检索结果-南通市图书馆

An Efficient Internet Traffic Classification System Using Deep Learning for IoT

Computers, Materials & Continua 2022年第4期71卷 407-422页

作者： Muhammad Basit Umair Zeshan Iqbal Muhammad Bilal Jamel Nebhen Tarik Adnan Almohamad Raja Majid mehmood Department of Computer Science University of Engineering and TechnologyTaxila47050Pakistan Division of Computer and Electronics Systems Engineering Hankuk University of Foreign StudiesYongin-siKorea Electrical-Electronics Engineering Department Faculty of EngineeringKarabük University78050KarabükTurkey Prince Sattam bin Abdulaziz University College of Computer Engineering and SciencesAlkharj11942Saudi Arabia Information and Communication Technology Department School of Electrical and Computer EngineeringXiamen University MalaysiaSepang43900Malaysia

Internet of Things(IoT)defines a network of devices connected to the internet and sharing a massive amount of data between each other and a central *** IoT devices are connected to a network therefore prone to *** management tasks and network operations such as security,intrusion detection,Quality-of-Service provisioning,performance monitoring,resource provisioning,and traffic engineering require traffic *** to the ineffectiveness of traditional classification schemes,such as port-based and payload-based methods,researchers proposed machine learning-based traffic classification systems based on shallow neural ***,machine learning-based models incline to misclassify internet traffic due to improper feature *** this research,an efficient multilayer deep learning based classification system is presented to overcome these challenges that can classify internet *** examine the performance of the proposed technique,Moore-dataset is used for training the *** proposed scheme takes the pre-processed data and extracts the flow features using a deep neural network(DNN).In particular,the maximum entropy classifier is used to classify the internet *** experimental results show that the proposed hybrid deep learning algorithm is effective and achieved high accuracy for internet traffic classification,i.e.,99.23%.Furthermore,the proposed algorithm achieved the highest accuracy compared to the support vector machine(SVM)based classification technique and k-nearest neighbours(KNNs)based classification technique.

关键词： Deep learning internet traffic classification network traffic management QoS aware application classification

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Enhancing Collaborative and Geometric Multi-Kernel Learning Using Deep Neural Network

引用

Computers, Materials & Continua 2022年第9期72卷 5099-5116页

作者： Bareera Zafar Syed Abbas Zilqurnain naqvi Muhammad Ahsan Allah Ditta Ummul Baneen Muhammad Adnan Khan Department of Mechatronics and Control Engineering University of Engineering and TechnologyLahore54890Pakistan Department of Information Sciences Division of Science and TechnologyUniversity of EducationLahore54000Pakistan Riphah School of Computing&Innovation Faculty of ComputingRiphah International UniversityLahore CampusLahore54000Pakistan Department Software Gachon UniversitySeongnam13120Korea

This research proposes a method called enhanced collaborative andgeometric multi-kernel learning (E-CGMKL) that can enhance the CGMKLalgorithm which deals with multi-class classification problems with non-lineardata distributions. CGMKL combines multiple kernel learning with softmaxfunction using the framework of multi empirical kernel learning (MEKL) inwhich empirical kernel mapping (EKM) provides explicit feature constructionin the high dimensional kernel space. CGMKL ensures the consistent outputof samples across kernel spaces and minimizes the within-class distance tohighlight geometric features of multiple classes. However, the kernels constructed by CGMKL do not have any explicit relationship among them andtry to construct high dimensional feature representations independently fromeach other. This could be disadvantageous for learning on datasets with complex hidden structures. To overcome this limitation, E-CGMKL constructskernel spaces from hidden layers of trained deep neural networks (DNN).Due to the nature of the DNN architecture, these kernel spaces not onlyprovide multiple feature representations but also inherit the compositionalhierarchy of the hidden layers, which might be beneficial for enhancing thepredictive performance of the CGMKL algorithm on complex data withnatural hierarchical structures, for example, image data. Furthermore, ourproposed scheme handles image data by constructing kernel spaces from aconvolutional neural network (CNN). Considering the effectiveness of CNNarchitecture on image data, these kernel spaces provide a major advantageover the CGMKL algorithm which does not exploit the CNN architecture forconstructing kernel spaces from image data. Additionally, outputs of hiddenlayers directly provide features for kernel spaces and unlike CGMKL, do notrequire an approximate MEKL framework. E-CGMKL combines the consistency and geometry preserving aspects of CGMKL with the compositionalhierarchy of kernel spaces extracted from DNN hidde

关键词： CGMKL multi-class classification deep neural network multiplekernel learning hierarchical kernel spaces

来源：

维普期刊数据库评论

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 Traffic Surveillance through Multi-Label Semantic Segmentation and Filter-Based Tracking

引用

Computers, Materials & Continua 2023年第9期76卷 3707-3725页

作者： Asifa mehmood Qureshi Nouf Abdullah Almujally Saud S.Alotaibi Mohammed Hamad Alatiyyah Jeongmin Park Department of Creative Technologies Air UniversityIslamabad44000Pakistan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Information Systems Department Umm Al-Qura UniversityMakkahSaudi Arabia Department of Computer Science College of Sciences and Humanities in AflajPrince Sattam Bin Abdulaziz UniversityAl-KharjSaudi Arabia Department of Computer Engineering Tech University of KoreaSiheung-siGyeonggi-do15073Korea

Road congestion,air pollution,and accident rates have all increased as a result of rising traffic density andworldwide population *** the past ten years,the total number of automobiles has increased significantly over the *** this paper,a novel method for intelligent traffic surveillance is *** proposed model is based on multilabel semantic segmentation using a random forest classifier which classifies the images into five *** improve the results,mean-shift clustering was applied to the segmented ***,the pixels given the label for the vehicle were extracted and blob detection was applied to mark each *** the validation of each detection,a vehicle verification method based on the structural similarity index is *** tracking of vehicles across the image frames is done using the Identifier(ID)assignment technique and particle ***,vehicle counting in each frame along with trajectory estimation was done for each *** proposed system demonstrated a remarkable vehicle detection rate of 0.83 over Vehicle Aerial Imaging from Drone(VAID),0.86 over AU-AIR,and 0.75 over the Unmanned Aerial Vehicle Benchmark Object Detection and Tracking(UAVDT)dataset during the experimental *** proposed system can be used for several purposes,such as vehicle identification in traffic,traffic density estimation at intersections,and traffic congestion sensing on a road.

关键词： Traffic surveillance multi-label segmentation random forest particle filter computer vision

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Hybrid Approach for Network Intrusion Detection

引用

Computers, Materials & Continua 2022年第1期70卷 91-107页

作者： Mavra mehmood Talha Javed Jamel Nebhen Sidra Abbas Rabia Abid Giridhar Reddy Bojja Muhammad Rizwan Department of Computer Science Kinnaird College for WomenLahore54000Pakistan ASET Labs IslamabadPakistan Prince Sattam bin Abdulaziz University College of Computer Science and EngineeringAlkharj11942Saudi Arabia College of Business and Information Systems Dakota State UniversityMadisonUnited States of America

Due to the widespread use of the internet and smart devices,various attacks like intrusion,zero-day,Malware,and security breaches are a constant threat to any organization’s network ***,a Network Intrusion Detection System(NIDS)is required to detect attacks in network *** paper proposes a new hybrid method for intrusion detection and attack *** proposed approach comprises three steps to address high false and low false-negative rates for intrusion detection and attack *** the first step,the dataset is preprocessed through the data transformation technique and min-max ***,the random forest recursive feature elimination method is applied to identify optimal features that positively impact the model’s ***,we use various Support Vector Machine(SVM)types to detect intrusion and the Adaptive Neuro-Fuzzy System(ANFIS)to categorize probe,U2R,R2U,and DDOS *** validation of the proposed method is calculated through Fine Gaussian SVM(FGSVM),which is 99.3%for the binary *** Square Error(MSE)is reported as 0.084964 for training data,0.0855203 for testing,and 0.084964 to validate multiclass categorization.

关键词： Network security intrusion detection system machine learning attacks data mining classification feature selection

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Recycled materials in railroad substructure: an energy perspective

引用

Railway Engineering Science 2022年第3期30卷 304-322页

作者： Buddhima Indraratna Yujie Qi Rakesh Sai Malisetty Sinniah KNavaratnarajah Fatima mehmood Miriam Tawk Transport Research Centre School of Civil and Environmental EngineeringFaculty of Engineering and Information TechnologyUniversity of Technology SydneySydneyNSW 2007Australia Department of Civil Engineering Faculty of EngineeringUniversity of PeradeniyaPeradeniyaSri Lanka School of Civil Mining and Environmental EngineeringUniversity of WollongongWollongongNSW 2522Australia College of Engineering and Technology American University of the Middle EastEgailaKuwait

Given that the current ballasted tracks in Australia may not be able to support faster and significantly heavier freight trains as planned for the future,the imminent need for innovative and sustainable ballasted tracks for transport infrastructure is *** the past two decades,a number of studies have been conducted by the researchers of Transport Research Centre(TRC)at the University of Technology Sydney(UTS)to investigate the ability of recycled rubber mats,as well as waste tyre cells and granulated rubber to improve the stability of track substructure including ballast and subballast *** paper reviews four applications of these novel methods,including using recycled rubber products such as CWRC mixtures(i.e.,mixtures of coal wash(CW)and rubber crumbs(RC))and SEAL mixtures(i.e.,mixtures of steel furnace slag,CW and RC)to replace subballast/capping materials,tyre cells reinforcements for subballast/capping layer and under ballast mats;and investigates the energy dissipation capacity for each application based on smallscale cyclic triaxial tests and large-scale track model *** has been found that the inclusion of these rubber products increases the energy dissipation effect of the track,hence reducing the ballast degradation efficiently and increasing the track ***,a rheological model is also proposed to investigate the effect of different rubber inclusions on their efficiency to reduce the transient motion of rail track under dynamic *** outcomes elucidated in this paper will lead to a better understanding of the performance of ballast tracks upgraded with resilient rubber products,while promoting environmentally sustainable and more affordable ballasted tracks for greater passenger comfort and increased safety.

关键词： Ballast degradation Recycled rubber Energy dissipation Laboratory testing Rheological model

来源：

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

Profiling Casualty Severity Levels of Road Accident Using Weighted Majority Voting

引用

Computers, Materials & Continua 2022年第6期71卷 4609-4626页

作者： Saba Awan Zahid mehmood Hassan Nazeer Chaudhry Usman Tariq Amjad Rehman Tanzila Saba Muhammad Rashid Department of Software Engineering University of Engineering and TechnologyTaxila47050Pakistan Department of Computer Engineering University of Engineering and TechnologyTaxila47050Pakistan Department of Electronics Information and BioengineeringPolitecnico di MilanoMilano20122Italy College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia College of Computer and Information Sciences Prince Sultan UniversityRiyadhSaudi Arabia Department of Computer Engineering Umm Al-Qura UniversityMakkah21421Saudi Arabia

To determine the individual circumstances that account for a road traffic accident,it is crucial to consider the unplanned connections amongst various factors related to a crash that results in high casualty *** of the road accident data concentrated mainly on categorizing accidents into different types using individually built classification methods which limit the prediction accuracy and fitness of the *** this article,we proposed a multi-model hybrid framework of the weighted majority voting(WMV)scheme with parallel structure,which is designed by integrating individually implemented multinomial logistic regression(MLR)and multilayer perceptron(MLP)classifiers using three different accident datasets i.e.,IRTAD,NCDB,and *** proposed WMV hybrid scheme overtook individual classifiers in terms of modern evaluation measures like ROC,RMSE,Kappa rate,classification accuracy,and performs better than state-of-theart approaches for the prediction of casualty severity ***,the proposed WMV hybrid scheme adds up to accident severity analysis through knowledge representation by revealing the role of different accident-related factors which expand the risk of casualty in a road *** aspects related to casualty severity recognized by the proposed WMV hybrid approach can surely support the traffic enforcement agencies to develop better road safety plans and ultimately save lives.

关键词： Prediction hybrid framework severity class casualty

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Automated White Blood Cell Disease Recognition Using Lightweight Deep Learning

引用

Computer Systems Science & Engineering 2023年第7期46卷 107-123页

作者： Abdullah Alqahtani Shtwai Alsubai Mohemmed Sha Muhammad Attique Khan Majed Alhaisoni Syed Rameez naqvi College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversitySaudi Arabia Department of Computer Science HITEC University TaxilaTaxilaPakistan Computer Sciences Department College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia

White blood cells(WBC)are immune system cells,which is why they are also known as immune *** protect the human body from a variety of dangerous diseases and outside *** majority of WBCs come from red bone marrow,although some come from other important organs in the *** manual diagnosis of blood disorders is difficult,it is necessary to design a computerized *** have introduced various automated strategies in recent years,but they still face several obstacles,such as imbalanced datasets,incorrect feature selection,and incorrect deep model *** proposed an automated deep learning approach for classifying white blood disorders in this *** data augmentation approach is initially used to increase the size of a ***,a Darknet-53 pre-trained deep learning model is used and finetuned according to the nature of the chosen *** the fine-tuned model,transfer learning is used,and features engineering is done on the global average pooling *** retrieved characteristics are subsequently improved with a specified number of iterations using a hybrid reformed binary grey wolf optimization *** that,machine learning classifiers are used to classify the selected best features for final *** experiment was carried out using a dataset of increased blood diseases imaging and resulted in an improved accuracy of over 99%.

关键词： White blood cells augmentation deep features feature selection classification

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Changes in Germination and Seedling Traits of Sesame under Simulated Drought

引用

Phyton-International Journal of Experimental Botany 2022年第4期91卷 713-726页

作者： Mukhtar Ahmed Ahmed M.S.Kheir Muhammad Zeeshan mehmood Shakeel Ahmad Mirza Hasanuzzaman Department of Agronomy PMAS-Arid Agriculture UniversityRawalpindi46300Pakistan International Center for Biosaline Agriculture Directorate of ProgramsDubai14660United Arab Emirates Soils Water and Environment Research InstituteAgricultural Research CenterCairo UniversityGiza12613Egypt Department of Agronomy Bahauddin Zakariya UniversityMultan60800Pakistan Department of Agronomy Sher-e-Bangla Agricultural UniversityDhaka1207Bangladesh

Drought is considered one of the leading abiotic constraints to agricultural crop production *** study was conducted to assess the effects of different drought treatments(***,10%PEG,and 20%PEG)on seed germination,germination indices,seedling traits,and drought tolerance indices of *** results showed that maximum reduction in the studied parameters was observed at higher PEG concentration(i.e.,20%PEG).As compared to control,the drought treatments viz.10%and 20%PEG decreased the values for germination indices,such as germination percentage,coefficient of variation of germination time,germination index,and seedling vigor ***,for seedling traits,the values were decreased for root length,shoot length,root shoot ratio,root fresh weight,shoot fresh weight,root dry weight and shoot dry weight under 10%and 20%PEG treatments significantly in comparison with ***,relative to control,the values for drought tolerance indices,such as germination drought tolerance index,root length drought tolerance index,shoot length drought tolerance index,total seedling length drought tolerance index,root fresh weight drought tolerance index,shoot fresh weight drought tolerance index,total fresh weight drought tolerance index,root dry weight drought tolerance index,shoot dry weight drought tolerance index and total dry weight drought tolerance index were also reduced under 10%and 20%PEG treatments,*** results confirms that drought impact on seed germination and seedling traits could be quantified by using different indices which can further help to design drought adaptation and mitigation *** on these results it can be concluded that germination indices,seedling traits,and drought tolerance indices have great potential to simulate drought stress impacts on different crop traits thus they should be used in all kinds of stress related studies.

关键词： Sesame drought stress PEG germination indices seedling traits drought tolerance indices

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Comprehensive Review on Epoxy Biocomposites Based on Natural Fibers and Bio‑fillers: Challenges, Recent Developments and Applications

引用

Advanced Fiber Materials 2022年第4期4卷 683-704页

作者： Fazal Maula Khan Ahmer Hussain Shah Shuo Wang Shah mehmood Jun Wang Wenbin Liu Xiaodong Xu Technology Ministry of EducationCollege of Materials Science and Chemical EngineeringHarbin Engineering UniversityRoom 534Jichu Building145#Nantong StreetNangang DistrictHarbin 150001China Department of Textile Engineering Balochistan University of Information TechnologyEngineering and Management SciencesQuetta 87300Pakistan

Natural fiber-reinforced polymers remained a hot topic of interest in material sciences over the last two *** fibers are appealing in composite materials due to their renewability,low density,better specific strength,biodegradability,accessibility,and low *** reinforced with natural fibers provide improved mechanical performance at a lower cost and could be the best alternative to synthetic ***-fillers have gained much attention nowadays due to their cost-effectivity and the ability to modify base materials in the composite *** materials reinforced epoxy composites have a high capacity due to their eco-friendliness,economic feasibility,and technical ***,some parameters directly influence desired product *** review discusses various properties of natural fibers and their impact on the overall performance of natural fiber-based epoxy *** summarizes the recent research on natural fibers/bio-fillers reinforced epoxy biocomposites.

关键词： Biocomposites Natural fibers Bio-fillers Reinforced epoxy composites

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Recent advances in 2D organic−inorganic heterostructures for electronics and optoelectronics

引用

SmartMat 2023年第2期4卷 37-68页

作者： Jahangir Khan Rana Tariq mehmood Ahmad Junyang Tan Rongjie Zhang Usman Khan Bilu Liu Shenzhen Geim Graphene Center Tsinghua‐Berkeley Shenzhen Institute&Institute of Materials ResearchTsinghua Shenzhen International Graduate SchoolTsinghua UniversityShenzhenChina Department of Electrical Engineering Narowal CampusUniversity of Engineering and TechnologyLahorePakistan Institute of Functional Porous Materials School of Materials Science and EngineeringZhejiang Sci‐Tech UniversityHangzhouChina

Two‐dimensional(2D)materials show outstanding properties such as dangling bond‐free surfaces,strong in‐plane while weak out‐of‐plane bonding,layer‐dependent electronic structures,and tunable electronic and optoelectronic properties,making them promising for numerous *** 2D inorganics with organic materials to make van der Waals heterostructures at the 2D thickness limit has created new platforms for fabricating on‐demand multifunctional *** further broaden the limited choices of 2D inorganic‐based heterostructures,a wide range of available 2D organic materials with tunable properties have opened new opportunities for designing large numbers of heterostructures with 2D inorganic *** review aims to attract the attention of researchers toward this emerging 2D organic−inorganic *** first highlight recent progress in organic−inorganic heterostructures and their synthesis and then discuss their potential applications,such as field‐effect transistors,photodetectors,solar cells,and neuromorphic computing *** the end,we present a summary of challenges and opportunities in this field.

关键词： 2D materials 2D organic−inorganic heterostructures electronics inorganic materials optoelectronics organic materials synthesis

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：