检索结果-内蒙古大学图书馆

IEEE International conference on Electronics, Circuits and Systems (ICECS)

作者： Rosario Arjona Iluminada Baturone Electronics and Electromagnetism Department Microelectronics Institute of Seville (IMSE-CNM-CSIC) University of Seville Seville Spain

Since singular point extraction plays an important role in many fingerprint recognition systems, a digital circuit to implement such processing is presented herein. A novel algorithm that combines hardware efficiency with precision in the extraction of the points has been developed. The circuit architecture contains three main building blocks to carry out the three main stages of the algorithm: extraction of a partitioned directional image, smoothing, and searching for the patterns associated with singular points. The circuit processes the pixels in a serial way, following a pipeline scheme and executing in parallel several operations. The design flow employed has been supported by CAD tools. It starts with high-level descriptions and ends with the hardware prototyping into a FPGA from Xilinx.

关键词： Fingerprint recognition Hardware Smoothing methods image matching Algorithm design and analysis Proposals Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

The Research of Levenberg-Marquardt Algorithm in Curve Fittings on Multiple GPUs

The Research of Levenberg-Marquardt Algorithm in Curve Fitti...

引用

IEEE International conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Lingjie Zhang Ying Zhao Kaixi Hou College of Information and Technology Beijing University of Chemical Technology Beijing China

During the study of biological viruses, a large number of fluorescent particle images are photographed by ultra-microscopes in order to observe the motion and variation of viruses. However, due to diffraction effects, the luminance values of these fluorescent images are distributed in the form of the Point Spread Function. Considering the popularity and robustness of the Levenberg-Marquardt Algorithm (LMA), in this paper the LMA is adopted to achieve Gaussian fitting. Because plenty of matrix operations are involved in this algorithm, it is appropriate to take advantage of GPU to deal with this parallel problem. Plus, the increase of the image dataset brings us much trouble, such as the growth of total running time and out-of-memory problem. Therefore, we also achieve quick Gaussian fitting on multiple GPUs. Test and analysis results show that near proportional growth of computing speed can be reached as the number of GPUs increases. And this work also has shown in using different quantity of GPUs, all input image data sizes can obtain some speedup and larger data sizes can obtain more efficient speedup.

关键词： Graphics processing unit Instruction sets Fitting Algorithm design and analysis Viruses (medical) Fluorescence Curve fitting

来源：评论

学校读者我要写书评

暂无评论

Scalable fast multipole methods on distributed heterogeneous architectures

Scalable fast multipole methods on distributed heterogeneous...

引用

Supercomputing conference

作者： Qi Hu Nail A. Gumerov Ramani Duraiswami Institute for Advanced Computer Studies (UMIACS) Department of Computer Science University of Maryland College Park USA

We fundamentally reconsider implementation of the Fast Multipole Method (FMM) on a computing node with a heterogeneous CPU-GPU architecture with multicore CPU(s) and one or more GPU accelerators, as well as on an interconnected cluster of such nodes. The FMM is a divide- and-conquer algorithm that performs a fast N-body sum using a spatial decomposition and is often used in a time- stepping or iterative loop. Using the observation that the local summation and the analysis-based translation parts of the FMM are independent, we map these respectively to the GPUs and CPUs. Careful analysis of the FMM is performed to distribute work optimally between the multicore CPUs and the GPU accelerators. We first develop a single node version where the CPU part is parallelized using OpenMP and the GPU version via CUDA. New parallel algorithms for creating FMM data structures are presented together with load balancing strategies for the single node and distributed multiple-node versions. Our implementation can perform the N-body sum for 128M particles on 16 nodes in 4.23 seconds, a performance not achieved by others in the literature on such clusters.

关键词： Graphics processing unit Receivers Clustering algorithms Kernel Arrays Sorting

来源：评论

学校读者我要写书评

暂无评论

NON-LINEAR NOISE COMPENSATION FOR ROBUST SPEECH RECOGNITION USING GAUSS-NEWTON METHOD

NON-LINEAR NOISE COMPENSATION FOR ROBUST SPEECH RECOGNITION ...

引用

IEEE International conference on Acoustics, Speech and Signal processing

作者： Yong Zhao Biing-Hwang (Fred) Juang Center for Signal and Image Processing Georgia Institute of Technology

ISBN: (纸本)9781457705380

In this paper, we present the Gauss-Newton method as a unified approach to optimizing non-linear noise compensation models, such as vector Taylor series (VTS), data-driven parallel model combination (DPMC), and unscented transform (UT). We demonstrate that the commonly used approaches that iteratively approximate the noise parameters in an EM framework are variants of the Gauss-Newton method. Through the formulation of the Gauss-Newton method for estimating noise means and variances, the noise estimation problems are reduced to determining the Jacobians of the noisy speech distributions. For the sampling-based compensations, we present two methods, sample Jacobian average (SJA) and cross-covariance (XCOV), to evaluate the Jacobians. Experiments on the Aurora 2 database verify the efficacy of the Gauss-Newton method to these noise compensation models.

关键词： Gauss-Newton method non-linear compensation ro-bust speech recognition vector Taylor series

来源：评论

学校读者我要写书评

暂无评论

An integrated visualization on network events VAST 2011 Mini Challenge #2 Award: “Outstanding integrated overview display”

An integrated visualization on network events VAST 2011 Mini...

引用

IEEE Symposium on Visual Analytics Science and Technology (VAST)

作者： Walter Marcelo Lamagna Master on Datamining and Knowledge Discovery Universidad de Buenos Aires Argentina

To visualize security trends for the data set provided by the VAST 2011 Mini Challenge #2 a custom tool has been developed. Open source tools [1,2], web programming languages [4,7] and an open source database [3] has been used to work with the data and create a visualization for security log files containing network security trends. In this paper, the tools and methods used for the analysis are described. The methods include the log synchronization with different timezone and the development of heat maps and parallel coordinates charts. To develop the visualization, processing and Canvas [4,7] was used.

关键词： Heating Security image color analysis Synchronization Data visualization Fires Arrays

来源：评论

学校读者我要写书评

暂无评论

A New Method for Lossless image Compression Using Recursive Crack Coding

Communications in Computer and Information Science

引用

Communications in Computer and Information Science 2011年 205 M4D卷 128-135页

作者： Meyyappan, T. Thamarai, S.M. Jeya Nachiaban, N.M. Department of Computer Science and Engineering Alagappa University Karaikudi 630 003 India Department of Computer Science and Engineering Thiagarajar College of Engineering Madurai 9 India

ISBN: (纸本)9783642240546

Popular entropy coding methods for lossless compression of images depend on probability models. They start by predicting the model of the data. The accuracy of this prediction determines the optimality of the compression. These methods are very slow because of visiting the data (pixels) in left to right order. parallel implementation of these methods is adopted by researchers to speed up the process. In this paper, the authors propose a new approach to image compression using crack coding. The novelty and better compression ratio of the method is due to its recursiveness in finding the variable-length entropy. The proposed method starts with the original image and develop crack codes in a recursive manner, marking the pixels visited earlier and expanding the entropy in four directions. The proposed method is experimented with sample bitmap images and results are encouraging. The method is implemented in uni-processor machine using C language source code. © Springer-Verlag Berlin Heidelberg 2011.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

GWAS-GMDR: A program package for genome-wide scan of gene-gene interactions with covariate adjustment based on multifactor dimensionality reduction

GWAS-GMDR: A program package for genome-wide scan of gene-ge...

引用

IEEE International conference on Bioinformatics and Biomedicine Workshops (BIBMW)

作者： Min-Seok Kwon Kyunga Kim Sungyoung Lee Wonil Chung Sung-Gon Yi Junghyun Namkung Taesung Park Interdisciplinary program in Bioinformatics Seoul National University South Korea Department of Statistics Seoul National University South Korea

Multifactor dimensionality reduction (MDR) has been successfully applied to identification of gene-gene interactions for the complex traits. Generalized MDR (GMDR) was its extension that allows adjustment for covariates. The current GMDR software mainly focuses on candidate gene association studies with a relatively small number of genetic markers and has some limitations to be extended to genome-wide association studies (GWAS) with a large number of genetic markers. We develop GWAS-GMDR, an effective parallel computing program package with special features for GWAS with a large number of genetic markers by using distributed job scheduling method and/or CUDA-enabled high-performance graphic processing units (GPU). First, GWAS-GMDR implements an effective memory handling algorithm and efficient procedures for GMDR to make joint analysis of multiple genes feasible for GWAS. Second, a weighted version of cross-validation consistency based on `top-K selection' (WCVC K ) is proposed to report multiple candidates for causal gene-gene interactions. Third, various performance measures are implemented to evaluate MDR classifiers, including balanced accuracy, tau-b, likelihood ratio and normalized mutual information. Fourth, some popular methods for handling missing genotypes are implemented. Finally, our applications support both CPU-based and GPU-based parallel computing system. We applied our applications using a real genome wide data set from WTCCC Crohn's disease dataset to identify two-way interaction models in genome-wide scale. The GWAS-GMDR package is a powerful tool for the gene-gene interaction analysis in a genome-wide scale. High-performance implementations are provided as native binaries for Linux, Mac OS X and Windows systems.

关键词： Bioinformatics Graphics processing unit Genomics Diseases parallel processing

来源：评论

学校读者我要写书评

暂无评论

First On-Site Data Analysis System for Subaru/Suprime-Cam

引用

PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF JAPAN 2011年第sp2期63卷 S585-S603页

作者： Furusawa, Hisanori Okura, Yuki Mineo, Sogo Takata, Tadafumi Nakata, Fumiaki Tanaka, Manobu Katayama, Nobuhiko Itoh, Ryosuke Yasuda, Naoki Miyazaki, Satoshi Komiyama, Yutaka Utsumi, Yousuke Uchida, Tomohisa Aihara, Hiroaki Natl Astron Observ Japan Tokyo 1818858 Japan Univ Tokyo Sch Sci Dept Phys Bunkyo Ku Tokyo 1330033 Japan Natl Astron Observ Japan Subaru Telescope Hilo HI 96720 USA High Energy Accelerator Res Org KEK Inst Particle & Nucl Studies Ibaraki 3050801 Japan Univ Tokyo Univ IPMU Inst Phys & Math Kashiwa Chiba 2778583 Japan

We developed an automated on-site quick analysis system for mosaic CCD data of Suprime-Cam, which is a wide-field camera mounted at the prime focus of the Subaru Telescope, Mauna Kea, Hawaii. The first version of the data-analysis system was constructed;and started to operate in general observations. This system is a new function of observing support at the Subaru Telescope to provide the Subaru user community with an automated on-site data evaluation, aiming at improvements of observers' productivity, especially in large imaging surveys. The new system assists the data evaluation tasks in observations by the continuous monitoring of the characteristics of every data frame during observations. The evaluation results and data frames processed by this system are also useful for reducing the data-processing time in a full analysis after an observation. The primary analysis functions implemented in the data-analysis system are composed of automated realtime analysis for data evaluation and on-demand analysis, which is executed upon request, including mosaicing analysis and flat making analysis. In data evaluation, which is controlled by the organizing software, the database keeps track of the analysis histories, as well as the evaluated values of data frames, including seeing and sky background levels;it also helps in the selection of frames for mosaicing and flat making analysis. We examined the system performance and confirmed an improvement in the data-processing time by a factor of 9 with the aid of distributed parallel data processing and on-memory data processing, which makes the automated data evaluation effective.

关键词： Astronomical data bases: miscellaneous methods: data analysis Techniques: image processing

来源：评论

学校读者我要写书评

暂无评论

Toward Optimal Deployment of Communication-Intensive Cloud Applications

Toward Optimal Deployment of Communication-Intensive Cloud A...

引用

IEEE International conference on Cloud Computing, CLOUD

作者： Pei Fan Ji Wang Zibin Zheng Michael R. Lyu National Laboratory for Parallel & Distributed Processing National University of Defense Technology Changsha China Department of Computer Science & Engineering Chinese University of Hong Kong Hong Kong China

Strongly promoted by the leading industrial companies, cloud computing becomes increasingly popular in re-cent years. The growth rate of cloud computing surpasses even the most optimistic predictions. A cloud application is a large-scale distributed system that consist a lot of distributed cloud nodes. How to make optimal deployment of cloud applications is a challenging research problem. When deploying a cloud application to the cloud environment, cloud node ranking is one of the most important approaches for selecting optimal cloud nodes for the cloud application. Traditional ranking methods usually rank the cloud nodes based on their QoS values, without considering the communication performance between cloud nodes. However, such kind of node relationship is very important for the communication-intensive cloud applications (e.g., Message Passing Interface (MPI) programs), which have a lot of communications between the selected cloud nodes. In this paper, we propose a novel clustering-based method for selecting optimal cloud nodes for deploying communication-intensive applications to the cloud environment. Our method not only takes into account the cloud node qualities, but also the communication performance between different nodes. We deploy several well-known MPI programs on a real-world cloud and compare our method with other methods. The experimental results show the effectiveness of our cluster-based method.

关键词： Time factors Cloud computing Benchmark testing Quality of service Servers Clustering algorithms Databases

来源：评论

学校读者我要写书评

暂无评论

Minimizing redundant paths for coding-based IP congestion control

Minimizing redundant paths for coding-based IP congestion co...

引用

International conference on Computer Sciences and Convergence Information Technology (ICCIT)

作者： Yuan Yuan Shengyun Liu Yuxing Peng National Laboratory for Parallel and Distributed Processing College of Computer National University of Defense Technology Changsha China

Network coding brings a new solution for IP congestion control, since more than one buffered packets can be encoded together and removed as a coded packet. This may significantly decrease the packet loss during the congestion, but at the cost of building redundant paths. However, how to minimize the overhead of redundant paths turns out to be a NP-hard problem. In this paper, we propose a novel approximation algorithm called FlowGrouping, which transforms the redundant paths building problem into a limited clique partition problem by increasing edge weights, and can find a good approximate solution within O(n 3 ) computation time.

关键词： Encoding Partitioning algorithms Buildings Merging Approximation methods Network coding IP networks

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：