检索结果-内蒙古大学图书馆

Feature-Based ordering algorithm for Data Presentation of Fuzzy ARTMAP Ensembles

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2014年第4期25卷 812-819页

作者： Oong, Tatt Hee Isa, Nor Ashidi Mat Univ Sains Malaysia Sch Elect & Elect Engn Imaging & Intelligent Syst Res Team George Town 14300 Malaysia

This brief presents a new ordering algorithm for data presentation of fuzzy ARTMAP (FAM) ensembles. The proposed ordering algorithm manipulates the presentation order of the training data for each member of a FAM ensemble such that the categories created in each ensemble member are biased toward the vector of the chosen input feature. Diversity is created by varying the training presentation order based on the ascending order of the values from the most uncorrelated input features. Analysis shows that the categories created in two FAMs are compulsively diverse when the chosen input features used to determine the presentation order of the training data are uncorrelated. The proposed ordering algorithm was tested on 10 classification benchmark problems from the University of California, Irvine, machine learning repository and a cervical cancer problem as a case study. The experimental results show that the proposed method can produce a diverse, yet well generalized, FAM ensemble.

关键词： Fuzzy ARTMAP (FAM) generalization neural network ensemble ordering algorithm pattern classification

来源：评论

学校读者我要写书评

暂无评论

Hybrid Data Regression Model Based on the Generalized Adaptive Resonance Theory Neural Network

引用

IEEE ACCESS 2019年 7卷 116438-116452页

作者： Wong, Shen Yuong Yap, Keem Siah Lim, Chee Peng Lee, Eric Wai Ming Xiamen Univ Malaysia Dept Elect & Elect Engn Sepang 43900 Malaysia Univ Tenaga Nas Dept Elect & Elect Engn Kajang 43000 Malaysia Deakin Univ Inst Intelligent Syst Res & Innovat Geelong Vic 3220 Australia City Univ Hong Kong Dept Architecture & Civil Engn Hong Kong Peoples R China

The Generalized Adaptive Resonance Theory (GART) model is a supervised online learning neural network based on an integration of Adaptive Resonance Theory (ART) and the Generalized Regression Neural Network (GRNN). It is capable of online learning, and is suitable for undertaking both classification and regression problems. In this paper, we further enhance GART (EGART) with four improvements to formulate a new EGART model. Three operating strategies for the EGART model to undertake regression problems are suggested. The first operating strategy is a fully online learning EGART model. The second operating strategy involves ordering algorithm for determining the presentation sequence of training samples during the initial training of EGART model. This strategy is considered as offline learning because a set of data samples must be available for the ordering algorithm to compute the best presentation sequence (hereinafter denoted as Ordered-EGART). The third operating strategy aims to demonstrate online learning capability of EART model (the first operating strategy) can still be resumed after training on the Ordered-EGART. It is most suitable for applications with a set of ready data samples and their sequences are predetermined by ordering algorithm prior to training of EGART model in offline mode, and triggers online learning when more new data samples become available (hereinafter denoted as IO-EGART). A series of experiments with five benchmark data sets from various application domains is conducted to assess and compare the effectiveness of the EGART model and three operating strategies with those of other methods published in literature as well as two fire safety engineering problems, i.e., predicting the thermal interface height in a single compartment fire and evacuation times in the event of fire. The results and comparisons with other approaches positively demonstrate the efficacy and applicability of EGART model as a useful data regression model for tackli

关键词： Adaptive resonance theory fire evacuation time general regression neural network ordering algorithm regression thermal interface height

来源：评论

学校读者我要写书评

暂无评论

A MIMO Receiver With Two-Dimensional ordering for Maximum Likelihood Detection in FBMC-QAM

引用

IEEE COMMUNICATIONS LETTERS 2017年第7期21卷 1465-1468页

作者： Sim, Dongkyu Lee, Chungyong Yonsei Univ Dept Elect & Elect Engn Seoul 03722 South Korea

We consider the multi-dimensional residual interference problem for a multiple-input multiple-output filter bank-based multicarrier system with quadrature amplitude modulation (MIMO-FBMC/QAM). For efficient interference cancellation, we propose a two-step MIMO maximum likelihood detection receiver with a 2-D ordering algorithm. Simulation results show the validity of the proposed receiver by comparing its bit error rate performance and computational complexity with that of other receivers.

关键词： MIMO-FBMC/QAM interference cancellation ordering algorithm maximum likelihood detection

来源：评论

学校读者我要写书评

暂无评论

On some properties of the Laplacian matrix revealed by the RCM algorithm

引用

CZECHOSLOVAK MATHEMATICAL JOURNAL 2016年第3期66卷 603-620页

作者： Pedroche, Francisco Rebollo, Miguel Carrascosa, Carlos Palomares, Alberto Univ Politecn Valencia Inst Matemat Multidisciplinaria Cami Vera S-N E-46022 Valencia Spain Univ Politecn Valencia Dept Sistemes Informat & Computacio Cami Vera S-N Valencia 46022 Spain

In this paper we present some theoretical results about the irreducibility of the Laplacian matrix ordered by the Reverse Cuthill-McKee (RCM) algorithm. We consider undirected graphs with no loops consisting of some connected components. RCM is a well-known scheme for numbering the nodes of a network in such a way that the corresponding adjacency matrix has a narrow bandwidth. Inspired by some properties of the eigenvectors of a Laplacian matrix, we derive some properties based on row sums of a Laplacian matrix that was reordered by the RCM algorithm. One of the theoretical results serves as a basis for writing an easy MATLAB code to detect connected components, by using the function "symrcm" of MATLAB. Some examples illustrate the theoretical results.

关键词： ordering algorithm reverse Cuthill-McKee algorithm graph partitioning Laplacian matrix

来源：评论

学校读者我要写书评

暂无评论

THE THRESHOLD DECISION MAKING EFFECTUATED BY THE ENUMERATING PREFERENCE FUNCTION

引用

INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISION MAKING 2013年第6期12卷 1201-1222页

作者： Aleskerov, Fuad T. Chistyakov, Vyacheslav V. Natl Res Univ Higher Sch Econ Dept Math Econ Moscow 101000 Russia Russian Acad Sci Inst Control Sci Moscow Russia Natl Res Univ Higher Sch Econ Dept Appl Math Nizhnii Novgorod 603155 Russia Natl Res Univ Higher Sch Econ Lab Algorithms & Technol Network Anal Nizhnii Novgorod 603093 Russia

Based on the leximin and leximax preferences, we consider two threshold preference relations on the set X of alternatives, each of which is characterized by an n-dimensional vector ( n >= 2) with integer components varying between 1 and m(m >= 2). We determine explicitly in terms of binomial coefficients the unique utility function for each of the two relations, which in addition maps X onto the natural 'interval' {1;2,..., vertical bar X vertical bar}, where (X) over tilde = X/I is the quotient set of X with respect to the indifference relation I on X induced by the threshold preference. This permits us to evaluate all equivalence classes and indifference classes of the threshold order on X, present an algorithm of ordering the monotone representatives of indifference classes, and restore the indifference class of an alternative via its ordinal number with respect to the threshold preference order.

关键词： Weak order surjective utility function indifference class ordinal number ordering algorithm dual preference

来源：评论

学校读者我要写书评

暂无评论

A note on fast approximate minimum degree orderings for symmetric matrices with some dense rows

引用

NUMERICAL LINEAR ALGEBRA WITH APPLICATIONS 2010年第1期17卷 43-55页

作者： Dollar, H. S. Scott, J. A. Rutherford Appleton Lab Computat Sci & Engn Dept Chilton OX11 0QX Oxon England

Recently, a number of variants of the approximate minimum degree algorithm have been proposed that aim to efficiently order symmetric matrices containing some dense rows. We compare the peformance of these variants on a range of problems and highlight their potential limitations. This leads us to propose a new variant that offers both speed and robustness. Copyright (C) 2009 John Wiley & Sons, Ltd.

关键词： approximate minimum degree ordering algorithm sparse symmetric matrices dense rows graph algorithms ordering algorithm

来源：评论

学校读者我要写书评

暂无评论

A hybrid neural network classifier combining ordered fuzzy ARTMAP and the dynamic decay adjustment algorithm

引用

SOFT COMPUTING 2008年第8期12卷 765-775页

作者： Tan, Shing Chiang Rao, M. V. C. Lim, Chee Peng Multimedia Univ Fac Informat Sci & Technol Bukit Beruang 75450 Melaka Malaysia Multimedia Univ Fac Engn & Technol Bukit Beruang 75450 Melaka Malaysia Univ Sci Malaysia Sch Elect & Elect Engn Nibong Tebal 14300 Penang Malaysia

This paper presents a novel conflict-resolving neural network classifier that combines the ordering algorithm, fuzzy ARTMAP (FAM), and the dynamic decay adjustment (DDA) algorithm, into a unified framework. The hybrid classifier, known as Ordered FAMDDA, applies the DDA algorithm to overcome the limitations of FAM and ordered FAM in achieving a good generalization/performance. Prior to network learning, the ordering algorithm is first used to identify a fixed order of training patterns. The main aim is to reduce and/or avoid the formation of overlapping prototypes of different classes in FAM during learning. However, the effectiveness of the ordering algorithm in resolving overlapping prototypes of different classes is compromised when dealing with complex datasets. Ordered FAMDDA not only is able to determine a fixed order of training patterns for yielding good generalization, but also is able to reduce/resolve overlapping regions of different classes in the feature space for minimizing misclassification during the network learning phase. To illustrate the effectiveness of Ordered FAMDDA, a total of ten benchmark datasets are experimented. The results are analyzed and compared with those from FAM and Ordered FAM. The outcomes demonstrate that Ordered FAMDDA, in general, outperforms FAM and Ordered FAM in tackling pattern classification problems.

关键词： adaptive resonance theory fuzzy ARTMAP ordering algorithm dynamic decay adjustment algorithm

来源：评论

学校读者我要写书评

暂无评论

ON OPERATING STRATEGIES OF THE FUZZY ARTMAP NEURAL NETWORK: A COMPARATIVE STUDY

引用

International Journal of Computational Intelligence and Applications 2003年第1期3卷 23-43页

作者： MEI MING KUAN CHEE PENG LIM ROBERT F. HARRISON School of Electrical & Electronic Engineering University of Science Malaysia 11800 Penang Malaysia Department of Automatic Control & Systems Engineering The University of Sheffield Mappin Street Sheffield S1 3JD United Kingdom

In this paper, the effectiveness of three different operating strategies applied to the Fuzzy ARTMAP (FAM) neural network in pattern classification tasks is analyzed and compared. Three types of FAM, namely average FAM, voting FAM, and ordered FAM, are formed for experimentation. In average FAM, a pool of the FAM networks is trained using random sequences of input patterns, and the performance metrics from multiple networks are averaged. In voting FAM, predictions from a number of FAM networks are combined using the majority-voting scheme to reach a final output. In ordered FAM, a pre-processing procedure known as the ordering algorithm is employed to identify a fixed sequence of input patterns for training the FAM network. Three medical data sets are employed to evaluate the performances of these three types of FAM. The results are analyzed and compared with those from other learning systems. Bootstrapping has also been used to analyze and quantify the results statistically.

关键词： Fuzzy ARTMAP operating strategies averaging voting ordering algorithm bootstrap

来源：评论

学校读者我要写书评

暂无评论

ROCK MEDIA MATHEMATICAL-MODELS PROCESSING

引用

MATHEMATICAL GEOLOGY 1991年第1期23卷 53-69页

作者： DRBOHLAV, K BUZKOVA, H KAIGL, J NEMEC, P STAVEBNI GEOL PRAGUECZECHOSLOVAKIA

This paper reports on mathematical models of rock media processing and on their use in designing open pit coal mines. Spatial mathematical model of rock media was processed on a 25 km2 model site, incorporating 918 borehole logs. The model is capable of providing information concerning the geological structure of every point of the investigated area by plotting geological cross-sections along given lines or by plotting contour lines of the surface or the base for thickness of chosen lithological strata. The computation of one point of a grid involves the following steps: Borehole logs are numericaly coded. The geological structure at an arbitrarily chosen point P is computed as follows. All borehole logs inside the circle (P;R) are used to compute the Z-coordinate of the ground at P by some interpolation formula chosen from those contained in the program system. Next, we check what stratum occurs topmost at boreholes inside the circle and which is most probable as the top stratum C1 at P. The Z-coordinate of the C1 stratum surface at P is computed. Then what strata occur under C1 stratum and which of them is the most probable stratum C2 is determined. The process of computation is repeated until a sequence of strata C(i) at P and Z(i) coordinates of their surfaces is ascertained. The interpolation formulas included in the system are proper linear combination of PAF (polynomial approximations formulas, linear or quadratic and weighted) and WAF (weighted average formulas). Among the various interpolation formulas, some proved more useful for tectonic fault lines, others for ordinary sedimentary surfaces.

关键词： GEOLOGICAL CROSS-SECTIONS CONTOUR LINES ordering algorithm INTERPOLATION FORMULAS COMPUTER PROGRAMS

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：