检索结果-内蒙古大学图书馆

computational performance optimization of support vector machine based on support vectors

NEUROCOMPUTING 2016年 211卷 66-71页

作者： Wang, Xuesong Huang, Fei Cheng, Yuhu China Univ Min & Technol Sch Informat & Elect Engn Xuzhou 221116 Peoples R China

The computational performance of support vector machine (SVM) mainly depends on the size and dimension of training sample set. Because of the importance of support vectors in the determination of SVM classification hyperplane, a kind of method for computational performance optimization of SVM based on support vectors is proposed. On one hand, at the same time of the selection of super-parameters of SVM, according to Karush-Kuhn-Tucker condition and on the precondition of no loss of potential support vectors, we eliminate non-support vectors from training sample set to reduce sample size and thereby to reduce the computation complexity of SVM. On the other hand, we propose a simple intrinsic dimension estimation method for SVM training sample set by analyzing the correlation between number of support vectors and intrinsic dimension. Comparative experimental results indicate the proposed method can effectively improve computational performance. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Support vector machine Support vector Sample size Intrinsic dimension computational performance

来源：评论

学校读者我要写书评

暂无评论

computational performance and cross-validation error precision of five PLS algorithms using designed and real data sets

引用

JOURNAL OF CHEMOMETRICS 2010年第5-6期24卷 320-332页

作者： Martins, Joao Paulo A. Teofilo, Reinaldo F. Ferreira, Marcia M. C. Univ Estadual Campinas Inst Chem Theoret & Appl Chemometr Lab BR-13083970 Campinas SP Brazil Univ Fed Vicosa Instrumentat & Chemometr Lab Dept Chem BR-36571000 Vicosa MG Brazil

An evaluation of computational performance and precision regarding the cross-validation error of five partial least squares (PLS) algorithms (NIPALS, modified NIPALS, Kernel, SIMPLS and bidiagonal PLS), available and widely used in the literature, is presented. When dealing with large data sets, computational time is an important issue, mainly in cross-validation and variable selection. In the present paper, the PLS algorithms are compared in terms of the run time and the relative error in the precision obtained when performing leave-one-out cross-validation using simulated and real data sets. The simulated data sets were investigated through factorial and Latin square experimental designs. The evaluations were based on the number of rows, the number of columns and the number of latent variables. With respect to their performance, the results for both simulated and real data sets have shown that the differences in run time are statistically different. PIS bidiagonal is the fastest algorithm, followed by Kernel and SIMPLS. Regarding cross-validation error, all algorithms showed similar results. However, in some situations as, for example, when many latent variables were in question, discrepancies were observed, especially with respect to SIMPLS. Copyright (C) 2010 John Wiley & Sons, Ltd.

关键词： computational performance partial least squares experimental design algorithms

来源：评论

学校读者我要写书评

暂无评论

computational performance of aggregated distillation models

引用

COMPUTERS & CHEMICAL ENGINEERING 2009年第1期33卷 296-308页

作者： Linhart, Andreas Skogestad, Sigurd Norwegian Univ Sci & Technol Dept Chem Engn N-7491 Trondheim Norway

Compartmental and aggregated modeling is used to derive low-order (reduced) dynamic models from detailed models of staged processes. In this study, the aggregated modeling method of [Levine, J., & Rouchon, R(1991). Quality control of binary distillation columns via nonlinear aggregated models. Automatica, 27, 4631 is revised with the objective of deriving computationally efficient models for real-time control and optimization applications. A simple implementation of the original method not requiring the specification of compartments is presented. The resulting DAE models are converted into ODE models by pre-solving and substituting the algebraic equations resulting from the reduction procedure, which is the key step to increase simulation speed. To study this, the performances of several full and reduced distillation models, with and without base-layer controllers, are compared using different numerical integrators. It is found that while the reduced DAE models are computationally not advantageous, the reduced ODE models decrease the simulation time by a factor of 5-10. (C) 2008 Elsevier Ltd. All rights reserved.

关键词： Model reduction Distillation Aggregated modeling computational performance Real-time optimization Singular perturbation

来源：评论

学校读者我要写书评

暂无评论

computational performance of State-Value Function Approximators based on RLS-HDP Estimators for Online DLQR Control System Design 18

Computational Performance of State-Value Function Approximat...

引用

18th UKSim-AMSS International Conference on Computer Modelling and Simulation (UKSim)

作者： Ferreira, Ernesto F. M. da Fonseca Neto, Joao Viana Moraes Rego, Patricia Helena Fed Univ Maranhho UEMA Elect Engn Grad Program PPGEE Sao Luis MA Brazil State Univ Maranhho UEMA Math & Comp Dept DEMATI Sao Luis MA Brazil

ISBN: (纸本)9781509008889

The Adaptive/Approximate Dynamic Programming (ADP) is an online design approach proposed to make possible the implementations in real time of optimal controllers based on Hamilton-Jacobi-Bellman (HJB) equation solution. In this paper, ADP schemes are presented in a Heuristic Dynamic Programming (HDP) framework, where Policy Iteration (PI) strategies in conjunction with Recursive Least Squares (RLS) methods are oriented to solve online the Riccati-type HJB equation associated with the Discrete Linear Quadratic Regulator (DLQR) problem. However, these schemes have a reasonable numerical complexity and, furthermore, numerical instability may be caused due to the covariance matrix ill-conditioning of the RLS approach. Thus, in order to improve numerical stability, as well as to reduce the computational effort spent on approximating the DLQR cost function, UDUT factorization and orthogonal decomposition methods, such as QR decomposition, are incorporated into the standard PI-HDP framework. The performance of the standard PI-HDP method and its variants are compared in terms of numerical stability and computational cost. It is shown that such variants lead to significant computational performance improvements when compared to the standard PI-HDP method.

关键词： Adaptative Control RLS DLQR computational performance UDUT QR

来源：评论

学校读者我要写书评

暂无评论

computational performance of heterogeneous ensemble frameworks on high-performance computing platforms 8

Computational performance of heterogeneous ensemble framewor...

引用

8th IEEE International Conference on Big Data (Big Data)

作者： Wang, Linhua Timsina, Prem Pandey, Gaurav Icahn Sch Med Mt Sinai Dept Genet & Genom Sci New York NY 10029 USA Mt Sinai Hlth Syst New York NY USA

ISBN: (纸本)9781728162515

To enable efficient computations on rapidly growing big data, a variety of high-performance computing (HPC) platforms, such as traditional multi-processor systems, Hadoop and cloud computing systems, have been developed. On the analytics side of big data, several innovative machine learning methods have been developed to enable the extraction of accurate and actionable knowledge from large datasets. In particular, heterogeneous ensemble algorithms, which are designed to aggregate an unrestricted variety and number of analytical models, have performed well for a variety of prediction problems. However, the performance of these algorithms in terms of computational metrics, such as time requirement, disk space consumption and memory usage, on these HPC platforms has not been systematically examined yet. Here, we address this gap in knowledge by implementing these algorithms and systematically assessing their computational performance on traditional HPC and Hadoop platforms. Our results show that these implementations used the resources, especially disk space and memory, consistent with the respective designs of the platforms. Furthermore, due to the iterative nature of the heterogeneous ensemble computations, the traditional HPC system executed them faster than Hadoop, since an in-memory design is better suited for them than a disk-based one. Overall, our study sheds new light on the computational performance of ensemble algorithms and software frameworks on two prominent HPC platforms, and offers a systematic methodology for conducting similar assessments for other data analytics methods as well. Basic source code of our heterogeneous ensemble implementations, as well as the HPC performance assessments, are available at https://***/GauravPandeyLab/HPC-Ensemble.

关键词： Ensembles predictive modeling high-performance computing Hadoop computational performance

来源：评论

学校读者我要写书评

暂无评论

computational performance Comparing of the State Estimation Problem Statementes in Polar and Rectangular Coordinates 16

Computational Performance Comparing of the State Estimation ...

引用

16th Conference on Electrical Machines, Drives and Power Systems (ELMA)

作者： Polyakov, Ilya Pazderin, Andrey Polyakova, Olga Ural Fed Univ Ural Power Engn Inst Ekaterinburg 620002 Russia

ISBN: (纸本)9781728114132

Despite the rapid development of computer technology, there is a need to increase the speed of steady state calculations and state estimation. It is connected with the calculation model dimension increasing, which is caused by smart grid concept implementation, distributed generation penetration and energy markets development. There are many papers that considered different approaches for state estimation computation speed increase by optimization mathematical operation with matrix and linear equation system solvers. In particular, some earlier papers tell that rectangular coordinates are significantly more preferable in terms of calculation speed than polar for state vector representation. This fact is necessary to check for modern computers. In this research it was examined for state estimation of three phase power system model.

关键词： computational performance power systems state estimation state estimation performance three-phase state estimation

来源：评论

学校读者我要写书评

暂无评论

computational performance of Java and C++ in processing large biomedical datasets

Computational performance of Java and C++ in processing larg...

引用

IEEE Canadian Conference on Electrical and Computer Engineering

作者： Vivanco, R Pizzi, N Natl Res Council Canada Inst Biodiagnost Winnipeg MB R3B 1Y6 Canada

ISBN: (纸本)0780375149

In the analysis of image-based biomedical data, such as functional magnetic resonance imaging (fMRI) or magnetic resonance spectroscopy (MRS), data sets from 40 to 90 12 are not uncommon, and some experimental fMRI paradigms require as much as 200 AD of storage. Software systems for the analysis of such data require a flexible data model, fast computational techniques and a graphical user interface. Object-oriented programming languages, such as Java and C++, facilitate software reuse and maintainability and provide the foundations for the development of complex data analysis applications. This paper explores the advantages and disadvantages of using these two programming environments when processing large datasets.

关键词： computational performance fMRI data analysis Java c plus

来源：评论

学校读者我要写书评

暂无评论

Edge of chaos and prediction of computational performance for neural circuit models

引用

NEURAL NETWORKS 2007年第3期20卷 323-334页

作者： Legenstein, Robert Maass, Wolfgang Graz Univ Technol Inst Theoret Comp Sci A-8010 Graz Austria

We analyze in this article the significance of the edge of chaos for real-time computations in neural microcircuit models consisting of spiking neurons and dynamic synapses. We find that the edge of chaos predicts quite well those values of circuit parameters that yield maximal computational performance. But obviously it makes no prediction of their computational performance for other parameter values. Therefore, we propose a new method for predicting the computational performance Of neural microcircuit models. The new measure estimates directly the kernel property and the generalization capability of a neural microcircuit. We validate the proposed measure by comparing its prediction with direct evaluations of the computational performance of various neural microcircuit models. The proposed method also allows us to quantify differences in the computational performance and generalization capability of neural circuits in different dynamic regimes (UP- and DOWN-states) that have been demonstrated through intracellular recordings in vivo. (c) 2007 Elsevier Ltd. All rights reserved.

关键词： neural networks spiking networks edge of chaos microcircuits computational performance network dynamics

来源：评论

学校读者我要写书评

暂无评论

Empirical and computational performance Prediction for Monopropellant Hydrazine Thruster Employed for Satellite

引用

JOURNAL OF SPACECRAFT AND ROCKETS 2009年第6期46卷 1186-1195页

作者： Han, Dong In Han, Cho Young Shin, Hyun Dong Korea Aerosp Res Inst Satellite Thermal & Prop Dept Satellite Res & & Dev Head Off Taejon 305333 South Korea Korea Adv Inst Sci & Technol Taejon 305701 South Korea

A ground hot-fire test and numerical simulations were conducted to analyze the high-temperature gas flow in a monopropellant hydrazine thruster used for the reaction control of small satellites. A 5 N grade thruster was used for these tests and simulations. The ground hot-fire test results show the basic characteristics of a hydrazine thruster and were used as verification criteria for the numerical analysis. It was found that the fraction of ammonia dissociation is an essential variable for determining the thruster performance based on a one-dimensional isentropic analysis. A relatively simple relation between the catalyst bed temperature and the fraction of ammonia dissociation adopted in the simulation showed that it reduces the analysis error from an arbitrary assumption of the fraction of ammonia dissociation without solving the complicated hydrazine catalytic reaction. The thruster performance was effectively predicted by numerical analysis, which includes the effect of fraction of ammonia dissociation. The significant features of the analysis program are that solving the complicated hydrazine decomposition process can be avoided and that two-dimensional flowfield information in the thruster can be provided covering a wide range of propellant inlet pressures from 3.45 to 24.14 bar.

关键词： I_(sp) : specific impulse M : Mach number m_p : propellant mass flow rate P_C : decomposition chamber pressure P_i : propellant inlet pressure T_c : decomposition chamber temperature u v : velocity in the x and y directions respectively ρ : density X : fraction of ammonia dissociation hydrazine analysis programme computational performance Numerical Analysis performance prediction fractions monopropellants ammonia reaction control satellites

来源：评论

学校读者我要写书评

暂无评论

Implementation of a gyrokinetic collision operator with an implicit time integration scheme and its computational performance

引用

COMPUTER PHYSICS COMMUNICATIONS 2019年 235卷 9-15页

作者： Maeyama, S. Watanabe, T. -H. Idomura, Y. Nakata, M. Nunami, M. Nagoya Univ Dept Phys Nagoya Aichi 4648602 Japan Japan Atom Energy Agcy 178-4-4 Wakashiba Kashiwa Chiba 2770871 Japan Natl Inst Fus Sci 322-6 Oroshi Cho Toki Gifu 5095292 Japan

We have implemented the Sugama collision operator in the gyrokinetic Vlasov simulation code, GKV, with an implicit time-integration scheme. The new method is versatile and independent of the details of the linearized collision operator, by means of an operator splitting, an implicit time integrator, and an iterative Krylov subspace solver. Numerical tests demonstrate stable computation over the time step size restricted by the collision term. An efficient implementation for parallel computation on distributed memory systems is realized by using the data transpose communication, which makes the iterative solver free from inter-node communications during iteration. Consequently, the present approach achieves enhancement of computational efficiency and reduction of computational time to solution simultaneously, and significantly accelerates the total performance of the application. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Gyrokinetics Collision Vlasov simulation computational performance

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：