检索结果-内蒙古大学图书馆

12th international conference on parallel processing and applied mathematics (PPAM)

作者： Jastrzab, Tomasz Silesian Tech Univ Inst Informat Gliwice Poland

ISBN: (纸本)9783319780245;9783319780238

In the paper we study the induction of minimal nondeterministic finite automata consistent with the sets of examples and counterexamples. the induced automata are minimal with respect to the number of states. We devise a generic parallel induction algorithm and two original parallelization schemes. the schemes take into account the possibility of solving the induction task on a PC with a multi-core processor. We consider theoretically different possible configurations of the parallelization schemes. We also provide some experimental results obtained for selected configurations.

关键词： parallel algorithm Nondeterministic finite automaton Grammatical inference

来源：评论

学校读者我要写书评

暂无评论

Comparison of parallel Time-Periodic Navier-Stokes Solvers 12th

Comparison of Parallel Time-Periodic Navier-Stokes Solvers

引用

12th international conference on parallel processing and applied mathematics (PPAM)

作者： Arbenz, Peter Hupp, Daniel Obrist, Dominik Swiss Fed Inst Technol Comp Sci Dept Zurich Switzerland Univ Bern ARTORG Ctr Bern Switzerland

ISBN: (纸本)9783319780245;9783319780238

In this paper we compare two different methods to compute time-periodic steady states of the Navier-Stokes equations. the first one is a traditional time-stepping scheme which has to be evolved until the state is reached. the second one uses periodic boundary conditions in time and uses a spectral discretization in time. the methods are compared with regard to accuracy and scalability by solving for a time-periodic Taylor-Green vortex. We show that the time-periodic steady state can be computed much faster with the spectral in time method than with the standard time-stepping method if the Womersley number is sufficiently large.

关键词： parallel-in-time Time-periodic Navier-Stokes equations Taylor-Green vortex

来源：评论

学校读者我要写书评

暂无评论

parallel Divide-and-Conquer Algorithm for Solving Tridiagonal Eigenvalue Problems on Manycore Systems 12th

Parallel Divide-and-Conquer Algorithm for Solving Tridiagona...

引用

12th international conference on parallel processing and applied mathematics (PPAM)

作者： Hirota, Yusuke Imamura, Toshiyuki RIKEN Adv Inst Computat Sci Kobe Hyogo Japan

ISBN: (纸本)9783319780245;9783319780238

We present a new parallel divide-and-conquer (DC) algorithm based on an execution scheduling by batched kernels for solving real-symmetric tridiagonal eigenvalue problems on manycore systems. Our algorithm has higher parallelism and requires less global synchronizations than a conventional algorithm. We compared the performance of the solver based on our algorithm with that of Intel MKL's DC solver and PLASMA's one on Xeon E5, Xeon Phi Knights Corner, and Xeon Phi Knights Landing. the numerical tests show that the implementation of our algorithm is comparable to Intel MKL on Xeon E5 and outperforms Intel MKL and PLASMA on the two Xeon Phi systems.

关键词： Divide-and-Conquer Algorithm Eigenvalue problem Manycore Xeon Phi

来源：评论

学校读者我要写书评

暂无评论

Development and Evaluation of Chat-bot Systems: the Applications of Citizen Service Procedures

Development and Evaluation of Chat-bot Systems: The Applicat...

引用

IIAI international conference on Advanced applied Informatics (IIAIAAI)

作者： Yuhei Kotsuka Ryo Murakami Sumika Arima Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba city Japan Faculty of Engineering Information and Systems University of Tsukuba Tsukuba city Japan

ISBN: (纸本)9781728126289

In this research, we developed Chat-bot systems (CB) to support a major part of citizen services of a city office in Japan. Two experiments were conducted to evaluate the effects of the CB quantitatively one is about the supply-side, and the other is about demand-side of the citizen services procedure. As the result of Experiment#1 of the supply-side, staff-to-staff work variation was reduced much, and no significant deterioration is observed in efficiency and effectiveness even when the city staffs respond to a service area without pre-memorized knowledge. On the other hand in demand-side, Experiment#2 is to evaluate the ability improvement of the citizens in the citizen service preparation through the CB, particularly to diverse citizens. As the result of evaluations, both the completeness and the time for the preparations are much improved by CB of citizen service procedure, because one-by-one information branch in CB is better than the city's Homepage which requires the window scroll for choosing information adapting to themselves.

关键词： government data processing human computer interaction interactive systems natural language processing public administration Government data processing Civil service computer human interaction interactive systems Natural Language processing Citizens Band Radio service areas citizens

来源：评论

学校读者我要写书评

暂无评论

Data Compilation Procedure of the Nuclear Reaction Data on the Unified Research Management System

Data Compilation Procedure of the Nuclear Reaction Data on t...

引用

IIAI international conference on Advanced applied Informatics (IIAIAAI)

作者： Hiroshi Masui Tomoyuki Baba Xun Shao Information Processing Center Kitami Institute of Technology Kitami Japan Graduate School of Information Science Kitami Institute of Technology Kitami Japan

Data compilation activity in the nuclear physics has been continued for over 40 years. In addition to neutron data for safe operation of nuclear reactors, utilization of charged particle nuclear reaction data has been promoted in various fields such as science, engineering and medical appellations. the complied data are classified into two categories. One is obtained from the experimental observation and the other is the evaluation deduced from the theoretical investigation combined with the model of reaction mechanism. the nuclear reaction data is compiled from the published scientific articles including the bibliographic information in addition to the experimental one, and the data is published on the website of the organization for the data compilation. In this work, we propose that the process of the data compilation is performed on a new environment for the scientific collaboration, which is called the Unified Research Management System (URMS), and aim to make the current compilation flow correspond to the services on URMS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

parallel Computing of Linear Systems with Linearly Dependent Intervals in MATLAB 12th

Parallel Computing of Linear Systems with Linearly Dependent...

引用

12th international conference on parallel processing and applied mathematics (PPAM)

作者： Kral, Ondrej Hladik, Milan Charles Univ Prague Dept Appl Math Fac Math & Phys Malostranske Nam 25 Prague 11800 Czech Republic

ISBN: (纸本)9783319780542;9783319780535

We implemented several known algorithms for finding an interval enclosure of the solution set of a linear system with linearly dependent interval parameters. To do that we have chosen MATLAB environment with use of INTLAB and VERSOFT libraries. Because our implementation is tested on Toeplitz and symmetric matrices, among others, there is a problem with a sparsity. We introduce straightforward format for representing such matrices, which seems to be almost as effective as the standard matrix representation but with less memory demands. Moreover, we take an advantage of parallel Computing Toolbox to enhance the performance of implemented methods and to get more insights on how the methods stands in a scope of a tightness-performance ratio. the contribution is a time-tightness performance comparison of such methods, memory efficient representation and an exploration of explicit parallelization impact.

关键词： Interval system Linear dependency parallelization MATLAB INTLAB

来源：评论

学校读者我要写书评

暂无评论

Implementation and Performance Analysis of 2.5D-PDGEMM on the K Computer 12th

Implementation and Performance Analysis of 2.5D-PDGEMM on th...

引用

12th international conference on parallel processing and applied mathematics (PPAM)

作者： Mukunoki, Daichi Imamura, Toshiyuki RIKEN Adv Inst Computat Sci Chuo Ku 7-1-26 Minatojima Minami Machi Kobe Hyogo 6500047 Japan

ISBN: (纸本)9783319780245;9783319780238

In this study, we propose a 2D-compatible implementation of 2.5D parallel matrix multiplication (2.5D-PDGEMM), which was designed to perform computations of 2D distributed matrices on a 2D process grid. We evaluated the performance of our implementation using 16384 nodes (131072 cores) on the K computer, which is a highly parallel computer. the results show that our 2.5D implementation outperforms conventional 2D implementations including the ScaLAPACK PDGEMM routine, in terms of strong scaling, even when the cost for matrix redistribution between 2D and 2.5D distributions is included. We discussed the performance of our implementation by providing a breakdown of the performance and describing the performance model of the implementation.

关键词： Matrix multiplication 2.5D algorithm parallel computing Communication-avoiding ScaLAPACK compatibility K computer

来源：评论

学校读者我要写书评

暂无评论

Improving the representation of hot flotation testing through the application of a novel, double batch flotation machine

引用

MINERALS ENGINEERING 2018年 123卷 63-70页

作者： Bernardis, F. L. Wallenius, J. M. CP Kelco Oy POB 500 Aanekoski 44101 Finland

Hot batch flotation tests are often applied to reduce risks in plant trials as they combine the benefits of matching complex plant feed stream compositions with the high precision of lab scale batch flotation testwork. One of the weaknesses of hot flotation tests is the sequential nature of the testwork, where ageing of pulp samples can influence metallurgical performance. When present this interference could at best generate inconclusive results, and at worst, inaccurate conclusions. To improve the reliability of test data, CP Kelco has developed a novel, double batch flotation machine for conducting parallel hot flotation tests on live flotation streams. Hot flotation tests with a sensitive Ni cleaner feed stream, principally containing pyrrhotite, pentlandite, magnesite and talc, were used to demonstrate the principles and potential of the device. parallel tests with the double flotation machine were shown to afford reproducible Ni recovery-grade curves, while sequential tests conducted with a 30 min ageing period showed a marked change in Ni recovery-grade curves. In this study, selectivity curves have been beneficial in identifying the sources of the changes caused by ageing, which appear to be due to an increased recovery of pyrrhotite.

关键词： Double flotation machine parallel hot flotation tests Ageing ore Selectivity curves Pyrrhotite

来源：评论

学校读者我要写书评

暂无评论

Classification of Benign or Malignant Cell Nuclei using Nucleolus

Classification of Benign or Malignant Cell Nuclei using Nucl...

引用

IIAI international conference on Advanced applied Informatics (IIAIAAI)

作者： Noriaki Kobayashi Yuji Iwahori Takashi Iwamoto Jun Ueda Boonserm Kijsirikul Aili Wang Dept. of Computer Science Chubu University Kasugai Japan Dept. of Biomedical Sciences Chubu University Kasugai Japan Center for Advanced Research and Education Asahikawa Medical University Asahikawa Japan Dept. of Computer Eng. Chulalongkorn University Bangkok Thailand Higher Education Key Lab. Harbin Univ. of Sci. and Tech. Harbin China

ISBN: (纸本)9781728126289

Cytology directly examining cells in the early detection of cancer plays an important role in the medical diagnosis, but this diagnosis depends on the experience and technology of a pathologist. Problem is that it costs time for the examination and its objectivity is poor in the less experienced pathologist. Although there are some previous researches to detect nuclei, this paper proposes the automatic classification of benign or malignant of cell nuclei based on the characteristics that nucleolus has the features of malignant cell nuclei and appears frequently in the malignant cell with cancer. Classification of benign or malignant cell nuclei is performed by detecting nucleoli and counting the number of nucleolus detected.

关键词： cancer cellular biophysics image classification medical image processing Nucleus Cell nucleus Cell Nucleolus cellular biophysics Medical image processing cancer cell Image classification Benign nuclei (nuclear physics) Taxonomy Automatic classification Early Diagnosis Medical diagnosis

来源：评论

学校读者我要写书评

暂无评论

parallel Crowd Simulation Based on Power Law 8

Parallel Crowd Simulation Based on Power Law

引用

8th international conference on Virtual Reality and Visualization (ICVRV)

作者： Wang, Ji Mao, Tianlu Song, Xiyuan Liu, Shaohua Jiang, Hao Wang, Zhaoqi Chinese Acad Sci Inst Comp Technol Beijing Key Lab Mobile Comp & Pervas Device Beijing Peoples R China Beijing Univ Posts & Telecommun Sch Elect Engn Beijing Peoples R China Univ Elect Sci & Technol China Inst Elect & Informat Engn Guangdong Beijing Peoples R China

ISBN: (纸本)9781538684979

Crowd simulation technology is increasingly used in the fields of film, animation, games, military training, and public safety. In this paper, we propose a parallel crowd simulation model based on Power Law. this model use CUDA architecture to parallelize the Power Law model on GPU, so that each agent's behavior simulation is synchronized on different threads. this model considers the fine effects of the microscopic model while significantly improving the model simulation efficiency, making it possible to simulate large-scale crowds in real time and can accurately obtain the status information of each agent in each frame.

关键词： Computing methodologies Modeling and simulation Model development and analysis Modeling methodologies Computing methodologies Computer graphics Animation Motion processing

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：