检索结果-内蒙古大学图书馆

Automatic Crack Locating Algorithm Using a convolution kernel Based on Eddy Current Field for the Fractal Planar Eddy Current Probe

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Chen, Guolong Fan, Le He, Jing Shi, Jianfei Li, Jianhua Jin, Wuyin Lanzhou Univ Technol Sch Mech & Elect Engn Lanzhou 730050 Peoples R China

The quantitative evaluation of defects is one of the challenges of eddy current (EC) testing. Efficient algorithm that requires a small amount of time and hardware resources is needed. In this article, based on the principle of the interaction between the EC field and the cracks, a ternary convolution kernel convolution algorithm based on an EC field is proposed to process the C-scan signal of the planar Koch EC sensor and locate the 28 cracks. The proposed algorithm comprises three steps: convolution kernel preparation, signal preprocessing, and convolution and positioning. The absolute and relative errors of the position relation between the #1 and the other cracks were less than 1.95 mm and 2.61%, respectively. This algorithm can be used for differential EC sensors to auto-locate the crack.

关键词： Probes convolution kernel Coils Training Fractals Eddy current testing Image reconstruction Shape Imaging convolution kernel crack positioning eddy current testing (ECT) fractal EC probe fractal geometry NDT

来源：评论

学校读者我要写书评

暂无评论

convolution kernel and iterative reconstruction affect the diagnostic performance of radiomics and deep learning in lung adenocarcinoma pathological subtypes

引用

THORACIC CANCER 2019年第10期10卷 1893-1903页

作者： Zhao, Wei Zhang, Wei Sun, Yingli Ye, Yuxiang Yang, Jiancheng Chen, Wufei Gao, Pan Li, Jianying Li, Cheng Jin, Liang Wang, Peijun Hua, Yanqing Li, Ming Fudan Univ Huadong Hosp Dept Radiol Shanghai 200040 Peoples R China Huadong Hosp Diag & Treatment Ctr Small Lung Nodules Shanghai Peoples R China Diannei Technol Shanghai Peoples R China Shanghai Jiao Tong Univ Dept Elect Engn Shanghai Peoples R China Shanghai Jiao Tong Univ SJTU UCLA Joint Ctr Machine Percept & Inference Shanghai Peoples R China GE Healthcare Beijing Peoples R China Tongji Univ Sch Med Tongji Hosp Dept Radiol Shanghai Peoples R China Fudan Univ Inst Funct & Mol Med Imaging Shanghai Peoples R China

Background The aim of this study was to investigate the influence of convolution kernel and iterative reconstruction on the diagnostic performance of radiomics and deep learning (DL) in lung adenocarcinomas. Methods A total of 183 patients with 215 lung adenocarcinomas were included in this study. All CT imaging data was reconstructed with three reconstruction algorithms (ASiR at 0%, 30%, 60% strength), each with two convolution kernels (bone and standard). A total of 171 nodules were selected as the training-validation set, whereas 44 nodules were selected as the testing set. Logistic regression and a DL framework-DenseNets were selected to tackle the task. Three logical experiments were implemented to fully explore the influence of the studied parameters on the diagnostic performance. The receiver operating characteristic curve (ROC) was used to evaluate the performance of constructed models. Results In Experiments A and B, no statistically significant results were found in the radiomic method, whereas two and six pairs were statistically significant (P < 0.05) in the DL method. In Experiment_C, significant differences in one and four models were found in the radiomics and DL methods, respectively. Moreover, models constructed with standard convolution kernel data outperformed that constructed with bone convolution kernel data in all studied ASiR levels in the DL method. In the DL method, B0 and S60 performed best in bone and standard convolution kernel, respectively. Conclusion The results demonstrated that DL was more susceptible to CT parameter variability than radiomics. Standard convolution kernel images seem to be more appropriate for imaging analysis. Further investigation with a larger sample size is needed.

关键词： convolution kernel deep learning iterative reconstruction lung adenocarcinomas radiomics

来源：评论

学校读者我要写书评

暂无评论

A Generalization of Haussler's convolution kernel——Mapping kernel and Its Application to Tree kernels

引用

Journal of Computer Science & Technology 2010年第5期25卷 1040-1054页

作者： Kilho Shin Tetsuji Kuboyama Graduate School of Applied Informatics University of HyogoKobeJapan Carnegie Mellon CyLab PittsburghU.S.A Computer Center Gakushuin UniversityTokyoJapan

Haussler＇s convolution kernel provides an effective framework for engineering positive semidefinite kernels, and has a wide range of *** the other hand,the mapping kernel that we introduce in this paper is its natural generalization,and will enlarge the range of application *** main theorem with respect to positive semidefiniteness of the mapping kernel（1） implies Haussler＇s theorem as a corollary,（2） exhibits an easy-to-check necessary and sufficient condition for mapping kernels to be positive semidefinite,and（3） formalizes the mapping kernel so that significant flexibility is provided in engineering new *** an evidence of the effectiveness of our results,we present a framework to engineer tree *** tree is a data structure widely used in many applications,and tree kernels provide an effective method to analyze tree-type ***,not only is the framework important as an example but also as a practical research *** description of the framework accompanies a survey of the tree kernels in the literature,where we see that 18 out of the 19 surveyed tree kernels of different types are instances of the mapping kernel,and examples of novel interesting tree kernels.

关键词： kernel convolution kernel tree edit distance

来源：评论

学校读者我要写书评

暂无评论

Error analysis in the reconstruction of a convolution kernel in a semilinear parabolic problem with integral overdetermination

引用

JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS 2015年 275卷 382-391页

作者： De Staelen, R. H. Van Bockstal, K. Slodicka, M. Univ Ghent Dept Math Anal Res Grp Numer Anal & Math Modeling NaM2 B-9000 Ghent Belgium

A semilinear parabolic problem of second order with an unknown solely time-dependent convolution kernel is considered. An additional given global measurement (a space integral of the solution) ensures the existence of a unique weak solution. The unknown kernel function can be approximated by a time-discrete numerical scheme based on Backward Euler's method (Rothe's method). In this contribution, an error analysis for the time discretization is performed of the existing numerical algorithm. Numerical experiments support the theoretically obtained results. (C) 2014 Elsevier B.V. All rights reserved.

关键词： Parabolic IBVP Integral overdetermination convolution kernel Reconstruction Error analysis

来源：评论

学校读者我要写书评

暂无评论

Numerical solution of Volterra integral equations of the second kind with convolution kernel by using Taylor-series expansion method

引用

APPLIED MATHEMATICS AND COMPUTATION 2005年第3期161卷 915-922页

作者： Maleknejad, K Aghazadeh, N Islamic Azad Univ Karaj Unit Dept Math Fac Sci Karaj Iran Iran Univ Sci & Technol Sch Math Tehran 16844 Iran

In this paper, we present a Taylor-series expansion method for a class of Volterra integral equations of second kind with smooth or weakly singular kernels. This method use Taylor-series approximation method for integral equation and transform the integral equation to an nth order, linear diffierential equation. Boundary conditions for differential equation produce in easy way. This method gives an approximate simple and closed form solution for integral equation. Some numerical example use to illustrate the accuracy of method. (C) 2004 Elsevier Inc. All rights reserved.

关键词： Taylor-series integral equation weakly singular kernel convolution kernel

来源：评论

学校读者我要写书评

暂无评论

Determination of a time-dependent convolution kernel in a non-linear hyperbolic equation

引用

INVERSE PROBLEMS IN SCIENCE AND ENGINEERING 2016年第6期24卷 1011-1029页

作者： Slodicka, M. Seliga, L. Univ Ghent Dept Math Anal Res Grp Numer Anal & Math Modeling NaM2 B-9000 Ghent Belgium

A non-linear wave equation with an unknown time-convolution kernel is considered. The missing kernel is recovered from an additional (space) integral measurement. The global in time existence, uniqueness as well as the regularity of a solution is addressed. A new numerical algorithm based on Rothe's method is designed and error estimates are derived.

关键词： Wave equation convolution kernel reconstruction error estimate time discretization

来源：评论

学校读者我要写书评

暂无评论

Ontology kernel - A convolution kernel for Ontology Alignment

引用

JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 2015年第2期31卷 415-432页

作者： Son, Jeong-Woo Yoon, Hee-Guen Park, Seong-Bae Elect & Telecommun Res Inst Broadcasting & Telecommun Media Res Lab Taejon 305700 South Korea Kyungpook Natl Univ Sch Engn & Comp Sci Taegu 702701 South Korea

Every ontology entity such as a concept or a property has its own structural information represented as a graph due to the relations with other entities. Therefore, it is important to consider not only its lexical similarity but also structural similarity in ontology alignment. This paper proposes ontology kernel that computes both types of similarities simultaneously. The idea of this kernel is to measure the structural similarity of ontology entities by mapping their entity graphs into the space spanned by entity random walks. The graph of an entity in the kernel expresses all relations with other entities. Thus, the ontology kernel can compare the similarity between entities no matter how complex the entities are and no matter how many kinds of relations they possess. A series of experiments with the standard data sets prove the generality and the superiority of the ontology kernel in ontology alignment.

关键词： ontology alignment ontology kernel convolution kernel graph similarity hyper graph

来源：评论

学校读者我要写书评

暂无评论

Demonstration of convolution kernel Operation on Resistive Cross-Point Array

IEEE ELECTRON DEVICE LETTERS

引用

IEEE ELECTRON DEVICE LETTERS 2016年第7期37卷 870-873页

作者： Gao, Ligang Chen, Pai-Yu Yu, Shimeng Arizona State Univ Sch Elect Comp & Energy Engn Tempe AZ 85287 USA

convolution is the key operation in the convolutional neural network, one of the most popular deep learning algorithms. The implementation of the convolution kernel on the resistive cross-point array is different than the implementation of the matrix-vector multiplication in prior works. In this letter, we propose a dimensional reduction of 2-D kernel matrix into 1-D column vector, i.e., a column of the array, and enable the parallel readout of multiple 2-D kernels simultaneously. As a proof-of-concept demonstration, we use the Prewitt kernels to detect both horizontal and vertical edges of the 20 x 20 pixels of black-and-white MNIST handwritten digits. The experiments were performed on the fabricated 12 x 12 resistive cross-point array based on the Pt/HfOx/TiN structure. The experimental results of the Prewitt kernel operation perfectly matches the simulation results, indicating the feasibility of the proposed implementation methodology of the convolution kernel on resistive cross-point array.

关键词： convolution kernel neuromorphic computing cross-point array resistive memory

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of a convolution kernel in a semilinear parabolic problem based on a global measurement

引用

NONLINEAR ANALYSIS-THEORY METHODS & APPLICATIONS 2015年 112卷 43-57页

作者： De Staelen, R. H. Slodicka, M. Univ Ghent Dept Math Anal Res Grp Numer Anal & Math Modeling NaM2 B-9000 Ghent Belgium

A semilinear parabolic problem of second order with an unknown time-convolution kernel is considered. The missing kernel is recovered from an additional integral measurement. The existence, uniqueness and regularity of a weak solution is addressed. We design a numerical algorithm based on Rothe's method, derive a priori estimates and prove convergence of iterates towards the exact solution. (C) 2014 Elsevier Ltd. All rights reserved.

关键词： Parabolic IBVP convolution kernel Reconstruction Convergence Time discretization

来源：评论

学校读者我要写书评

暂无评论

An adaptive bilateral filtering method based on improved convolution kernel used for infrared image enhancement

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2022年第8期16卷 2231-2237页

作者： Lv, Hui Shan, Pengfei Shi, Hongfang Zhao, Li Zibo Normal Coll Dept Math & Phys 99 Ouling Rd Zibo 255130 Shandong Peoples R China Zhiquli Artificial Intelligence Technol Co Ltd Sh Res & Dev Dept Shandong Artificial Intelligence Ind Pk Jinan 250014 Shandong Peoples R China

Smoothing filters are widely used in computer vision and computer graphics. Bilateral filtering is a typical edge-preserving filter, which has the advantages of sharpening the image edge contour and denoising. The traditional adaptive bilateral filtering algorithms only considered the spatial variance and the adaptation of gray-scale variance which ignores the influence of the convolution kernel on infrared images. In this paper, an adaptive bilateral filter method improved convolution kernel is proposed for infrared image enhancement which combines the edge detection operator with bilateral filtering. The method primarily combines the advantages of edge detection operators to propose an improved convolution kernel in bilateral filtering. The main purpose of the proposed method is used to enhance the details of infrared images and suppress noise. The effective of the proposed method is verified by the experiment.

关键词： Infrared imagery Bilateral filter Image enhancement convolution kernel

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：