does not follow a simple probability model and hence the available sampling plans fail.In this paper,we have developed acceptance sampling plans when the product life follows a general Weibull distribution.The sampling plans have been constructed by considering the crisp and fuzzy behavior of the acceptance probability.These sampling plans have been constructed by assuming an infinite lot size.It has been found that the number of items required for inspection decreases with an increase in some parameters.

关键词： General Weibull distribution sampling plans acceptance probability fuzzy plan

On Relations for Moments of Generalized Order Statistics for Lindley–Weibull Distribution

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4期41卷 197-208页

作者： Faten A.Momen khan Saman Hanif Shahbaz Muhammad qaiser Shahbaz Department of Statistics University of JeddahJeddahKingdom of Saudi Arabia Department of Statistics King Abdulaziz UniversityJeddahKingdom of Saudi Arabia

Moments of generalized order statistics appear in several areas of science and engineering.These moments are useful in studying properties of the random variables which are arranged in increasing order of importance,for example,time to failure of a computer system.The computation of these moments is sometimes very tedious and hence some algorithms are required.One algorithm is to use a recursive method of computation of these moments and is very useful as it provides the basis to compute higher moments of generalized order statistics from the corresponding lower-order moments.Generalized order statistics pro-vides several models of ordered data as a special case.The moments of general-ized order statistics also provide moments of order statistics and record values as a special case.In this research,the recurrence relations for single,product,inverse and ratio moments of generalized order statistics will be obtained for Lindley–Weibull distribution.These relations will be helpful for obtained moments of gen-eralized order statistics from Lindley–Weibull distribution recursively.Special cases of the recurrence relations will also be obtained.Some characterizations of the distribution will also be obtained by using moments of generalized order statistics.These relations for moments and characterizations can be used in differ-ent areas of computer sciences where data is arranged in increasing order.

关键词： Generalized order statistics Lindley–Weibull distribution recurrence relations moments

Fake News Encoder Classifier (FNEC) for Online Published News Related to COVID-19 Vaccines

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7期37卷 73-90页

作者： Asma qaiser Saman Hina Abdul Karim Kazi Saad Ahmed Raheela Asif Department of Computer Science and Information Technology NED University of Engineering and TechnologyKarachi75270Pakistan Department of Computer Science Iqra UniversityKarachi76400Pakistan Department of Software Engineering NED University of Engineering and TechnologyKarachi75270Pakistan

In the past few years,social media and online news platforms have played an essential role in distributing news content rapidly.Consequently.verification of the authenticity of news has become a major challenge.During the COVID-19 outbreak,misinformation and fake news were major sources of confusion and insecurity among the general public.In the first quarter of the year 2020,around 800 people died due to fake news relevant to COVID-19.The major goal of this research was to discover the best learning model for achieving high accuracy and performance.A novel case study of the Fake News Classification using ELECTRA model,which achieved 85.11%accuracy score,is thus reported in this manuscript.In addition to that,a new novel dataset called COVAX-Reality containing COVID-19 vaccine-related news has been contributed.Using the COVAX-Reality dataset,the performance of FNEC is compared to several traditional learning models i.e.,Support Vector Machine(SVM),Naive Bayes(NB),Passive Aggressive Classifier(PAC),Long Short-Term Memory(LSTM),Bi-directional LSTM(Bi-LSTM)and Bi-directional Encoder Representations from Transformers(BERT).For the evaluation of FNEC,standard metrics(Precision,Recall,Accuracy,and F1-Score)were utilized.

关键词： Deep learning fake news detection machine learning transformer model classification