检索结果-南通市图书馆

Handling Class Imbalance in Online Transaction Fraud Detection

Computers, Materials & Continua 2022年第2期70卷 2861-2877页

作者： Kanika Jimmy Singla ali Kashif Bashir Yunyoung Nam Najam UI Hasan usman Tariq School of Computer Science and Engineering Lovely Professional UniversityPunjabIndia Department of Computing and Mathematics ManchesterMetropolitan UniversityUK&School of Electrical Engineering and Computer ScienceNational University of Science and TechnologyIslamabadPakistan Department of Computer Science and Engineering Soonchunhyang UniversityAsan31538Korea Department of Electrical and Computer Engineering Dhofar UniversitySalalahOman College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia

With the rise of internet facilities,a greater number of people have started doing online transactions at an exponential rate in recent years as the online transaction system has eliminated the need of going to the bank physically for every ***,the fraud cases have also increased causing the loss of money to the ***,an effective fraud detection system is the need of the hour which can detect fraudulent transactions automatically in ***,the genuine transactions are large in number than the fraudulent transactions which leads to the class imbalance *** this research work,an online transaction fraud detection system using deep learning has been proposed which can handle class imbalance problem by applying algorithm-level methods which modify the learning of the model to focus more on the minority class i.e.,fraud transactions.A novel loss function named Weighted Hard-Reduced Focal Loss(WH-RFL)has been proposed which has achieved maximum fraud detection rate i.e.,True PositiveRate(TPR)at the cost of misclassification of few genuine transactions as high TPR is preferred over a high True Negative Rate(TNR)in fraud detection system and same has been demonstrated using three publicly available imbalanced transactional ***,Thresholding has been applied to optimize the decision threshold using cross-validation to detect maximum number of frauds and it has been demonstrated by the experimental results that the selection of the right thresholding method with deep learning yields better results.

关键词： Class imbalance deep learning fraud detection loss function thresholding

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

Photocatalysis vs adsorption by metal oxide nanoparticles

引用

Journal of Materials Science & Technology 2022年第36期131卷 122-166页

作者： usman Qumar Jahan Zeb Hassan Rukhsar Ahmad Bhatti ali Raza Ghazanfar Nazir Walid Nabgan Muhammad Ikram Solar Cell Applications Research Lab Department of PhysicsGovernment College University Lahore54000 PunjabPakistan Department of Physics University of Lahore(Chenab Campus)Adjacent Chenab BridgeGujrat50700 PunjabPakistan Department of Physics University of Sialkot(USKT)1-Km Main Daska RoadSialkot51040 PunjabPakistan Department of Nanotechnology and Advanced Materials Engineering Sejong UniversitySeoul 05006Republic of Korea Departament d’Enginyeria Química Universitat Rovira i VirgiliAv Països Catalans 2643007 TarragonaSpain.

Background:Metal oxide(MO)nanomaterials and related nanocomposites have been extensively studied for their potential use in water *** of their controlled morphologies,texture qualities,variable surface chemistry,distinct crystalline nature,high stability,and tunable band edges,MO nanostructured materials are highly selective towards deleting organic contaminants and heavy metal ions via adsorption and semiconductor ***-enhanced photocatalysis has recently received increasing interest,mainly due to the ability of the metal to directly or indirectly degrade pollutants.A diverse selection of MOs,with titanium dioxide(Ti O2),zinc oxide(Zn O),iron oxides(IO),and tungsten(W),as well as graphene-MOs nanocomposites with variable structure,crystalline,and morphological properties,offers a powerful platform for the growth of effective ***:The current work discusses novel advancements and potential for the removal of adsorptive and photocatalytic degradation of organic compounds(phenolic,pesticide molecules,dyes,and so on)as well as heavy metal ions using semiconductor materials.A photocatalyst based on a MO-scheme heterostructure can manage the appropriate conduction band(CB)and valence band(VB)locations,securing considerable redox *** review should be of interest to the broad readership dealing with applied and fundamental aspects of water treatments and material *** strategies including surface modification,plasmonic enhancement,and metal cocatalysts have been introduced to enhance photocatalytic *** findings:The current article discussed the significantly utilized synthesis strategies and mechanism of heterojunction photocatalysts using a ***,adsorption sections guarantee that mercury,chromium,cadmium,arsenic,and lead-based ions are successfully removed from polluted water via the adsorption *** characteristics,such as concentration,coexisting ions,p H,and ki

关键词： Photocatalyst Adsorbate Metal Oxides Z-scheme Surface Modification Heterojunction Semiconductor heterostructures Nanoparticles

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

Perovskite-type lanthanum ferrite based photocatalysts:Preparation,properties,and applications

引用

Journal of Energy Chemistry 2022年第3期31卷 314-338,I0009页

作者： Muhammad Humayun Habib Ullah Muhammad usman Aziz Habibi-Yangjeh Asif ali Tahir Chundong Wang Wei Luo School of Optical and Electronic Information Wuhan National Laboratory for OptoelectronicsEngineering Research Center for Functional Ceramics of the Ministry of EducationHuazhong University of Science and TechnologyWuhan 430074HubeiChina Environment and Sustainability Institute University of ExeterPenryn TR109FECornwallUnited Kingdom Center of Research Excellence in Nanotechnology King Fahd University of Petroleum and Minerals(KFUPM)Dhahran 31261Saudi Arabia Department of Chemistry Faculty of ScienceUniversity of Mohaghegh ArdabiliArdabili P.O.Box 179ArdabilIran

Clean energy and a sustainable environment are grand challenges that the world is facing which can be addressed by converting solar energy into transportable and storable fuels(chemical fuel).The main scientific and technological challenges for efficient solar energy conversion,energy storage,and environmental applications are the stability,durability,and performance of low-cost functional *** different nanomaterials,perovskite type LaFeO_(3)has been extensively investigated as a photocatalyst due to its abundance,high stability,compositional and structural fexibility,high electrocatalytic activity,efficient sunlight absorption,and tunable band gap and band ***,it is urgent to write a comprehensive review to highlight the trend,challenges,and prospects of LaFeO_(3)in the field of photocatalytic solar energy conversion and environment *** critical review summarizes the history and basic principles of ***,it reviews in detail the LaFeO_(3),applications,shortcomings,and activity enhancement strategies including the design of nanostructures,elemental doping,and heterojunctions construction such as Type-I,Type-II,Z-Type,and uncommon ***,the optical and electronic properties,charge carriers separation,electron transport phenomenon and alignment of the band gaps in LaFeO_(3)-based heterostructures are comprehensively discussed.

关键词： Perovskite-type LaFeO_(3) Solar fuel Photocatalysis Doping Heterostructures

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

Two-Mode Biomedical Sensor Build-up:Characterization of Optical Amplifier

引用

Computers, Materials & Continua 2022年第3期70卷 5487-5501页

作者： usman Masud Fathe Jeribi Mohammed Alhameed Faraz Akram ali Tahir Mohammad Yousaf Naudhani Faculty of Electrical and Electronics Engineering University of Engineering and TechnologyTaxila47050Pakistan Department of Electrical Communication Engineering University of KasselKassel34127Germany College of Computer Science&Information Technology Jazan UniversityJazan45142Saudi Arabia Faculty of Engineering and Applied Sciences Riphah International UniversityIslamabad44000Pakistan Faculty of Information&Communication Technology Balochistan University of Information TechnologyEngineering and Management SciencesQuetta

Intracavity absorption spectroscopy is a strikingly sensitive technique that has been integrated with a two-wavelength setup to develop a sensor for human *** factors are considered in such a scenario,out of which Relative Intensity Noise(RIN)has been exploited as an important parameter to characterize and calibrate the said *** the performance of an electrical based assessment arrangement which has been developed in the laboratory as an alternative to the expensive Agilent setup,the optical amplifier plays a pivotal role in its development and operation,along with other components and their ***,the investigation and technical analysis of the amplifier in the system has been explored in *** algorithm developed for the automatic measurements of the system has been effectively deployed in terms of the laser’s *** this in perspective,a frequency dependent calibration has been pursued in depth with this scheme which enhances the sensor’s efficiency in terms of its *** this way,our investigation helps us in a better understanding and implementation perspective of the proposed system,as the outcomes of our analysis adds to the precision and accuracy of the entire system.

关键词： Biomedical sensor cavity optomechanics spectroscopy relative intensity noise semiconductor laser diode

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

Adaptive Runtime Monitoring of Service Level Agreement Violations in Cloud Computing

引用

Computers, Materials & Continua 2022年第6期71卷 4199-4220页

作者： Sami Ullah Khan Babar Nazir Muhammad Hanif Akhtar ali Sardar Alam usman Habib Department of Computer Science COMSATS UniversityAbbottabad CampusPakistan Faculty of Computer Science and Engineering Ghulam Ishaq Khan(GIK)Institute of Engineering Sciences and Technology TopiPakistan IFahja Pvt Limited PeshawarPakistan Department of Computer Science National University of Computer and Emerging Sciences IslamabadChiniot-Faisalabad CampusPakistan

The cloud service level agreement(SLA)manage the relationship between service providers and consumers in cloud *** is an integral and critical part of modern era IT vendors and communication *** to low cost and flexibility more and more consumers delegate their tasks to cloud providers,the SLA emerges as a key aspect between the consumers and *** monitoring of Quality of Service(QoS)attributes is required to implement SLAs because of the complex nature of cloud *** other factors,such as user reliability,satisfaction,and penalty on violations are also taken into ***,there is no such policy of cloud SLA monitoring to minimize SLA *** this work,we have proposed a cloud SLA monitoring policy by dividing a monitoring session into two parts,for critical and non-critical *** critical and non-critical parameters will be decided on the interest of the consumer during SLA *** will help to shape a new comprehensive SLA based Proactive Resource Allocation Approach(RPAA)which will monitor SLA at runtime,analyze the SLA parameters and try to find the possibility of SLA *** also have implemented an adaptive system for allocating cloud IT resources based on SLA violations and *** have defined two main components of SLA-PRAA i.e.,(a)Handler and(b)Accounting and Billing *** have also described the function of both components through *** experimental results validate the performance of our proposed method in comparison with state-of-the-art cloud SLA policies.

关键词： Energy consumption penalty calculation proactive resource allocation service level agreement(SLA)monitoring SLA violation detection

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

PAN-DeSpeck:A Lightweight Pyramid and Attention-Based Network for SAR Image Despeckling

引用

Computers, Materials & Continua 2023年第9期76卷 3671-3689页

作者： Saima Yasmeen Muhammad usman Yaseen Syed Sohaib ali Moustafa M.Nasralla Sohaib Bin Altaf Khattak Department of Computer Sciences Comsats UniversityIslamabadPakistan Department of Research and Development Shearwater GeoservicesCrawleyWest SussexUK Department of Communications&Networks Engineering Prince Sultan UniversityRiyadhSaudi Arabia

SAR images commonly suffer fromspeckle noise,posing a significant challenge in their analysis and *** convolutional neural network(CNN)based despeckling methods have shown great performance in removing speckle ***,these CNN-basedmethods have a *** do not decouple complex background information in ***,they have deep network structures thatmay result in many parameters,limiting their applicability tomobile ***,extracting key speckle information in the presence of complex background is also a major problem with *** proposed study addresses these limitations by introducing a lightweight pyramid and attention-based despeckling(PAN-Despeck)*** primary objective is to enhance image quality and enable improved information interpretation,particularly on mobile devices and scenarios involving complex *** PAN-Despeck network leverages domainspecific knowledge and integrates Gaussian Laplacian image pyramid decomposition for multi-resolution image *** utilizing this approach,complex background information can be effectively decoupled,leading to enhanced despeckling ***,the attention mechanism selectively focuses on key speckle features and facilitates complex background *** network incorporates recursive and residual blocks to ensure computational efficiency and accelerate training speed,making it lightweight while maintaining high *** comprehensive evaluations,it is demonstrated that PAN-Despeck outperforms existing image restoration *** an impressive average peak signal-to-noise ratio(PSNR)of 28.355114 and a remarkable structural similarity index(SSIM)of 0.905467,it demonstrates exceptional performance in effectively reducing speckle noise in SAR *** source code for the PAN-DeSpeck network is available on GitHub.

关键词： Synthetic Aperture Radar(SAR) SAR image despeckling speckle noise deep learning pyramid networks multiscale image despeckling

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 Cascaded Design of Best Features Selection for Fruit Diseases Recognition

引用

Computers, Materials & Continua 2022年第1期70卷 1491-1507页

作者： Faiz ali Shah Muhammad Attique Khan Muhammad Sharif usman Tariq Aimal Khan Seifedine Kadry Orawit Thinnukool Department of Computer Science COMSATS University IslamabadWah Campus47080Pakistan Department of Computer Science HITEC University TaxilaTaxila47040Pakistan College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz UniversityAl-KhrajSaudi Arabia National University of Science and Technology Islamabad IslamabadPakistan Faculty of Applied Computing and Technology Noroff University CollegeKristiansandNorway Research Group of Embedded Systems and Mobile Application in Health Science College of ArtsMedia and TechnologyChiang Mai UniversityChiang Mai50200Thailand

Fruit diseases seriously affect the production of the agricultural sector,which builds financial pressure on the country’s *** manual inspection of fruit diseases is a chaotic process that is both time and cost-consuming since it involves an accurate manual inspection by an ***,it is essential that an automated computerised approach is developed to recognise fruit diseases based on leaf *** to the literature,many automated methods have been developed for the recognition of fruit diseases at the early ***,these techniques still face some challenges,such as the similar symptoms of different fruit diseases and the selection of irrelevant *** processing and deep learning techniques have been extremely successful in the last decade,but there is still room for improvement due to these ***,we propose a novel computerised approach in this work using deep learning and featuring an ant colony optimisation(ACO)based *** proposed method consists of four fundamental steps:data augmentation to solve the imbalanced dataset,fine-tuned pretrained deep learning models(NasNetMobile andMobileNet-V2),the fusion of extracted deep features using matrix length,and finally,a selection of the best features using a hybrid ACO and a Neighbourhood Component Analysis(NCA).The best-selected features were eventually passed to many classifiers for final *** experimental process involved an augmented dataset and achieved an average accuracy of 99.7%.Comparison with existing techniques showed that the proposed method was effective.

关键词： Fruits diseases data augmentation deep learning features fusion 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

Efficient Facial Recognition Authentication Using Edge and Density Variant Sketch Generator

引用

Computers, Materials & Continua 2022年第1期70卷 505-521页

作者： Summra Saleem M.usman Ghani Khan Tanzila Saba Ibrahim Abunadi Amjad Rehman Saeed ali Bahaj Department of Computer Science UETLahorePakistan Al-Khwarizmi Institute of Computer Science UETLahorePakistan Artificial Intelligence&Data Analytics Lab CCIS Prince Sultan University Riyadh11586Saudi Arabia MIS Department College of Business Administration Prince Sattam Bin Abdulaziz UniversityAlkharjSaudi Arabia

Image translation plays a significant role in realistic image synthesis,entertainment tasks such as editing and colorization,and security including personal *** Edge GAN,the major contribution is attribute guided vector that enables high visual quality content *** research study proposes automatic face image realism from freehand sketches based on Edge *** propose a density variant image synthesis model,allowing the input sketch to encompass face features with minute *** density level is projected into non-latent space,having a linear controlled function *** assists the user to appropriately devise the variant densities of facial sketches and image *** data set of Large Scale CelebFaces Attributes(ClebA),Labelled Faces in theWild(LFWH),Chinese University of Hong Kong(CHUK),and self-generated Asian images are used to evaluate the proposed *** solution is validated to have the capability for generating realistic face images through quantitative and qualitative results and human evaluation.

关键词： Edge generator density variant sketch generator face translation recognition residual block

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

Triple Key Security Algorithm Against Single Key Attack on Multiple Rounds

引用

Computers, Materials & Continua 2022年第9期72卷 6061-6077页

作者： Muhammad Akram Muhammad Waseem Iqbal Syed Ashraf ali Muhammad usman Ashraf Khalid Alsubhi Hani Moaiteq Aljahdali Department of Computer Science Superior University Lahore54000Pakistan Department of Software Engineering Superior University Lahore54000Pakistan Department of Computer Science The Institute of Management Sciences(PAK-AIMS)Lahore54000Pakistan Department of Computer Science GC Women University SialkotPakistan Department of Computer Science King Abdulaziz UniversityJeddahSaudi Arabia Faculty of Computing and Information Technology King Abdulaziz UniversityJeddahSaudi Arabia

In cipher algorithms,the encryption and decryption are based on the same *** are some limitations in cipher algorithms,for example in polyalphabetic substitution cipher the key size must be equal to plaintext otherwise it will be repeated and if the key is known then encryption becomes *** paper aims to improve the said limitations by designing of Triple key security algorithm(TKS)in which the key is modified on polyalphabetic substitution cipher to maintain the size of the key and *** plaintext character is substituted by an alternative *** mode of substitution is transformed cyclically which depends on the current position of the modified *** keys are used in the encryption and decryption process on 8 or 16 rounds with the Exclusively-OR(XOR)of the 1st *** study also identifies a single-key attack on multiple rounds block cipher in mobile communications and applied the proposed technique to prevent the *** utilization of the TKS algorithm,the decryption is illustrated,and security is analyzed in detail with mathematical examples.

关键词： Encryption decryption cipher symmetric key cryptography single key attack

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

Human Gait Recognition Based on Sequential Deep Learning and Best Features Selection

引用

Computers, Materials & Continua 2023年第6期75卷 5123-5140页

作者： Ch Avais Hanif Muhammad ali Mughal Muhammad Attique Khan usman Tariq Ye Jin Kim Jae-Hyuk Cha Department of Electrical Engineering HITEC UniversityTaxilaPakistan Department of Computer Science HITEC UniversityTaxilaPakistan College of Computer Engineering and Science Prince Sattam Bin Abdulaziz UniversityAl-Kharaj11942Saudi Arabia Department of Computer Science Hanyang UniversitySeoul04763Korea

Gait recognition is an active research area that uses a walking theme to identify the subject *** Gait Recognition(HGR)is performed without any cooperation from the ***,in practice,it remains a challenging task under diverse walking sequences due to the covariant factors such as normal walking and walking with wearing a ***,over the years,have worked on successfully identifying subjects using different techniques,but there is still room for improvement in accuracy due to these covariant *** paper proposes an automated model-free framework for human gait recognition in this *** are a few critical steps in the proposed ***,optical flow-based motion region esti-mation and dynamic coordinates-based cropping are *** second step involves training a fine-tuned pre-trained MobileNetV2 model on both original and optical flow cropped frames;the training has been conducted using static *** third step proposed a fusion technique known as normal distribution serially *** the fourth step,a better optimization algorithm is applied to select the best features,which are then classified using a Bi-Layered neural *** publicly available datasets,CASIA A,CASIA B,and CASIA C,were used in the experimental process and obtained average accuracies of 99.6%,91.6%,and 95.02%,*** proposed framework has achieved improved accuracy compared to the other methods.

关键词： Human gait recognition optical flow deep learning features fusion 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

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：