检索结果-内蒙古大学图书馆

Healthy/Glaucoma Fundus Retinal Image Classification using butterfly algorithm Optimized ResNet-Features

Procedia Computer Science 2025年 258卷 1804-1812页

作者： Ramya Mohan Seifedine Kadry Sahar Yassine Venkatesan Rajinikanth Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai 602105 TN India Department of applied data science Noroff University College Kristiansand Norway

Hospitals frequently use medical image supported disease diagnosis to identify diseases and evaluates their severity. Automation in image examination is normally preferred to reduce the diagnostic burden. Developing a Deep-Learning Tool (DLT) to analyze the fundus-photography (FP) labeled as healthy/glaucoma class is the aim of this research. Different phases in this DLT involves the following; collection of FP database from image repository and resizing it to 224x224x3 pixels, feature extraction using ResNet (RN) model, feature reduction using the Brownian-butterfly algorithm (BBA), serial concatenation of features to obtain fused-features (FF), and executing the binary classification using 3-fold cross validation. This work utilized a two-fold training in order to improve detection accuracy with the FP data. This investigation is executed using individual and FF to verify the DLT’s performance. The results of this research validates that, the K-Nearest Neighbor (KNN) assisted classification provides 100% accuracy when FF based investigation is executed.

关键词： Healthcare global health fundus image ResNet butterfly algorithm classification

来源：评论

学校读者我要写书评

暂无评论

A FAST butterfly algorithm FOR THE COMPUTATION OF FOURIER INTEGRAL OPERATORS

引用

MULTISCALE MODELING & SIMULATION 2009年第4期7卷 1727-1750页

作者： Candes, Emmanuel Demanet, Laurent Ying, Lexing CALTECH Pasadena CA 91125 USA Stanford Univ Dept Math Stanford CA 94305 USA Univ Texas Austin Dept Math Austin TX 78712 USA Univ Texas Austin ICES Austin TX 78712 USA

This paper is concerned with the fast computation of Fourier integral operators of the general form integral(Rd)e(2 pi iota Phi(x,k)) f(k) dk, where k is a frequency variable, Phi(x, k) is a phase function obeying a standard homogeneity condition, and f is a given input. This is of interest, for such fundamental computations are connected with the problem of finding numerical solutions to wave equations and also frequently arise in many applications including reflection seismology, curvilinear tomography, and others. In two dimensions, when the input and output are sampled on N x N Cartesian grids, a direct evaluation requires O(N(4)) operations, which is often times prohibitively expensive. This paper introduces a novel algorithm running in O(N(2) log N) time, i.e., with near-optimal computational complexity, and whose overall structure follows that of the butterfly algorithm. Underlying this algorithm is a mathematical insight concerning the restriction of the kernel e(2 pi iota Phi(x, k)) to subsets of the time and frequency domains. Whenever these subsets obey a simple geometric condition, the restricted kernel is approximately low-rank;we propose constructing such low-rank approximations using a special interpolation scheme, which prefactors the oscillatory component, interpolates the remaining nonoscillatory part, and finally remodulates the outcome. A byproduct of this scheme is that the whole algorithm is highly efficient in terms of memory requirement. Numerical results demonstrate the performance and illustrate the empirical properties of this algorithm.

关键词： Fourier integral operators butterfly algorithm dyadic partitioning Lagrange interpolation separated representation multiscale computations

来源：评论

学校读者我要写书评

暂无评论

A PARALLEL butterfly algorithm

引用

SIAM JOURNAL ON SCIENTIFIC COMPUTING 2014年第1期36卷 C49-C65页

作者： Poulson, Jack Demanet, Laurent Maxwell, Nicholas Ying, Lexing Stanford Univ Dept Math Stanford CA 94305 USA MIT Dept Math Cambridge MA 02139 USA Univ Houston Dept Math Houston TX 77004 USA Stanford Univ ICME Stanford CA 94305 USA

The butterfly algorithm is a fast algorithm which approximately evaluates a discrete analogue of the integral transform integral R-d K(x, y)g(y)dy at large numbers of target points when the kernel, K(x, y), is approximately low-rank when restricted to subdomains satisfying a certain simple geometric condition. In d dimensions with O(N-d) quasi-uniformly distributed source and target points, when each appropriate submatrix of K is approximately rank-r, the running time of the algorithm is at most O(r(2)N(d) logN). A parallelization of the butterfly algorithm is introduced which, assuming a message latency of alpha and per-process inverse bandwidth of beta, executes in at most O(r(2) N-d/p logN + (beta r N-d/p + alpha)log p) time using p processes. This parallel algorithm was then instantiated in the form of the open-source Distbutterfly library for the special case where K(x, y) = exp(i Phi(x, y)), where Phi(x, y) is a black-box, sufficiently smooth, real-valued phase function. Experiments on Blue Gene/Q demonstrate impressive strong-scaling results for important classes of phase functions. Using quasi-uniform sources, hyperbolic Radon transforms, and an analogue of a three-dimensional generalized Radon transform were, respectively, observed to strong-scale from 1-node/16-cores up to 1024-nodes/16,384-cores with greater than 90% and 82% efficiency, respectively.

关键词： butterfly algorithm Egorov operator Radon transform parallel Blue Gene/Q

来源：评论

学校读者我要写书评

暂无评论

An analysis of a butterfly algorithm

引用

COMPUTERS & MATHEMATICS WITH APPLICATIONS 2017年第9期74卷 2125-2143页

作者： Boerm, S. Boerst, C. Melenk, J. M. Univ Kiel Inst Informat Christian Albrechts Pl 4 D-24118 Kiel Germany Tech Univ Wien Wiedner Hauptstr 8-10 A-1040 Vienna Austria

butterfly algorithms are an effective multilevel technique to compress discretizations of integral operators with highly oscillatory kernel functions. The particular version of the butterfly algorithm presented in Cantles, et al. (2009) realizes the transfer between levels by Chebyshev interpolation. We present a refinement of the analysis given in Demanet, et al. (2012) for this particular algorithm. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： butterfly algorithm Stability of iterated polynomial interpolation

来源：评论

学校读者我要写书评

暂无评论

SPARSE FOURIER TRANSFORM VIA butterfly algorithm

引用

SIAM JOURNAL ON SCIENTIFIC COMPUTING 2009年第3期31卷 1678-1694页

作者： Ying, Lexing Univ Texas Austin Dept Math Austin TX 78712 USA

This paper introduces a fast algorithm for computing sparse Fourier transforms with spatial and Fourier data supported on curves or surfaces. This problem appears naturally in several important applications of wave scattering, digital signal processing, and reflection seismology. The main idea of the algorithm is that the interaction between a frequency region and a spatial region is approximately low rank if the product of their widths are bounded by the maximum frequency. Based on this property, we can approximate the interaction between these two boxes accurately and compactly using a small number of equivalent sources. The overall structure of the algorithm follows the butterfly algorithm. The computation is further accelerated by exploiting the tensor-product property of the Fourier kernel in two and three dimensions. The proposed algorithm is accurate and has the optimal complexity. We present numerical results in both two and three dimensions.

关键词： Fourier transform butterfly algorithm multiscale methods far field pattern

来源：评论

学校读者我要写书评

暂无评论

Fast Accurate Bi-SAR Imaging Based on butterfly algorithm

Fast Accurate Bi-SAR Imaging Based on Butterfly Algorithm

引用

International Conference on Computational Problem-Solving (ICCP)

作者： Song, Leiquan Li, Zhongyu Wu, Junjie Huang, Yulin Yang, Jianyu Univ Elect Sci & Technol China Sch Elect Engn Chengdu 611731 Peoples R China

ISBN: (纸本)9781479921508

The butterfly algorithm is imported to achieve high resolution and large scene imaging fast for bistatic synthetic aperture radar (Bi-SAR). The fast algorithm benefits from projecting the frequency domain signal after matched filtering to subimage. Quad tree structures constructed on both signal and image spaces are used to projected signal recursively. Following the traversal of the quadtree, the image resolution is ameliorated gradually. The algorithm run on parallel processors and fast imaging is accomplished. Except for imaging precisely and quickly, wide scene imaging is also obtained. The simulation image shows the high quality image with good resolution and large PSLR.

关键词： butterfly algorithm Bi-SAR low-rank approximation quadtree

来源：评论

学校读者我要写书评

暂无评论

FAST ACCURATE NEAR SPACE CIRCULAR SAR DATA FOCUSING BASED ON butterfly algorithm

FAST ACCURATE NEAR SPACE CIRCULAR SAR DATA FOCUSING BASED ON...

引用

IEEE Joint International Geoscience and Remote Sensing Symposium (IGARSS) / 35th Canadian Symposium on Remote Sensing

作者： Yang, Haiguang Li, Zhongyu Song, Leiquan Wu, Junjie Huang, Yulin Yang, Jianyu Univ Elect Sci & Technol China Chengdu 611731 Peoples R China

ISBN: (纸本)9781479957750

The butterfly algorithm is introduced to achieve fast imaging of near space circular synthetic aperture radar (SAR) raw data with high resolution and large scene. The fast algorithm benefits from projecting the frequency domain signal after matched filtering to subimage. Quad tree structures constructed on both signal and image spaces are used to project signal recursively. Following the traversal of the quadtree, the image resolution is ameliorated gradually. The algorithm run on parallel processors and fast imaging is accomplished. Except for the ability of precise and quick imaging, large scene imaging is also achieved. The simulation results show the high quality image with good resolution.

关键词： butterfly algorithm near space circular SAR low-rank approximation quadtree

来源：评论

学校读者我要写书评

暂无评论

Device-Saving Pipeline Architectures of Multi-dimensional DCT Similar butterfly algorithm

Device-Saving Pipeline Architectures of Multi-dimensional DC...

引用

IEEE International Conference on Integrated Circuits and Microsystems (ICICM)

作者： Liu Yuanyuan Chen Hexin Zhao Yan Yang Chuxi Jilin Univ Coll Commun Engn Changchun Peoples R China Jilin Agr Univ Coll Informat technol Changchun Peoples R China

ISBN: (纸本)9781509028146

In traditional multi-dimensional discrete cosine transform (DCT) algorithm, n dimensions are processed separately. In order to realize n-D global DCT and construct the unity architectures of blocks with different sizes, we have proposed n-D DCT similar butterfly algorithm and its unit pipeline architectures. And in order to solve the problems of this algorithm hardware architectures use a lot of delayers or selectors independently and in algorithm different blocks are not easy to integrate, based on the basic principles of DCT and on the basis of the "tensor" operation, premised on the multi-dimensional DCT pipeline algorithm we have proposed, we invest algorithm architectures to save devices. Firstly, we present n-D DCT pipeline algorithm based on theory of 1-D DCT and tensor product operation in brief, and give n-D DCT similar butterfly architectures. Secondly, we propose pipeline architectures units and the corresponding whole pipeline architecture of n-D DCT. Thirdly and foremost, we set up delayers-group models by reusing delayers and selectors, the models are integrative and nested. The experimental results indicate that the reduce ratio of number of delayers and selectors increased obviously as block size increase by using our device-saving algorithm. The characteristics of our pipeline architectures algorithm are fast, low complexity, and multidimensional compatibility.

关键词： multi-dimension DCT butterfly algorithm pipeline architectures device-saving

来源：评论

学校读者我要写书评

暂无评论

Three Dimensional DCT Similar butterfly algorithm and its Pipeline Architectures

Three Dimensional DCT Similar Butterfly Algorithm and its Pi...

引用

2016 IEEE Information Technology,Networking,Electronic and Automation Control Conference(ITNEC 2016)

作者： Liu Yuanyuan Chen Hexin Zhao Yan Yang Chuxi College of Communication Engineering Jilin University College of information technology Jilin Agricultural University

ISBN: (纸本)9781467391955

In traditional three-dimensional(3D) discrete cosine transform(DCT) algorithm, three dimensions are processed separately. In order to realize 3D global DCT and construct the unity architectures of blocks with different sizes, we propose 3D DCT similar butterfly algorithm and its unit pipeline architectures. Firstly, we present 3D DCT pipeline algorithm based on the theory of 1D DCT and tensor product ***, we give the 3D DCT similar butterfly ***, we propose unit pipeline architectures and the corresponding whole pipeline architecture of 3D DCT. The experimental results indicate that we only require half number of add operation and approximately 30% multiplication operations comparing to conventional 3D DCT algorithm. And the processing time to transform one block using our method takes less than 15% of the time using traditional methods.

关键词： Three-dimension(3D) DCT butterfly algorithm Pipeline architectures Video signal processing

来源：评论

学校读者我要写书评

暂无评论

Optimization of the hybrid solar power plants comprising photovoltaic and concentrating solar power using the butterfly algorithm

引用

ENERGY CONVERSION AND MANAGEMENT 2022年 257卷 115310-115310页

作者： Kong, Ling-gang Chen, Xin-long Gong, Jing-hu Fan, Duo-jin Wang, Bao-li Li, Shuo Lanzhou Jiaotong Univ Engn Res Ctr Solar Hermal Stoage Integrated Energ Lanzhou 730070 Peoples R China China Railway First Survey & Design Inst Grp Co L Xian 710000 Peoples R China Southeast Univ Sch Energy & Environm Key Lab Solar Energy Sci & Technol Jiangsu Prov Nanjing 210096 Peoples R China Xian Univ Architecture & Technol Sch Bldg Serv Sci & Engn Xian 710055 Peoples R China

This study optimized grid intermittency and instability resulting from photovoltaic (PV) by adding concentrating solar power (CSP) equipped with thermal energy storage (TES), which can be used to form hybrid solar power for grid dispatching. The PV-CSP were optimized by using a hybrid butterfly algorithm to meet the power gener-ation demands and lowest system operation costs. Based on the optimal output and operating characteristics of hybrid power, the economics of peak-valley and fixed electricity prices were studied and compared. The optimal TES capacity was 6-h electricity generation. Hybrid power with optimal TES capacity could achieve a 4.2% increase for power production and 10.4% decrease for operation cost. The peak-valley price provided a better economic benefit than the fixed electricity price. A reasonable configuration of TES can ensure the flexibility and stability of hybrid plant. Hybrid power contributes to a flexible use of dispatch capabilities by equipped with TES, making PV power completely utilize, especially during the periods of high solar radiation. For power systems, hybrid power can be used to replace partly conventional thermal power to achieve highly economic and environmental benefits.

关键词： Hybrid power Photovoltaic Concentrating solar power Scheduling optimization butterfly algorithm Peak-valley electricity price

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：