检索结果-内蒙古大学图书馆

6th international conference on Neural Information Processing, ICONIP 1999

ISBN: (纸本)0780358716

the proceedings contain 213 papers. the topics discussed include: learning and recall of temporal sequences in network of CA3 pyramidal cells and a basket cell;spiking neuron models, for regular-spiking, intrinsically bursting, and fast-spiking neurons;the use of a multilayer feedforward neural network for mineral prospectively mapping;discrimination of seismic signals using fuzzy entropy and a new FLVQ method;weightless neural network based monitoring of screw fastenings in automated assembly;multiple descent cost competitive learning and data-compressed 3-D morphing;fuzzy Bayesian networks - a general formalism for representation, inference and learning with hybrid Bayesian networks;an optimised decision tree induction algorithm for real world data domains;a neural mechanism of hyperaccurate detection of phase advance and delay in electrosensory system of weakly electric fish;a neural model of control system for foraging trips of honeybees;a diagnostic tool for tree based supervised classification learning algorithms;optimization of non-quadratic cost functions associated with Hopfield-like neural networks: impact of initial coefficient values;evolution versus training: an investigation into combining genetic algorithms and neural networks;comparison between syntactic pattern recognition and the randomized Hough transform;automated segmentation of the lateral ventricle of MR brain by fuzzy inference;identification of a landmark in a roentgenographic cephalogram by employing the wavelet neurons;connectionist incremental learning by analogy;and approximating discrete mapping of chaotic dynamical system based on on-line EM algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ICONIP 1999, 6th international conference on Neural Information Processing - Proceedings

ICONIP 1999, 6th International Conference on Neural Informat...

引用

6th international conference on Neural Information Processing, ICONIP 1999

ISBN: (纸本)0780358716

关键词：

来源：评论

学校读者我要写书评

暂无评论

6th international conference on Computational Intelligence, 1999

6th International Conference on Computational Intelligence, ...

引用

6th international conference on Computational Intelligence, Fuzzy Days 1999

ISBN: (纸本)354066050X

the proceedings contain 84 papers. the special focus in this conference is on Computational Intelligence. the topics include: Topological theory of fuzziness;similarity based system reconfiguration by fuzzy classification and hierarchical interpolate fuzzy reasoning;a fuzzy system for fetal heart rate assessment;efficient graph coloring by evolutionary algorithms;determination of decision rules on the basis of genetic algorithms;modeling a refrigeration system using recurrent neural networks;evaluating nugget sizes of spot welds by using artificial neural network;spotting relevant information in extremely large document collections;fuzzy controller generation with a fuzzy classification method;transformation and optimization of fuzzy controllers using signal processing techniques;search of optimal error correcting codes with genetic algorithms;an unsupervised clustering with evolutionary strategy to estimate the cluster number;multi-objective optimization in evolutionary algorithms using satisfiability classes;neural network approach to design of distributed hard real-time systems;supporting traditional controller of combustion engines by means of neural networks;controlling biological wastewater treatment plants using fuzzy control and neural networks;pareto-optimality in scheduling problems;controlled Markov chain optimization of genetic algorithms;tackling epistatic problems using dynastically optimal recombination;application of artificial neural network in control of vector pulse-width modulation inverter;modeling multiple microstructure transformations in steels with a boltzmann neural net;fuzzy controllers by unconventional technologies for tentacle arms;control of robot arm approach by fuzzy pattern comparison technique;a fuzzy shapes characterization for robotics;generated connectives in many valued logic and characterization of dienes implication.

关键词：

来源：评论

学校读者我要写书评

暂无评论

recognition of facial expressions based on the Hopfield memory model

International Conference on Multimedia Computing and Systems...

引用

international conference on Multimedia Computing and Systems -Proceedings 1999年 2卷 133-137页

作者： Dai, Ying Shibata, Yoshitaka Nakano, Yasuaki Hashimoto, Koji Iwate Pref. Univ Japan

In this paper, a new method for recognizing the facial expressions by utilizing the Hopfield model is presented. In this method, the Hopfield memory model with recall capability is constructed. When a facial image is given to the Hopfield memory as an input, the all units which are at the stable states yield its associate recall pattern. Based on the composed Hopfield memory model, the relation between the reliability of the recalls and the number of faces which are memorized in the Hopfield memory is analyzed. Based on the performance of the Hopfield memory model, the scheme for the facial expressions recognition combined with the pattern matching is presented. the experimental results are shown and analyzed.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Comparison between syntactic pattern recognition and the randomized Hough transform

Comparison between syntactic pattern recognition and the ran...

引用

international conference on Neural Information Processing

作者： L.T. Tan C.P. Lian C.J.S. De Silva University of Western Australia Perth WA AU

In view of the increasing demand on cytologic diagnostic and screening tests for early breast cancer patients, the paper reports on the attempt by the authors to automate the process of analysing cytology images. the novel feature of the diagnostic approach is the application of syntactic pattern recognition in segmenting occluded cells (or blobs) to count the individual cells that make up these blobs.

关键词： pattern recognition Image edge detection Erbium Breast cancer Tumors Medical treatment Electronic equipment testing Image analysis Image segmentation Color

来源：评论

学校读者我要写书评

暂无评论

the discrete moments of the circles 8th

The discrete moments of the circles

引用

8th international conference on Discrete Geometry for Computer Imagery, DGCI 1999

作者： Žunić, Joviša University of Novi Sad Trg D. Obradovića 6 Novi Sad21000 Serbia

ISBN: (纸本)3540656855

the moment of (p,q)-order, mp,q(C), of a circle C given by (x-a)2 + (y-b)2 ≤ r2, is defined to be (Formula Presented). It is naturally to c assume that the discrete moments dmp,q(C), defined as (Formula Presented) can be a good approximation for mp,q(C). this paper gives an answer what is the order of magnitude for the difference between a real moment mp,q(C) and its approximation dmp,q(C), calculated from the corresponding digital picture. Namely, we estimate (Formula Presented) in function of the size of the considered circle C and its center position if p and q are assumed to be integers. these differences are upper bounded with (Formula Presented), where e is an arbitrary small positive number. the established upper bound can be understood as very sharp. the result has a practical importance, especially in the area of image processing and pattern recognition, because it shows what the picture resolution should be used in order to obtain a required precision in the parameter estimation from the digital data taken from the corresponded binary picture. © Springer-Verlag Berlin Heidelberg 1999.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Top-down and bottom-up processing of spatiotemporal patterns in a fully recurrent network of nonmonotonic neurons

Top-down and bottom-up processing of spatiotemporal patterns...

引用

international conference on Neural Information Processing

作者： S. Murakami M. Morita Doctoral Program in Engineering University of Tsukuba Ibaraki Japan Institute of Engineering Mechanics and Systems University of Tsukuba Ibaraki Japan

A fully recurrent neural network with a nonmonotonic activation function that treats temporal sequences without expanding them into spatial patterns is described. this network associates a complex spatiotemporal pattern with a simple one using trajectory attractors formed by simple learning. Computer simulations show that the model not only has high recognition and generation abilities but can also perform advanced processing using bidirectional interactions.

关键词： Spatiotemporal phenomena Intelligent networks Neurons Recurrent neural networks Biological neural networks pattern recognition Systems engineering and theory Computer simulation Neural networks Delay

来源：评论

学校读者我要写书评

暂无评论

Neural discriminating analysis on preprocessed data

Neural discriminating analysis on preprocessed data

引用

IEEE international conference on Electronics, Circuits and Systems (ICECS)

作者： E.S. Caner J.M. de Seixas Brazil COPPE/EE/UFRJ Rio de Janeiro Brazil

A neural discriminating analysis is developed in order to reduce significantly the dimension of input data spaces in pattern recognition problems. It searches for the restricted set of orthogonal directions in the input data space that classifies events with maximum discrimination efficiency. Improvements on the performance of the resulting compact discriminator are shown to be obtained when the discriminating analysis is performed on an image space that results from the application of a preprocessing map on the original input data space. As a case study, a particle discriminator for high-energy experimental physics is successfully developed, achieving efficiencies above 97%. the implementation of the method in a multiprocessor environment based on digital signal processor (DSP) technology is also addressed for online operation.

关键词： Data analysis Space technology pattern analysis pattern recognition Image analysis Performance analysis Data preprocessing Physics Digital signal processors Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

Shape retrieval by inexact graph matching

International Conference on Multimedia Computing and Systems...

引用

international conference on Multimedia Computing and Systems -Proceedings 1999年 1卷 772-776页

作者： Huet, Benoit Cross, Andrew D.J. Hancock, Edwin R. Univ of York York United Kingdom

this paper describes a graph-matching technique for recognising line-pattern shapes in large image databases. the methodological contribution of the paper is to develop a Bayesian matching algorithm that uses edge-consistency and node attribute similarity. this information is used to determine the a posteriori probability of a query graph for each of the candidate matches in the database. the node feature-vectors are constructed by computing normalised histograms of pairwise geometric attributes. Attribute similarity is assessed by computing the Bhattacharyya distance between the histograms. recognition is realised by selecting the candidate from the database which has the largest a posteriori probability. We illustrate the recognition technique on a database containing 2500 line patterns extracted from real-world imagery. Here the recognition technique is shown to significantly outperform a number of algorithm alternatives.

关键词： pattern matching

来源：评论

学校读者我要写书评

暂无评论

Rule generation from a rotation-invariant neural pattern recognition system

Rule generation from a rotation-invariant neural pattern rec...

引用

international conference on Neural Information Processing

作者： M. Fukumi K. Nakaura N. Akamatsu Department of Information Science and Intelligent Systems University of Tokushima Tokushima Japan SYSTEM LSI Limited Matsuyama Japan

A method of extracting rules from a rotation-invariant neural pattern recognition system formed using a genetic algorithm (GA) is presented. In particular, deterministic mutation (DM) is utilized to improve its convergence properties. It is performed on the basis of the result of neural network structure learning. DM can evolve chromosomes of individuals to increase their fitness functions in a deterministic manner. In this paper, coin data are used as inputs. the coins used are a Japanese 500-yen coin and a South Korean 500-won coin, which are very similar. GA is utilized to reduce the number of connection weights in the neural network. the network weights surviving after training represent rules to perform pattern classification for the coin data. the rules are then extracted from the network. Furthermore, the network has a procedure to substitute signum units for hidden sigmoid ones in examining its recognition accuracy. It enables us to easily extract rules. Simulation results show that this approach can generate a simple network structure and, as a result, simple rules for coin data classification.

关键词： pattern recognition Neural networks Data mining Delta modulation Genetic mutations Information science Intelligent systems Large scale integration Convergence pattern classification

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：