检索结果-内蒙古大学图书馆

14th International Conference on Digital Signal processing (DSP 2002)

作者： Castanié, F Roviras, D TeSA ENSEEIHT F-31071 Toulouse France

ISBN: (纸本)0780375033

neural networks (NN) are now widely used and renown to solve recognition and classification problems. The present paper aims at showing how their learning capability can be applied to adaptive signal processing problems, either in replacement of conventional adaptive methods or to cope with most difficult cases raised by mobile space communication: non linear and/or non stationary problems. A brief overview of NN is given in the first section, highlighting their key features approximation capability, learning characteristic, etc.. The following sections focus on 3 majors applications to Space Communications: system and channel identification, equalization, and predistortion. The conclusion reached in this paper is that NN has no counterpart able to yield general solutions to these classes of problems with a single tool.

关键词： Signal processing

来源：评论

学校读者我要写书评

暂无评论

Adaptive filters and multichannel signal processing

Adaptive filters and multichannel signal processing

引用

Symposium on Adaptive Systems for Signal processing, Communications, and Control (AS-SPCC)

作者： Venetsanopoulos, AN Plataniotis, KN Univ Toronto Dept ECE Toronto ON M5S 3G4 Canada

ISBN: (纸本)0780358007

processing multichannel signals using digital signal processing techniques has received increased attention lately due to its importance in applications, such as multimedia technologies and telecommunications. The perspective of the topic offered here is one that comes primarily from work done in the field of multichannel image processing. The adaptive filtering techniques discussed in the paper relate to image processing with the emphasis placed primarily on filtering algorithms based on fuzzy logic concepts, multidimensional scaling, and order statistics-based designs. The strong potential of adaptive filters for multichannel image processing is illustrated with several examples.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

Novelty detection using extreme value statistics

引用

iee PROCEEDINGS-VISION image AND SIGNAL processing 1999年第3期146卷 124-129页

作者： Roberts, SJ Univ London Imperial Coll Sci Technol & Med Dept Elect & Elect Engn London SW7 2BT England

Extreme value theory is a branch of statistics that concerns the distribution of data of unusually low or high value, i.e. in the tails of some distribution. These extremal points are important in many applications as they represent the outlying regions of normal events against which we may wish to define abnormal events. In the context of density modelling, novelty detection or radial-basis function systems, points that lie outside of the range of expected extreme values may be flagged as outliers. There has been interest in the area of novelty detection, but decisions as to whether a point is an outlier or not tend to be made on the basis of exceeding some (heuristic) threshold. It is shown that a more principled approach may be taken using extreme value statistics.

关键词： Bioelectric signals outliers Signal detection statistical analysis signal detection Biology and medical computing medical data threshold epileptic seizure events Patient diagnostic methods and instrumentation electrical activity Electrical activity in neurophysiological processes electroencephalogram extreme value theory EEG noise removal outlying regions Electrodiagnostics and other electrical measurement techniques noise Computer vision and image processing techniques Probability theory, stochastic processes, and statistics density modelling Signal processing theory data distribution radial-basis function systems neural computing techniques novelty detection image processing abnormal events Other topics in statistics hand tremor radial basis function networks brain extreme value statistics medical image processing normal events auto-regressive model coefficients electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Towards the use of problem knowledge in training neural networks for image processing tasks

Towards the use of problem knowledge in training neural netw...

引用

Proceedings of the 1999 7th International Conference on image processing and its applications

作者： Chaplin, R.I. Hodgson, R.M. Gunetileke, S. Massey Univ Palmerston North New Zealand

The application of task-specific knowledge to initialize the network weights prior to training is studied. Supervised neural network training is a high dimensional optimization problem and the initial conditions of the search are critical to the quality of the solutions and the speed of the convergence to the solution. Rule insertion into fuzzy neural networks can reduce the training time and lead to better solutions.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Functional neural network prototype for multidimensional data analysis

Functional neural network prototype for multidimensional dat...

引用

Proceedings of the 1999 7th International Conference on image processing and its applications

作者： Sirlantzis, K. Howells, G. Paschalakis, S. Univ of Kent at Canterbury Kent United Kingdom

Artificial neural networks present a powerful tool to analyze complex systems. They have been long used to tackle the difficulties of image analysis and interpretation with applications ranging from character recognition to colour image processing. This paper presents a novel approach which exploits the generality of expressions available in the area of Constructive Type Theory and its potential for the production of guaranteed bug free, probably correct software to develop a working neural Network Prototype. To illustrate the possible applications of our work we will present results from two examples arising from our co-operation with the Dover Harbour Board.

关键词： image analysis

来源：评论

学校读者我要写书评

暂无评论

applications of cellular neural networks (CNN) to grey scale image filtering

Applications of cellular neural networks (CNN) to grey scale...

引用

Proceedings of the 1999 the 9th International Conference on 'Artificial neural networks (ICANN99)'

作者： Moran, Miauel A.Jaramillo Munoz, J.Alvaro Fernandez Universidad de Extremadura Badajoz Spain

ISBN: (纸本)0852967217

In the present work an adaptation of the Cellular neural Network (CNN) model to grey scale image processing is proposed. This task is performed programming the network to work as a classical spatial filter, taking advantage of the neural Network structure in order to improve the filtering effects. This enhancement is carried out by the inclusion of the feedback of the state variables and the adaptation of the input bias of every neuron based on the brightness of the image. A proper choice of the gain of the output function may also improve some of the network capabilities.

关键词： Cellular neural networks

来源：评论

学校读者我要写书评

暂无评论

Fetal echocardiographic image segmentation using neural networks

Fetal echocardiographic image segmentation using neural netw...

引用

Proceedings of the 1999 7th International Conference on image processing and its applications

作者： Piccoli, L. Dahmer, A. Scharcanski, J. Navaux, P.O.A. Brazil

This paper discusses supervised and unsupervised neural networks approaches to fetal echocardiographic image segmentation. The obtained results were compared with images segmented by a known unsupervised clustering technique (i.e. k-means). The visual aspect of the segmented images was evaluated with respect to its visual quality by an expert. A subset of the segmented images showed sufficient details of the internal heart anatomy to allow medical diagnosis. The visual observation was matched closely by our unsupervised image segmentation approach, using the modified Hubert index.

关键词： Diagnostic radiography

来源：评论

学校读者我要写书评

暂无评论

New method for invariant hand-written digit recognition using neural networks

New method for invariant hand-written digit recognition usin...

引用

Proceedings of the 1999 7th International Conference on image processing and its applications

作者： Chaker, F. Braham, R. Ghorbel, F. Ecole Nationale des Sciences de l'Informatique Tunisia

neural networks were used to solve invariant pattern classification problems. The first one consists of a pure neural solution. The neural network learns by itself the pre-processing required and extracts local information. The second one consists of extracting invariant features by using analytical methods. A solution based on the second approach where two types of features are used in the step of information extraction is proposed. These features are fed to a neural network which is used for partitioning the space in regions corresponding to classes and consequently for realizing the classification step in a pattern recognition system independent of certain geometric transformations of the space.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

neural network based automatic target processing and recognition

Neural network based automatic target processing and recogni...

引用

Proceedings of the 1999 7th International Conference on image processing and its applications

作者： Vasconcelos, G.C. Adeodato, P.J.L. Carvalho Filho, E.C.B. de A. Sodre, E. Cavalcanti, G.D. Federal Univ of Pernambuco Brazil

A set of solutions are described with respect to the pre-processing, automatic acquisition, manipulation and interpretation of radar images based on advanced neural networks, pattern recognition and other computational intelligence techniques. The solutions have demonstrated the benefits of applying input dimension reduction techniques, Kahunen-Loeve transforms (PCA) and Walsh-Hadamard transforms (WH-PCS) methods on radar image recognition systems. Recognition results were considered satisfactory for the data sets tested.

关键词： Radar target recognition

来源：评论

学校读者我要写书评

暂无评论

Hybrid neural network for the identification of narcotics and explosives

Hybrid neural network for the identification of narcotics an...

引用

Proceedings of the 1999 7th International Conference on image processing and its applications

作者： Rughooputh, H.C.S. Rughooputh, S.D.D.V. Univ of Mauritius Mauritius

Raman spectroscopy proves to be a versatile technique for forensic tasks. Whilst it is very easy and fast to record a spectrum, it may be very time-consuming for the non-experts (and even the experts) to identify chemicals from the large database of Raman spectra of these materials. Parallel developments in the field of neural networks have come to a stage that they can participate well in the recognition of these materials. In this paper, a novel neural network-based technique is developed and presented for the quick identification of chemical compounds, in particular narcotics and explosives. Preliminary results suggest this hybrid network has a great potential for forensic applications and for recognition of materials, in general.

关键词： Object recognition

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：