检索结果-内蒙古大学图书馆

International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI)

作者： Su-yu Huang Bo Zhang School of Computer Science Wuhan Donghu University Wuhan China

ISBN: (纸本)9781728150956

In this paper, aiming at the problems of traditional K-means clustering algorithm in big data processing, such as performance and determination of initial clustering center, an improved k-means clustering algorithm based on Hadoop platform is proposed. This algorithm uses canopy algorithm and cosine similarity to calculate, optimizes the determination of initial clustering center by K-means algorithm, and uses parallel computing framework to expand the algorithm in parallel. To adapt to big data processing. The experimental results show that the improved k-means clustering algorithm based on Hadoop platform has better clustering effect, and also has good speedup and scalability when processing a large number of data.

关键词： Clustering algorithms Scalability Classification algorithms Partitioning algorithms Computer science Big Data parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Mathematical Simulation of a Massive Star Evolution Based on a Gasdynamical Model

引用

Mathematical Models and Computer Simulations 2018年第3期10卷 357-362页

作者： Babakov, A.V. Popov, M.V. Chechetkin, V.M. Institute for Computer Aided Design Russian Academy of Sciences Moscow 123056 Russian Federation École Normale Supérieure de Lyon CRAL (UMR CNRS 5574) Université de Lyon 1 Lyon France Keldysh Institute of Applied Mathematics Russian Academy of Sciences Moscow 125047 Russian Federation National Research Nuclear University MEPhI Moscow 115409 Russian Federation Kurchatov Institute of Atomic Energy Moscow 123182 Russian Federation

The flow method, together with an algorithm for self-gravity computations, is applied for the three-dimensional modeling of astrophysical flows. This method is based on the difference approximations of conservation laws written for finite volumes. It is implemented within the FLUX simulation tool box, designed for computer systems with a cluster architecture. The problem of hydrodynamic simulation in the model of a massive star of the third generation (Pop III), which is a progenitor of a pair-instability supernova (PISN), is considered. Large-scale convective structures are produced under neutral equilibrium conditions that significantly affect the process of a supernova explosion. © 2018, Pleiades Publishing, Ltd.

关键词： aerohydrodynamics astrophysics conservative difference schemes gravity mathematical modeling numerical methods parallel algorithms supernovae vortex structures

来源：评论

学校读者我要写书评

暂无评论

A Message-Passing based Algorithm for k-Terminal Reliability 14

A Message-Passing based Algorithm for k-Terminal Reliability

引用

14th European Dependable Computing Conference (EDCC)

作者： Minh Le Weidendorfer, Josef Siemens AG Erlangen Germany Leibniz Supercomp Ctr Munich Germany

ISBN: (纸本)9781538680605

As the exact computation of the k-terminal reliability is an NP-Complete problem, runtime and memory requirements grow exponentially with the input size. Shared memory parallelization algorithms were developed for reducing runtime. However, even a relatively high amount of memory can already be exhausted within a short period of time. A message-passing based algorithm is proposed in order to circumvent the memory limitation of shared memory implementations. It is the first message-passing based algorithm for the k-terminal problem. The new algorithm is designed for the currently most efficient BDD-based method. New data structures such as the distributed BDD and a distributed hash table lead to good speedup results and load-balanced task distributions. Now the size of computable inputs are limited to the memory carried along by the available cores. The two-terminal reliability of a 17 node complete network was computed on 1024 cores of the SuperMUC within 7 minutes, using 1.28 Terabyte of memory and resulting in more than 6 billion BDD nodes.

关键词： k-terminal reliability distributed memory parallel algorithms BDD dependability analysis

来源：评论

学校读者我要写书评

暂无评论

ICCM2016: Implementation of the Parareal Algorithm to Optimize Nanoparticle Transport in Porous Media Simulations

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL METHODS 2019年第5期16卷

作者： Waghmare, Akhil Seshaiyer, Padmanabhan Harvard Univ Cambridge MA 02138 USA George Mason Univ Fairfax VA 22030 USA

This research study aims to conduct the analysis and implementation of efficient algorithms for simulations of micro and nanoparticle transport models in porous media, coupled with the Darcy-Forchheimer fluid model, modified to include electromagnetic effects. The schemes developed were implemented via a parallel infrastructure for benchmark problems with a flexible algorithm that is efficient, robust, and stable. These improvements in the reliability and efficiency of simulations of nanoparticle transport in porous media contribute to the creation of an efficient method to counteract the contaminants in groundwater, and ultimately increase the availability of clean drinking water.

关键词： Water quality computational modeling colloid transport parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Accelerating Alignment for Short Reads Allowing Insertion of Gaps on Multi-Core Cluster

Accelerating Alignment for Short Reads Allowing Insertion of...

引用

IEEE International Conference on parallel and Distributed Computing, Applications and Technologies (PDCAT)

作者： Yongjie Yang Cheng Zhong Danyang Chen School of Computer Electronics and Information Guangxi University Nanning China Dept. of Information Technology Shanghai Rural Commercial Bank Shanghai China

ISBN: (数字)9781728126166

ISBN: (纸本)9781728126173

The sequence alignment is an important basic work in analyzing large biological data. For the massive short reads alignment problem, based on the dynamic programming approach, divide and conquer principle, and FUSE kernel module, a parallel short-read alignment method allowing the optimal number of inserting gaps depending on species and sequence length is developed on multi-core cluster. The experimental results on real and synthetic data show that the proposed parallel alignment method can achieve good speedup with the same alignment accuracy as the sequential alignment method. Compared with the existing parallel alignment method, the proposed method can remarkably reduce the time of partitioning reference genome and reads files and accelerate the large-scale short-read alignment.

关键词： Genomics Bioinformatics Fuses parallel algorithms Clustering algorithms Acceleration

来源：评论

学校读者我要写书评

暂无评论

Almost Optimal Column-wise Prefix-sum Computation on the GPU 12th

Almost Optimal Column-wise Prefix-sum Computation on the GPU

引用

12th International Conference on parallel Processing and Applied Mathematics (PPAM)

作者： Tokura, Hiroki Fujita, Toru Nakano, Koji Ito, Yasuaki Hiroshima Univ Dept Informat Engn Kagamiyama 1-4-1 Higashihiroshima 7398527 Japan

ISBN: (纸本)9783319780542;9783319780535

The row-wise and column-wise prefix-sum computation of a matrix has many applications in the area of image processing such as computation of the summed area table and the Euclidean distance map. It is known that the prefix-sums of a 1-dimensional array can be computed efficiently on the GPU. Hence, the row-wise prefix-sums of a matrix can also be computed efficiently on the GPU by executing this prefix-sum algorithm for every row in parallel. However, the same approach does not work well for computing the column-wise prefix-sums, because inefficient stride memory access to the global memory is performed. The main contribution of this paper is to present an almost optimal column-wise prefix-sum algorithm on the GPU. Since all elements in an input matrix must be read and the resulting prefix-sums must be written, computation of the column-wise prefix-sums cannot be faster than simple matrix duplication in the global memory of the GPU. Quite surprisingly, experimental results using NVIDIA TITAN X show that our column-wise prefix-sum algorithm runs only 2-6% slower than matrix duplication. Thus, our column-wise prefix-sum algorithm is almost optimal.

关键词： Prefix computation parallel algorithms GPU CUDA

来源：评论

学校读者我要写书评

暂无评论

Implicit Decomposition for Write-Efficient Connectivity algorithms 32

Implicit Decomposition for Write-Efficient Connectivity Algo...

引用

27th International Heterogeneity in Computing Workshop in conjunction with 32nd IEEE International parallel and Distributed Processing Symposium (IPDPS)

作者： Ben-David, Naama Blelloch, Guy E. Fineman, Jeremy T. Gibbons, Phillip B. Gu, Yan McGuffey, Charles Shun, Julian Carnegie Mellon Univ Pittsburgh PA 15213 USA Georgetown Univ Washington DC 20057 USA MIT CSAIL Cambridge MA 02139 USA

ISBN: (纸本)9781538643686

The future of main memory appears to lie in the direction of new technologies that provide strong capacity-toperformance ratios, but have write operations that are much more expensive than reads in terms of latency, bandwidth, and energy. Motivated by this trend, we propose sequential and parallel algorithms to solve graph connectivity problems using significantly fewer writes than conventional algorithms. Our primary algorithmic tool is the construction of an o(n)-sized implicit decomposition of a bounded-degree graph G on n nodes, which combined with read-only access to G enables fast answers to connectivity and biconnectivity queries on G. The construction breaks the linear-write "barrier", resulting in costs that are asymptotically lower than conventional algorithms while adding only a modest cost to querying time. For general non-sparse graphs on m edges, we also provide the first parallel algorithms for connectivity and biconnectivity that require o(m) writes and O(m) operations. These algorithms provide insight into how applications can efficiently process computations on large graphs in systems with read-write asymmetry.

关键词： Random access memory Computational modeling Task analysis parallel algorithms Writing Standards Clustering algorithms"

来源：评论

学校读者我要写书评

暂无评论

Recent advancements in parallel algorithms for string matching on computing models - A survey and experimental results

Recent advancements in parallel algorithms for string matchi...

引用

International Conference on Advanced Computing, Networking and Security, ADCONS 2011

作者： Someswararao, Chinta Raju, K. Butchi Appaji, S.V. Raju, S. Viswanadha Reddy, K.K.V.V.V.S. Department of CSE SRKR Engg. College Bhimavaram AP India Department of CSE GRIET Hyderabad AP India School of IT JNTUH Hyderabad AP India Rayalasheema University AP India

ISBN: (纸本)9783642292798

The increase in huge amount of data is seen clearly in present days because of requirement for storing more information. To extract certain data from this large database is a very difficult task, including text processing, information retrieval, text mining, pattern recognition and DNA sequencing. So we need concurrent events and high performance computing models for extracting the data. This will create a challenge to the researchers. One of the solutions is parallel algorithms for string matching on computing models. This work reviews typical algorithms and profiles their performance under various situations to study the influence of the number, the length, and the character distribution. This paper provides various available techniques that are suggested by several authors with its merits and demerits. In this we say that this survey will help the researchers to develop a better. © 2012 Springer-Verlag.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Faster bit-parallel algorithms for unordered pseudo-tree matching and tree homeomorphism

Faster bit-parallel algorithms for unordered pseudo-tree mat...

引用

作者： Kaneta, Yusaku Arimura, Hiroki Raman, Rajeev Graduate School of Information Science and Technology Hokkaido University N14 W9 Sapporo 060-0814 Japan Department of Computer Science University of Leicester University Road Leicester LE1 7RH United Kingdom

In this paper, we consider the unordered pseudo-tree matching problem, which is a problem of, given two unordered labeled trees P and T, finding all occurrences of P in T via such many-to-one matchings that preserve node labels and parent-child relationship. This problem is closely related to the tree pattern matching problem for XPath queries with child axis only. If m>w, we present an efficient algorithm that solves the problem in O(nmlog(w)/w) time using O(hm/w+mlog(w)/w) space and O(mlog(w)) preprocessing on a unit-cost arithmetic RAM model with addition, where m is the number of nodes in P, n is the number of nodes in T, h is the height of T, and w is the word length, and we assume that w≥logn. We also discuss a modification of our algorithm for the unordered tree homeomorphism problem, which corresponds to the tree pattern matching problem for XPath queries with descendant axis only. © 2011 Elsevier B.V.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

parallelized Top-k Route Search with User's Preferences

Parallelized Top-k Route Search with User's Preferences

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Sen Zhang Youming Ge Qun Jiang Haihang Li Yubao Liu School of Data and Computer Science Sun Yat-Sen University Guangzhou P.R.China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou P.R.China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

In this paper, we consider the top-k route search with user's preferences. Specifically, given a set of POIs, our problem is to find k different routes from a source POI to a target POI such that the constraint on route cost and the POIs covered by the route can optimally satisfy the user-defined weighted feature preference. It has been shown that the problem is NP-hard. The challenge is how to select from plenty of POIs and construct an optimal route especially when the size of candidate POIs is large. In order to support top-k route search on a large dataset or with a looser budget constraint, we propose a parallel method on a single machine to speed up the search. Moreover, we adopt further effective pruning strategies to reduce the search space. The experimental results on real-world datasets show that our proposed parallel method is much efficient, about 10 times faster than the existing serial algorithm at best.

关键词： Roads Search problems parallel algorithms Big Data Task analysis Aggregates

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：