检索结果-内蒙古大学图书馆

Convergence analysis for sigma-pi-sigma neural network based on some relaxed conditions

INFORMATION SCIENCES 2022年 585卷 70-88页

作者： Fan, Qinwei Kang, Qian Zurada, Jacek M. Xian Polytech Univ Sch Sci Xian 710048 Peoples R China Univ Louisville Dept Elect & Comp Engn Louisville KY 40292 USA Spoleczna Akad Nauk PL-90011 Lodz Poland

The main objective of the study is to investigate the Takagi-Sugeno fuzzy-model-based networked control system under the fuzzy event-triggered H-infinity control scheme. Instead of considering the conventional network transmission delay, the paper introduces the probability distribution based network transmission delay, which is more compatible with real time-simulations. Due to distributed transmission delay, the closed-loop network con-trol system has become distributed delay system. To make use of full information about the membership function, the Lyapunov function candidate is designed as fuzzy-membership-dependent Lyapunov function. A switching concept with respect to the rate of changes in membership functions is introduced to design the optimal control gain matrices for the considered system. The main advantage of the fuzzy-membership-dependent Lyapunov function is that it can ensure the less conservatism of the result without increasing the number of decision variables. To validate the effectiveness of the proposed approach, two kinds are real-time systems are taken into account, one is nonlinear mass-spring-damper model, followed by an industrial example, say, surface mounted permanent mag-net synchronous motor model. The corresponding simulation results show the superiority of the proposed results over the existing works. (C) 2021 Elsevier Inc. All rights reserved.

关键词： Sigma-Pi-sigma neural network batch algorithm Boundedness Convergence

来源：评论

学校读者我要写书评

暂无评论

The Optimal Source Bias Method based on RMC code

引用

ANNALS OF NUCLEAR ENERGY 2018年 121卷 525-530页

作者： Pan, Qingquan Rao, Junjie Wang, Kan Zhou, Yuying Tsinghua Univ Dept Engn Phys Beijing 100084 Peoples R China Univ Chinese Acad Sci Shanghai Inst Appl Phys Beijing 100049 Peoples R China

When criticality calculation is performed with Reactor Monte Carlo (RMC) code for reactor analysis, the fission source iterative method is selected. There are two strategies to sample the fission neutrons in each fissile region: the conventional Proportional Stratified Sampling Method that focuses on the real physical process, and the author-developed Optimal Stratified Sampling Method that focuses on the optimal mathematics treatment. The Optimal Stratified Sampling Method have the effect of global variance reduction and could be easily implemented with the use of optimal source bias coefficients. However, the calculation of optimal source bias coefficients needs the values of variances in advance, which is almost impossible. To meet the requirement, a batch Approximate Method is then put forward. The batch Approximate Method based on the batch algorithm and Shannon Entropy Diagnosis, eliminates the correlation among cycles during the criticality calculation. Combining the Optimal Stratified Sampling Method and the batch Approximate Method, the Optimal Source Bias Method is established and developed in RMC code. The Optimal Source Bias Method was tested with a standard Pressurized Water Reactor assembly. The effect of global variance reduction was found, as well as the flattening of variance distribution. So, the new method is valuable for the high fidelity computation of the RMC code. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： RMC Stratified Sampling Method batch algorithm Variance reduction

来源：评论

学校读者我要写书评

暂无评论

Blind Equalization of Multilevel Signals via Support Vector Regression 10

Blind Equalization of Multilevel Signals via Support Vector ...

引用

10th International Conference on Advanced Computational Intelligence (ICACI)

作者： Sun, Chao Yang, Ling Chen, Li Zhang, Jiliang Yang, Rong Lanzhou Univ Sch Informat Sci & Engn Lanzhou Gansu Peoples R China

ISBN: (纸本)9781538643624

In this paper, two families of batch algorithms are constructed in the support vector regression (SVR) framework for blind equalization of multilevel signals. Specifically, the error functions of constant modulus algorithm CMA(p, 2) and multimodulus algorithm MMA(p,2) are contained in the penalty term of the SVR. Simulation results show that the proposed MMA(p,2)-based algorithms perform better than the CMA(p,2)based ones, which exhibit lower residual intersymbol interference (ISI) and higher probability of convergence. With respect to conventional dual-mode scheme, the MMA(p,2)-based algorithms show better performance in the case of higher noise or smaller data block, therefore they are robust and more suitable for multilevel signals. In addition, they avoid tedious switching mechanism of dual-mode scheme and overcome phase rotation.

关键词： blind equalization batch algorithm support vector regression constant modulus algorithm multimodulus algorithm

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Trajectory Compression algorithms on Marine Surveillance data

Performance Analysis of Trajectory Compression Algorithms on...

引用

International Conference on Advances in Computing, Communications and Informatics (ICACCI)

作者： Singh, Ashutosh Kumar Aggarwal, Vinay Saxena, Pavas Prakash, Om Ctr Artificial Intelligence & Robot Bangalore 560093 Karnataka India

ISBN: (纸本)9781509063673

This paper provides a comprehensive empirical performance analysis of various trajectory compression algorithms for offline compression of trajectory data of sea borne objects which include boats, trawlers, ships etc. Our empirical study uses data from a surveillance application. The surveillance application receives data from various sensors which include GPS integrated sensors, Radars, AIS, S-AIS etc. The algorithms under consideration include the classical Douglas Peucker algorithm, SQUISH, OLDCAT, SPM. These algorithms have been compared with respect to the capability to preserve the spatio-temporal information and execution time.

关键词： Data Compression Lossy Compression Lossless Compression Online algorithm batch algorithm Coastal Surveillance System AIS (Automatic Identification System) S-AIS Coastal Surveillance Radar GPS Entropy

来源：评论

学校读者我要写书评

暂无评论

A Web Service Approach for Integrating e-Health Data in a Low Bandwidth Environment 2

A Web Service Approach for Integrating e-Health Data in a Lo...

引用

Pan African Conference on Science Computing and Telecommunications PACT

作者： Ndume, Vitalis Nkansah-Gyekye, Yaw Ko, Jesuk NM AIST CoCSE Arusha Tanzania Gwangju Univ Dept Healthcare Management Gwangju South Korea

ISBN: (纸本)9781479968992

This paper describes a batch algorithm for integrating heterogeneous e-Health data using Web Service Model in a low bandwidth environment. The focus is on the problem of higher volume of data stored in relational databases and the integration architecture with uncertain schema. In specific the paper presents a batch algorithm for efficient integration and management of heterogeneous health records in an environment with higher network disconnection. The web service application for implementation was developed using Visual Basic .NET. The validation and test cases of the software was done using Demographical Surveillance data sets as well as baseline census data for sample vital registration with verbal autopsy. The result indicates that the proposed algorithm is capable of transferring data in a network with higher disconnection. The analysis of the execution time among four configured relational databases indicates that time taken to transfer data between MySQL engine and SQL server engine is shorter compared to other relation databases under the test. In addition, the architecture and the embedded algorithm may be useful for integrating e-Health records from different research group so that scientists can access them at a single point.

关键词： Integration e-Health batch algorithm Staging database

来源：评论

学校读者我要写书评

暂无评论

On Steepest Descent Adaptation: A Novel batch Implementation of Blind Equalization algorithms

On Steepest Descent Adaptation: A Novel Batch Implementation...

引用

IEEE Global Telecommunications Conference (GLOBECOM 2010)

作者： Han, Huy-Dung Ding, Zhi Hu, Junqiang Qian, Dayou Univ Calif Davis Davis CA 95616 USA

ISBN: (纸本)9781424456383

Blind equalization typically achieves parameter optimization through cost minimization using stochastic gradient descent in both batch and adaptive algorithms. In general, stochastic descent algorithms typically require large number of iterations or long data samples to converge. The batch approach is generally based on data reuse (recycling) and refiltering to recompute the cost gradient after each iterative parameter update, thereby causing long processing delays. In this work, we present a novel steepest descent batch algorithm that does not require data recycling. We consider the popular Constant Modulus algorithm and the Minimum Entropy Deconvolution for normalized cumulant maximization. Both algorithms utilize 4-th order cumulants. The proposed steepest descent batch implementation of both algorithms converge rapidly in a few iterations and deliver superior performance without the delay due to data recycling and refiltering(1).

关键词： constant modulus blind equalization frequency domain implementation batch algorithm open-loop

来源：评论

学校读者我要写书评

暂无评论

Using batch algorithm for kernel blind source separation

引用

NEUROCOMPUTING 2005年第1-3期69卷 273-278页

作者： Sun, ZL Huang, DS Zheng, CH Shang, L Chinese Acad Sci Hefei Inst Intelligent Machines Intelligent Comp Lab Hefei 230031 Peoples R China Univ Sci & Technol China Dept Automat Hefei 230026 Anhui Peoples R China

By combining the batch algorithm with the kernel trick, an improved kernel blind source separation (IKBSS) is presented. The lKBSS has not only a better performance but also a less computational complexity compared to... 详细信息

关键词： batch algorithm Kernel trick blind source separation feature vector selection

来源：评论

学校读者我要写书评

暂无评论

batch and median neural gas

引用

NEURAL NETWORKS 2006年第6-7期19卷 762-771页

作者： Cottrell, Marie Hammer, Barbara Hasenfuss, Alexander Villmann, Thomas Tech Univ Clausthal Inst Comp Sci D-38678 Clausthal Zellerfeld Germany Univ Paris 01 SAMOS MATISSE F-75634 Paris 13 France Univ Leipzig Clin Psychotherapy D-04107 Leipzig Germany

Neural Gas (NG) constitutes a very robust clustering algorithm given Euclidean data which does not suffer from the problem of local minima like simple vector quantization, or topological restrictions like the self-organizing map. Based on the cost function of NG, we introduce a batch variant of NG which shows much faster convergence and which can be interpreted as an optimization of the cost function by the Newton method. This formulation has the additional benefit that, based on the notion of the generalized median in analogy to Median SOM, a variant for non-vectorial proximity data can be introduced. We prove convergence of batch and median versions of NG, SOM, and k-means in a unified formulation, and we investigate the behavior of the algorithms in several experiments. (c) 2006 Elsevier Ltd. All rights reserved.

关键词： neural gas batch algorithm proximity data median clustering convergence

来源：评论

学校读者我要写书评

暂无评论

Sequential updating algorithm for extracting the basis of Karhunen-Loeve transformation

Sequential updating algorithm for extracting the basis of Ka...

引用

International Conference on Image Processing (ICIP 2004)

作者： Qu, YY Zheng, NN Li, CH Yuan, ZJ Xian Jiaotong Univ Inst Artificial Intelligence & Robot Xian Peoples R China

ISBN: (纸本)0780385543

Karhunen-Loeve transformation (KLT) is a Popular method for dimensional reduction and feature extraction in image analysis. signal processing, automatic control systems, and so on, while the drawback of the KLT is expensive computation. In this paper, we propose a novel updating algorithm for KLT, the rank-k updating algorithm, which has advantages especially for image sequences: it is faster than batch algorithm, it can handle the dynamic database, and it does not save the entire database. Furthermore it makes the active learning and recognition possible in Computer vision. Finally we analyze the Computational complexity and error of the algorithm. We also show its application in face analysis. The experimental results demonstrate the efficiency Of Our algorithm.

关键词： image sequences Karhunen-Loeve transforms feature extraction computational complexity image reconstruction visual databases computer vision face recognition sequential updating algorithm Karhunen-Loeve transformation feature extraction image analysis rank-k updating algorithm image sequence batch algorithm active learning image recognition computational complexity face analysis image reconstruction

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：