检索结果-南通市图书馆

Deep Image Restoration Model: A Defense Method Against Adversarial Attacks

Computers, Materials & Continua 2022年第5期71卷 2209-2224页

作者： Kazim Ali adnan n.quershi Ahmad Alauddin Bin Arifin Muhammad Shahid Bhatti Abid Sohail Rohail Hassan Department of Information Technology University of Central PunjabLahore54000Pakistan Department of Communication Technology and network Faculty of Computer Science and Information TechnologyUniversity Putra MalaysiaSalengor43400Malaysia Department of Computer Science Comsats University IslamabadLahore Campus54000Pakistan Othman Yeop Abdullah Graduate School of Business University Utara MalaysiaKuala Lumpur50300Malaysia

These days,deep learning and computer vision are much-growing fields in this modern world of information *** learning algorithms and computer vision have achieved great success in different applications like image classification,speech recognition,self-driving vehicles,disease diagnostics,and many *** success in various applications,it is found that these learning algorithms face severe threats due to adversarial *** examples are inputs like images in the computer vision field,which are intentionally slightly changed or *** changes are humanly *** are misclassified by a model with high probability and severely affects the performance or *** this scenario,we present a deep image restoration model that restores adversarial examples so that the target model is classified correctly *** proved that our defense method against adversarial attacks based on a deep image restoration model is simple and state-of-the-art by providing strong experimental results *** have used MnIST and CIFAR10 datasets for experiments and analysis of our defense *** the end,we have compared our method to other state-ofthe-art defense methods and proved that our results are better than other rival methods.

关键词： Computer vision deep learning convolutional neural networks adversarial examples adversarial attacks adversarial defenses

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

Detection of Lung nodules on X-ray Using Transfer Learning and Manual Features

引用

Computers, Materials & Continua 2022年第7期72卷 1445-1463页

作者： Imran Arshad Choudhry adnan n.Qureshi Faculty of Information Technology University of Central PunjabLahorePakistan

The well-established mortality rates due to lung cancers,scarcity of radiology experts and inter-observer variability underpin the dire need for robust and accurate computer aided diagnostics to provide a second *** this end,we propose a feature grafting approach to classify lung cancer images from publicly available national Institute of Health(nIH)chest X-Ray dataset comprised of 30,805 unique *** performance of transfer learning with pre-trained VGG and Inception models is evaluated in comparison against manually extracted radiomics features added to convolutional neural network using custom *** classification with both approaches,Support VectorsMachines(SVM)are *** results from the 5-fold cross validation report Area Under Curve(AUC)of 0.92 and accuracy of 96.87%in detecting lung nodules with the proposed *** is a plausible improvement against the observed accuracy of transfer learning using Inception(79.87%).The specificity of allmethods is>99%,however,the sensitivity of the proposed method(97.24%)surpasses that of transfer learning approaches(n experiments amongst Random Forests,Decision Trees,and K-nearest neighbor ***,the proposed approach can be used in clinical and research environments to provide second opinions very close to the experts’intuition.

关键词： Lungs cancer convolutional neural network hand-crafted feature extraction deep learning 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

Hybridization of Cnn with LBP for Classification of Melanoma Images

引用

Computers, Materials & Continua 2022年第6期71卷 4915-4939页

作者： Saeed Iqbal adnan n.Qureshi Ghulam Mustafa Faculty of Information Technology University of Central PunjabLahorePakistan Department of Computer Sciences Bahria University Lahore CampusPakistan

Skin cancer(melanoma)is one of the most aggressive of the cancers and the prevalence has significantly increased due to increased exposure to ultraviolet ***,timely detection and management of the lesion is a critical consideration in order to improve lifestyle and reduce *** this end,we have designed,implemented and analyzed a hybrid approach entailing convolutional neural networks(Cnn)and local binary patterns(LBP).The experiments have been performed on publicly accessible datasets ISIC 2017,2018 and 2019(HAM10000)with data augmentation for in-distribution *** a novel contribution,the Cnn architecture is enhanced with an intelligible layer,LBP,that extracts the pertinent visual *** of Basal Cell Carcinoma,Actinic Keratosis,Melanoma and Squamous Cell Carcinoma has been evaluated on 8035 and 3494 cases for training and testing,*** outcomes with cross-validation depict a plausible performance with an average accuracy of 97.29%,sensitivity of 95.63%and specificity of 97.90%.Hence,the proposed approach can be used in research and clinical settings to provide second opinions,closely approximating experts’intuition.

关键词： Skin cancer convolutional neural network feature extraction local binary pattern 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

Emitter layer optimization in heterojunction bifacial silicon solar cells

引用

Journal of Semiconductors 2022年第12期43卷 65-71页

作者： adnan Shariah Feda Mahasneh Department of Physics Jordan University of Science and TechnologyIrbid 22110Jordan

Silicon solar cells continue to dominate the market,due to the abundance of silicon and their acceptable *** heterojunction with intrinsic thin layer(HIT)structure is now the dominant *** the efficiency of these cells could expand the development choices for HIT solar *** presented a detailed investigation of the emitter a-Si:H(n)lay-er of a p-type bifacial HIT solar cell in terms of characteristic parameters which include layer doping concentration,thickness,band gap width,electron affinity,hole mobility,and so *** cell composition:(ZnO/nc-Si:H(n)/a-Si:H(i)/c-Si(p)/a-Si:H(i)/nc-Si:H(p)/ZnO).The results reveal optimal values for the investigated parameters,for which the highest computed efficiency is 26.45%when lighted from the top only and 21.21%when illuminated from the back only.

关键词： HIT solar cells bifacial solar cells nano-crystalline silicon films gradient doping parameter optimization

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

Phase transformation from cubic ZnS to hexagonal ZnO by thermal annealing

引用

Journal of Semiconductors 2015年第3期36卷 19-22页

作者： K.Mahmood M.Asghar n.Amin adnan Ali Department of Physics GC University Faisalabad Department of Physics The Islamia University of Bahawalpur

We have investigated the mechanism of phase transformation from ZnS to hexagonal ZnO by high- temperature thermal annealing. The ZnS thin films were grown on Si （001） substrate by thermal evaporation system using ZnS powder as source material. The grown films were annealed at different temperatures and characterized by X-ray diffraction （XRD）, photoluminescence （PL）, four-point probe, scanning electron microscope （SEM） and energy dispersive X-ray diffraction （EDX）. The results demonstrated that as-deposited ZnS film has mixed phases but high-temperature annealing leads to transition from ZnS to ZnO. The observed result can be explained as a two- step process：（1） high-energy O atoms replaced S atoms in lattice during annealing process, and （2） S atoms diffused into substrate and/or diffused out of the sample. The dissociation energy of ZnS calculated from the Arrhenius plot of 1000/T versus log （resistivity） was found to be 3.1 eV. PL spectra of as-grown sample exhibits a characteristic green emission at 2.4 eV of ZnS but annealed samples consist of band-to-band and defect emission of ZnO at 3.29 eV and 2.5 eV respectively. SEM and EDX measurements were additionally performed to strengthen the argument.

关键词： ZnS phase transformation EDX XRD PL

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

Radiographic evaluation of vascularity in scaphoid nonunions:A review

引用

World Journal of Orthopedics 2020年第11期11卷 475-482页

作者： Hena S Cheema adnan n Cheema Department of Diagnostic Radiology University of PennsylvaniaPhiladelphiaPA 19104United States Department of Orthopaedic Surgery University of PennsylvaniaPhiladelphiaPennsylvania 19104United States

Scaphoid fractures,particularly those that occur more proximally,are unreliable in achieving union due to the retrograde blood supply of the scaphoid *** compromise is associated with the development of nonunions and avascular necrosis of the proximal *** to the tenuous blood supply of the scaphoid,it is imperative that the vascularity be assessed when creating diagnostic and treatment *** detection of vascular compromise via imaging may signal impending nonunion and allow clinicians to perform interventions that aid in restoring perfusion to the *** compromise in the scaphoid presents a diagnostic challenge,in part due to the non-specific findings on plain radiographs and computed *** resonance imaging techniques have dramatically improved our ability to assess the blood supply to the scaphoid and improve time to *** review aims to summarize these advances and highlights the importance of imaging in assessing vascular compromise in scaphoid nonunion and in reperfusion following surgical intervention.

关键词： Vascularity Perfusion Scaphoid fracture Scaphoid nonunion Scaphoid open reduction and internal fixation Bone graft

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

Defending Adversarial Examples by a Clipped Residual U-net Model

引用

Intelligent Automation & Soft Computing 2023年第2期35卷 2237-2256页

作者： Kazim Ali adnan n.Qureshi Muhammad Shahid Bhatti Abid Sohail Mohammad Hijji Department of Computer Science Faculty of Information TechnologyUniversity of Central Punjab Lahore54000Pakistan Department of Computer Science COMSAT University IslamabadLahore CampusLahore54000Pakistan Faculty of Computers and Information Technology Computer Science DepartmentUniversity of TabukTabuk47711Saudi Arabia

Deep learning-based systems have succeeded in many computer vision ***,it is found that the latest study indicates that these systems are in danger in the presence of adversarial *** attacks can quickly spoil deep learning models,e.g.,different convolutional neural networks(Cnns),used in various computer vision tasks from image classiﬁcation to object *** adversarial examples are carefully designed by injecting a slight perturbation into the clean *** proposed CRU-net defense model is inspired by state-of-the-art defense mechanisms such as Magnet defense,Generative Adversarial net-work Defense,Deep Regret Analytic Generative Adversarial networks Defense,Deep Denoising Sparse Autoencoder Defense,and Condtional Generattive Adversarial network *** have experimentally proved that our approach is better than previous defensive *** proposed CRU-net model maps the adversarial image examples into clean images by eliminating the adversarial *** proposed defensive approach is based on residual and U-net *** experiments are done on the datasets MnIST and CIFAR10 to prove that our proposed CRU-net defense model prevents adversarial example attacks in WhiteBox and BlackBox settings and improves the robustness of the deep learning algorithms especially in the computer visionﬁ*** have also reported similarity(SSIM and PSnR)between the original and restored clean image examples by the proposed CRU-net defense model.

关键词： Adversarial examples adversarial attacks defense method residual learning u-net cgan cru-et model

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

Sensitivity analysis of a dense discrete phase model for 3D simulations of a tapered fluidized bed

引用

Particuology 2024年第11期94卷 59-83页

作者： Muhammad adnan nouman Ahmad Pornpote Piumsomboon Benjapon Chalermsinsuwan Fuel Research Center Department of Chemical TechnologyFaculty of ScienceChulalongkorn UniversityBangkok10330Thailand School of Chemical and Materials Engineering National University of Sciences and TechnologyIslamabad44000Pakistan Advanced Computational Fluid Dynamics Research Unit Chulalongkorn UniversityBangkok10330Thailand

This study aims to conduct a sensitivity analysis of closure models and modeling parameters for the Dense Discrete Phase Modeling(DDPM)approach in order to investigate the hydrodynamics of a 3D lab-scale Tapered Fluidized Bed(TFB).The closure models and model parameters under investigation include the gas-solid drag force,viscous models,particle-particle interaction models,restitution coefficient,specularity coefficient,and rebound *** primary objective of this sensitivity analysis is to optimize the numerical model's *** numerical results,in terms of axial and lateral Solid Volume Fraction(SVF)profiles obtained from the sensitivity analysis,indicate that the drag force and restitution coefficient significantly influence the hydrodynamics of the *** selecting these parameters could result in the improved performance of the numerical ***,the sensitivity of turbulence models,particle-particle interaction models,specularity coefficient,and rebound coefficient has a lesser impact on the hydrodynamics *** work concludes with the recommendation of a set of closure models and modeling parameters that offer the most accurate prediction of the hydrodynamics of the TFB.

关键词： Sensitivity analysis Dense discrete phase model Sub-models Modeling parameters Tapered fluidized bed Hydrodynamics

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

Batch Preparation and Characterization of Electrospun Porous Polylactic Acid‑Based nanofiber Membranes for Antibacterial Wound Dressing

引用

Advanced Fiber Materials 2022年第4期4卷 832-844页

作者： Jing Yin Lan Xu adnan Ahmed national Engineering Laboratory for Modern Silk College of Textile and Clothing EngineeringSoochow UniversitySuzhouChina

A good wound dressing needs to promote wound healing and tissue repair when the skin is *** this study,a self-made spherical section free surface electrospinning device was used to produce large quantities of electrospun porous polylactic acid(PLA)/chitosan(CS)/aloin nanofiber membranes(nFMs)for antibacterial wound *** porous structures of PLAbased nanofibers were controlled by adjusting the weight ratios of mixed solvent and *** results showed that highquality porous PLA/CS/aloin(PCA)nFMs were obtained when the weight ratios of chloroform/n,n-dimethylformamide and PLA:CS were 90/10 and 7:1,*** porous PCA nFMs exhibited high porosity,acceptable mechanical properties,moderate hydrophobicity,good swelling property,and high water vapor transmission ***,they also showed excellent blood coagulative,antibacterial,biocompatible properties,which had the potential to be used in the application of antibacterial wound dressings.

关键词： Batch preparation Polylactic acid/chitosan/aloin nanofiber membranes Spherical section free surface electrospinning Antibacterial wound dressings

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

De-noising Brain MRI Images by Mixing Concatenation and Residual Learning(MCR)

引用

Computer Systems Science & Engineering 2023年第5期45卷 1167-1186页

作者： Kazim Ali adnan n.Qureshi Muhammad Shahid Bhatti Abid Sohail Muhammad Hijji Atif Saeed Department of Computer Science Faculty of Information TechnologyUniversity of Central Punjab LahoreLahore54000Pakistan Department of Computer Science COMSAT University IslamabadLahore CampusLahore54000Pakistan Faculty of Computers and Information Technology Computer Science DepartmentUniversity of TabukTabuk47711Saudi Arabia

Brain magnetic resonance images(MRI)are used to diagnose the different diseases of the brain,such as swelling and tumor *** quality of the brain MR images is degraded by different noises,usually salt&pepper and Gaussian noises,which are added to the MR images during the acquisition *** the presence of these noises,medical experts are facing problems in diagnosing diseases from noisy brain MR ***,we have proposed a de-noising method by mixing concatenation,and residual deep learning techniques called the MCR de-noising *** proposed MCR method is to eliminate salt&pepper and gaussian noises as much as possible from the brain MRI *** MCR method has been trained and tested on the noise quantity levels 2%to 20%for both salt&pepper and gaussian *** experiments have been done on publically available brain MRI image datasets,which can easily be accessible in the experiments and result *** Structure Similarity Index Measure(SSIM)and Peak Signal-to-noise Ratio(PSnR)calculate the similarity score between the denoised images by the proposed MCR method and the original clean ***,the Mean Squared Error(MSE)measures the error or difference between generated denoised and the original *** proposed MCR denoising method has a 0.9763 SSIM score,84.3182 PSnR,and 0.0004 MSE for salt&pepper noise;similarly,0.7402 SSIM score,72.7601 PSnR,and 0.0041 MSE for Gaussian noise at the highest level of 20%*** the end,we have compared the MCR method with the state-of-the-art de-noising filters such as median and wiener de-noising filters.

关键词： MR brain images median filter wiener filter concatenation learning residual learning MCR de-noising method

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：