检索结果-南通市图书馆

Three-Stage Transfer Learning with AlexNet50 for MRI Image Multi-Class Classification with Optimal Learning Rate

Computer Modeling in Engineering & sciences 2025年第1期142卷 155-183页

作者： Suganya Athisayamani A.Robert Singh Gyanendra Prasad Joshi Woong Cho School of computing Sastra Deemed to be UniversityThanjavur613401India Department of Computational Intelligence SRM Institute of Science and TechnologyKattankulathur603203India Department of AI and software Engineering Kangwon National UniversitySamcheok25913Republic of Korea Department of Electronics Information and Communication EngineeringKangwon National UniversitySamcheok25913Republic of Korea

In radiology,magnetic resonance imaging(MRI)is an essential diagnostic tool that provides detailed images of a patient’s anatomical and physiological *** is particularly effective for detecting soft tissue ***,radiologists manually interpret these images,which can be labor-intensive and time-consuming due to the vast amount of *** address this challenge,machine learning,and deep learning approaches can be utilized to improve the accuracy and efficiency of anomaly detection in MRI *** manuscript presents the use of the Deep AlexNet50 model for MRI classification with discriminative learning *** are three stages for learning;in the first stage,the whole dataset is used to learn the *** the second stage,some layers of AlexNet50 are frozen with an augmented dataset,and in the third stage,AlexNet50 with an augmented dataset with the augmented *** method used three publicly available MRI classification datasets:Harvard whole brain atlas(HWBA-dataset),the School of Biomedical Engineering of Southern Medical University(SMU-dataset),and The National Institute of Neuroscience and Hospitals brain MRI dataset(NINS-dataset)for *** hyperparameter optimizers like Adam,stochastic gradient descent(SGD),Root mean square propagation(RMS prop),Adamax,and AdamW have been used to compare the performance of the learning ***-dataset registers maximum classification *** evaluated the performance of the proposed classification model using several quantitative metrics,achieving an average accuracy of 98%.

关键词： MRI tumors classification AlexNet50 transfer learning hyperparameter tuning optimizer

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

Multi-Scale Dilated Convolution Network for SPECT-MPI Cardiovascular Disease Classification with Adaptive Denoising and Attenuation Correction

引用

Computer Modeling in Engineering & sciences 2025年第1期142卷 299-327页

作者： A.Robert Singh Suganya Athisayamani Gyanendra Prasad Joshi Bhanu Shrestha Department of Computational Intelligence SRM Institute of Science and TechnologyKattankulathur603203Tamil NaduIndia School of computing Sastra Deemed to be UniversityThanjavur613401Tamil NaduIndia Department of Artificial Intelligence&software Kangwon National UniversitySamcheok25913Republic of Korea Department of Information Convergence System Graduate School of Smart ConvergenceKwangwoon UniversitySeoul01897Republic of Korea

Myocardial perfusion imaging(MPI),which uses single-photon emission computed tomography(SPECT),is a well-known estimating tool for medical diagnosis,employing the classification of images to show situations in coronary artery disease(CAD).The automatic classification of SPECT images for different techniques has achieved near-optimal accuracy when using convolutional neural networks(CNNs).This paper uses a SPECT classification framework with three steps:1)Image denoising,2)Attenuation correction,and 3)Image *** denoising is done by a U-Net architecture that ensures effective image *** correction is implemented by a convolution neural network model that can remove the attenuation that affects the feature extraction process of ***,a novel multi-scale diluted convolution(MSDC)network is *** merges the features extracted in different scales and makes the model learn the features more *** scales of filters with size 3×3 are used to extract *** three steps are compared with state-of-the-art *** proposed denoising architecture ensures a high-quality image with the highest peak signal-to-noise ratio(PSNR)value of *** proposed classification method is compared with the five different CNN models,and the proposed method ensures better classification with an accuracy of 96%,precision of 87%,sensitivity of 87%,specificity of 89%,and F1-score of 87%.To demonstrate the importance of preprocessing,the classification model was analyzed without denoising and attenuation correction.

关键词： SPECT-MPI CAD MSDC denoising attenuation correction 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

Highly Optimized Code Generation for Stencil Codes with Computation Reuse for GPUs

引用

Journal of Computer science & Technology 2016年第6期31卷 1262-1274页

作者： Wen-Jing Ma Kan Gao Guo-Ping Long laboratory of parallel software and computing science Institute of Software Chinese Academy of Sciences Beijing 100190 China State Key laboratory of Computer science Institute of Software Chinese Academy of Sciences Beijing 100190 China Information Center China Association for Science and Technology Beijing 100863 China

Computation reuse is known as an effective optimization technique. However, due to the complexity of modern GPU architectures, there is yet not enough understanding regarding the intriguing implications of the interplay of compu- ration reuse and hardware specifics on application performance. In this paper, we propose an automatic code generator for a class of stencil codes with inherent computation reuse on CPUs. For such applications, the proper reuse of intermediate results, combined with careful register and on-chip local memory usage, has profound implications on performance. Current state of the art does not address this problem in depth, partially due to the lack of a good program representation that can expose all potential computation reuse. In this paper, we leverage the computation overlap graph （COG）, a simple representation of data dependence and data reuse with ＂element view＂, to expose potential reuse opportunities. Using COG, we propose a portable code generation and tuning framework for GPUs. Compared with current state-of-the-art code generators, our experimental results show up to 56.7% performance improvement on modern GPUs such as NVIDIA C2050.

关键词： GPGPU OpenCL stencil code generation computation reuse

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

MULTIVARIATE FOURIER SERIES OVER A CLASS OF NON TENSOR-PRODUCT PARTITION DOMAINS

引用

Journal of Computational Mathematics 2003年第1期21卷 53-62页

作者： Jiachang Sun(parallel computing Division, Institute of software, Chinese Academy of sciences, Beijing 100080, China) parallel computing Division Institute of Software Chinese Academy of Sciences 北京 100080

This paper finds a way to extend the well-known Fourier methods, to so-called n+1 directions partition domains in n-dimension. In particular, in 2-D and 3-D cases, we study Fourier methods over 3-direction parallel hexagon partitions and 4-direction parallel parallelogram dodecahedron partitions, respectively. It has pointed that, the most concepts and results of Fourier methods on tensor-product case, such as periodicity,orthogonality of Fourier basis system, partial sum of Fourier series and its approximation behavior, can be moved on the new non tensor-product partition case.

关键词： Multivariate Fourier methods Non tensor-product partitions Multivariate Fourier series

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

Commutation of Geometry-Grids and Fast Discrete PDE Eigen-Solver GPA

引用

Chinese Annals of Mathematics,Series B 2023年第5期44卷 735-752页

作者： Jiachang SUN Jianwen CAO Ya ZHANG Haitao ZHAO laboratory of parallel software and Computational science Institute of SoftwareChinese Academy ofSciencesBeijing 100190China

A geometric intrinsic pre-processing algorithm(GPA for short)for solving largescale discrete mathematical-physical PDE in 2-D and 3-D case has been presented by Sun(in 2022–2023).Different from traditional preconditioning,the authors apply the intrinsic geometric invariance,the Grid matrix G and the discrete PDE mass matrix B,stiff matrix A satisfies commutative operator BG=GB and AG=GA,where G satisfies G^(m)=I,mparallelism of geometric mesh pre-transformation is mainly proportional to the number of faces of polyhedron”is obtained through research,and it is further found that“commutative of grid mesh matrix and mass matrix is an important basis for the feasibility and reliability of GPA algorithm”.

关键词： Mathematical-physical discrete eigenvalue problems Commutative operator Geometric pre-processing algorithm Eigen-polynomial factorization

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

Improved Differential and Linear Active S-Boxes Search Techniques for Feistel Type Ciphers

引用

Chinese Journal of Electronics 2015年第2期24卷 343-348页

作者： ZHANG Lei WU Wenling Trusted computing and Information Assurance laboratory Institute of Software State Key laboratory of Computer science Institute of Software

We propose improved differential and linear active S-boxes search techniques for Feistel type ciphers. We give a uniform representation of Feistel type structures which can benefit the analysis of differential propagation. By analyzing the properties of Feistel type environment, we present some important observations of differential propagation and propose a notion of equivalent state set which can narrow down the search space noticeably. We present a practical algorithm to improve the search of active S-boxes for Feistel type ciphers. It is basically a Viterbi search operating on equivalent state set and also adopts the pruning mechanism. Our experimental results show that the improved algorithm have advantages in respect to memory and time complexities, and it can be applied efficiently to Feistel cipher with large blocks. The search program can be implemented in normal PC, which will be more practical and useful for the designers and cryptanalysts.

关键词： Block cipher Feistel type ciphers Differential and linear active S-boxes Automatic search technique

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Solving multi-objective constrained minimum weighted bipartite assignment problem: a case study on energy-aware radio broadcast scheduling

引用

science China(Information sciences) 2022年第8期65卷 23-38页

作者： Yupeng ZHOU Mingjie FAN Feifei MA Minghao YIN College of Information science and Technology Northeast Normal University laboratory of parallel software and Computational science Institute of Software Chinese Academy of Sciences State Key laboratory of Computer science Institute of Software Chinese Academy of Sciences

This paper proposes a multi-objective constrained minimum weighted bipartite assignment problem(MCMWBAP), which is considered an extension of the classical bipartite matching problem(BMP). We first provide the formulation of the MCMWBAP and prove that it is an NP-hard combinatorial optimization problem. Based on this formulation, multi-objective energy-aware shortwave radio broadcast resource allocation problem(MSRBRAP) application is studied. The goal of this problem is to allocate radio programs to transmission devices to broadcast all radio programs felicitously with a maximized objective of total qualified monitoring sites and a minimized objective of energy consumption. Then, a novel multi-objective hybrid evolutionary algorithm(MOHEA), which is integrated with push and pull initialization, the dynamic resource allocation strategy, and the aggregate local search procedure, is developed to solve the *** proposed method is evaluated using two categories of benchmarks for MCMWBAP together with a real scenario case study for MSRBRAP. Furthermore, the key components of MOHEA are analyzed, and the experimental results demonstrate that MOHEA outperforms two classical multi-objective evolutionary algorithms(NSGA-II and MOEA/D), improving working efficiency.

关键词： constrained minimum weighted bipartite assignment multi-objective energy-aware radio broadcast scheduling evolutionary algorithms dynamic resource allocation aggregate local search

来源：

同方期刊数据库

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

A new class of three-variable orthogonal polynomials and their recurrences relations

引用

science China Mathematics 2008年第6期51卷 1071-1092页

作者： SUN JiaChang State Key laboratory of Computer science,R&D Center for parallel computing,Institute of software,Chinese Academy of sciences,Beijing 100080,China State Key laboratory of Computer science R & D Center for Parallel Computing Institute of Software Chinese Academy of Sciences Beijing China

A new class of three-variable orthogonal polynomials, defined as eigenfunctions of a second order PDE operator, is studied. These polynomials are orthogonal over a curved tetrahedron region, which can be seen as a mapping from a traditional tetrahedron, and can be taken as an extension of the 2-D Steiner domain. The polynomials can be viewed as Jacobi polynomials on such a domain. Three-term relations are derived explicitly. The number of the individual terms, involved in the recurrences relations, are shown to be independent on the total degree of the polynomials. The numbers now are determined to be five and seven, with respect to two conjugate variables z, $ \bar z $ and a real variable r, respectively. Three examples are discussed in details, which can be regarded as the analogues of the Chebyshev polynomials of the first and the second kinds, and Legendre polynomials.

关键词： 3-D PDE eigen-problem three-variable Chebyshev polynomials Legendre polynomial Jacobi polynomials recurrence relations 65N25 42C05 33C45

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

B-splines on 3-D tetrahedron partition in four-directional mesh

引用

science China Mathematics 2001年第4期44卷 491-496页

作者：孙家昶施锡泉 parallel computing Division and laboratory of Computer science Institute of Software Chinese Academy of Sciences Beijing China Department of Applied Mathematics University of Dalian Dalian China

It is more difficult to construct 3-D splines than in 2-D case. Some results in the three directional meshes of bivariate case have been e xtended to 3-D case and corresponding tetrahedron partition has been constructed. The support of related Bsplines and their recurrent formulas on integration and differentiationdifference are obtained. The results of this paper can be extended into higher dimension spaces, and can be also used in wavelet analysis, because of the relationship between spline and wavelets.

关键词： high dimensional splines box splines tetrahedron partition

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

EDGE-ORIENTED HEXAGONAL ELEMENTS

引用

Journal of Computational Mathematics 2007年第4期25卷 430-439页

作者： Chao Yang Jiachang Sun parallel computing Lab. Institute of Software Chinese Academy of Sciences Beijing 100080 China

In this paper, two new nonconforming hexagonal elements are presented, which are based on the trilinear function space Q1^（3） and are edge-oriented, analogical to the case of the rotated Q1 quadrilateral element. A priori error estimates are given to show that the new elements achieve first-order accuracy in the energy norm and second-order accuracy in the L^2 norm. This theoretical result is confirmed by the numerical tests.

关键词： Nonconforming finite element method Hexagonal element Q1 element.

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

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：