检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： R.A. Dara M. Kamel Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Waterloo ONT Canada

The need for the design of complex and incremental training algorithms in multiple neural network systems has motivated us to study combining methods from the cooperation perspective. One way of achieving effective cooperation is through sharing resources such as information and components. The degree and method by which multiple classifier systems share training resources can be a measure of cooperation. Despite the growing number of interests in data modification techniques, such as bagging and k-fold cross-validation, there is no guidance for whether sharing or not sharing training patterns results in higher accuracy and under what conditions. We implemented several partitioning techniques and examined the effect of sharing training patterns by varying the size of overlap between 0-100% of the size of training subsets. Under most conditions studied, multinet systems showed improvement over the presence of larger overlap subsets.

关键词： Intelligent networks Neural networks Bagging Boosting Diversity reception pattern analysis machine intelligence Laboratories Algorithm design and analysis Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

An information-theoretic measure to evaluate data partitions in multiple classifiers

An information-theoretic measure to evaluate data partitions...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： R.A. Dara M. Makrehchi M. Kamel Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Waterloo ONT Canada

Data partitioning, such as bagging and boosting, has been extensively used in the construction of multiple classifier systems. One objective of data partitioning is to achieve uncorrelated classifiers. Most existing techniques achieve diversity through random partitioning, and they do not take advantage of the information within data patterns before training. In this work, combining techniques are studied and categorized from a new perspective. In addition, we introduce two new measures, total diversity index and imbalance, with which multiple classifiers can be compared. Several simulations and comparative studies have been carried out on a common benchmark data set and results are presented

关键词： Diversity reception Bagging machine intelligence Laboratories Information theory Design methodology pattern recognition Focusing Text categorization Image recognition

来源：评论

学校读者我要写书评

暂无评论

Effect of sharing training patterns on the performance of classifier ensemble

Effect of sharing training patterns on the performance of cl...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： R.A. Dara M. Kamel Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Waterloo ONT Canada

The availability of large and complex data sets has shifted the focus of pattern recognition toward developing techniques that can efficiently handle these types of data sets. Multiple classifier systems have the promise of reducing the error and complexity by partitioning the data space and combining classifier predictions. However, difficulties arise in ways of generating these various partitions and using them effectively. In this paper, several methods of partitioning is studied and compared, by examining implicit and explicit sharing of the training patterns among multiple classifiers. We implemented several partitioning techniques using random and a more intelligent approach, clustering, to obtain more insight into the effect of shared and disjoint data representation across the training subsets. Improved classification accuracy suggests that implicit sharing of training patterns is always beneficial, while explicit sharing is useful for small size training data.

关键词： Training data Boosting Diversity reception Voting pattern analysis machine intelligence Laboratories Availability pattern recognition Diversity methods

来源：评论

学校读者我要写书评

暂无评论

A reinforcement learning framework for parameter control in computer vision applications

A reinforcement learning framework for parameter control in ...

引用

Canadian Conference on Computer and Robot Vision, CRV

作者： G.W. Taylor Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Waterloo ONT Canada

We propose a framework for solving the parameter selection problem for computer vision applications using reinforcement learning agents. Connectionist-based function approximation is employed to reduce the state space. Automatic determination of fuzzy membership functions is stated as a specific case of the parameter selection problem. Entropy of a fuzzy event is used as a reinforcement. We have carried out experiments to generate brightness membership functions for several images. The results show that the reinforcement learning approach is superior to an existing simulated annealing-based approach.

关键词： Learning Computer vision Application software State-space methods Simulated annealing Filters pattern analysis machine intelligence Laboratories Function approximation

来源：评论

学校读者我要写书评

暂无评论

Comparing viewpoint evaluation functions for model-based inspectional coverage

Comparing viewpoint evaluation functions for model-based ins...

引用

Canadian Conference on Computer and Robot Vision, CRV

作者： C. Wong M. Kamel Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Waterloo ONT Canada

Though based on rigorously developed ideas from imaging geometry, viewpoint evaluation in the active area of camera placement planning research still relies on the intuition and creativity of researchers for the formulation of objective measures. In this paper, a comparative study of five different viewpoint evaluation functions is presented. All five functions are based on a similar set of imaging requirements and considerations but each is unique in its formulation, and in some cases, in its objective. Functional behaviour and performance for the vision task of model-based inspectional coverage are studied quantitatively and qualitatively.

关键词： Inspection Cameras machine vision Layout Image analysis Sensor systems Surveillance Solid modeling pattern analysis machine intelligence

来源：评论

学校读者我要写书评

暂无评论

Shape retrieval using concavity trees

Shape retrieval using concavity trees

引用

International Conference on pattern Recognition

作者： O. El Badawy M. Kamel Pattern Analysis and Machine Intelligence Laboratory Systems Design Engineering University of Waterloo Waterloo ONT Canada

Concavity trees are well-known abstract structures. This paper proposes a new shape-based image retrieval method based on concavity trees. The proposed method has two main components. The first is an efficient (in terms of space and time) contour-based concavity tree extraction algorithm. The second component is a recursive concavity-tree matching algorithm that returns a distance between two trees. We demonstrate that concavity trees are able to boost the retrieval performance of two feature sets by at least 15% when tested on a database of 625 silhouette images.

关键词： Shape Image retrieval Information retrieval Testing Image databases pattern recognition pattern analysis machine intelligence Laboratories System analysis and design

来源：评论

学校读者我要写书评

暂无评论

Competitive coding scheme for palmprint verification

Competitive coding scheme for palmprint verification

引用

International Conference on pattern Recognition

作者： A.W.-K. Kong D. Zhang Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Waterloo ONT Canada Biometrics Research Center Department of Computing Hong Kong Polytechnic University Kowloon Hong Kong China

There is increasing interest in the development of reliable, rapid and non-intrusive security control systems. Among the many approaches, biometrics such as palmprints provide highly effective automatic mechanisms for use in personal identification. This paper presents a new method for extracting features from palmprints using the competitive coding scheme and angular matching. The competitive coding scheme uses multiple 2-D Gabor filters to extract orientation information from palm lines. This information is then stored in a feature vector called the competitive code. The angular matching with an effective implementation is then defined for comparing the proposed codes, which can make over 9,000 comparisons within 1s. In our testing database of 7,752 palmprint samples from 386 palms, we can achieve a high genuine acceptance rate of 98.4% and a low false acceptance rate of 3/spl times/10/sup -6/%. The execution time for the whole process of verification, including preprocessing, feature extraction and final matching, is 1s.

关键词： Biometrics Feature extraction Gabor filters Security Automatic control Control systems Data mining Iris Fingerprint recognition Humans

来源：评论

学校读者我要写书评

暂无评论

A Reinfrocement Learning Approach to Online Learning in Control

A Reinfrocement Learning Approach to Online Learning in Cont...

引用

International Conference on Control and Automation (ICCA)

作者： A.M. Tehrani M.S. Kamel Systems Design Engineering Department Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Waterloo ONT Canada

In search for a reinforcement learning technique with the simplicity of tabular techniques and capability of dealing with continuous states like in fuzzy systems, we introduce a new approach, which we have called Adaptive Pseudo Fuzzy technique. The idea is to partition the state space with some window functions similar to fuzzy membership functions and learn the output values by changing the rules’ consequents directly. This is a kind of local function approximation similar to RBFs and CMACs, however, unlike RBFs it does not shift the basis, and unlike CMACs it does not go through complex coarse coding. This method represents the input as a fuzzy system and learns the output as a look-up-table. We employed this technique in Sarsa(λ) to build a general online controller and examined it for a pole-balancing problem.

关键词： Fuzzy systems Learning State-space methods Function approximation

来源：评论

学校读者我要写书评

暂无评论

Optimization of a Neural Dynamics Based Controller for a Nonholonomic Mobile Robot Using Genetic Algorithms

Optimization of a Neural Dynamics Based Controller for a Non...

引用

International Conference on Control and Automation (ICCA)

作者： Hao Li S.X. Yang F. Karray Pattern Analysis and Machine Intelligence (PAMI) Lab Systems Design Engineering University of Waterloo Waterloo ONT Canada Advanced Robotics and Intelligent Systems (ARIS) Laboratory School of Engineering University of Guelph Guelph ONT Canada

In this paper, a neural dynamics based controller for a nonholonomic mobile robot is proposed. The turn angle of the robot in the proposed model is characterized by a biologically inspired shunting equation derived from Hodgkin and Huxley’s membrane equation. This model is capable of generating smooth steering velocity command that drives the robot to track desired paths. Some parameters in the proposed neural dynamics based controller need to be selected. A genetic algorithm is designed to optimize the model parameters that can guarantee the convergence of tracking error of the mobile robot. Simulation studies of a fourdegree-of-freedom mobile robot are conducted, which demonstrate the effectiveness of the proposed motion controller.

关键词： Mobile robots Genetic algorithms Biological system modeling Equations Biomembranes Algorithm design and analysis Design optimization Convergence Motion control

来源：评论

学校读者我要写书评

暂无评论

Shape-based image retrieval applied to trademark images

引用

International Journal of Image and Graphics 2002年第3期2卷 375-393页

作者： El Badawy, Ossama Kamel, Mohamed Pattern Analysis and Machine Intelligence Laboratory Department of Systems Design Engineering University of Waterloo 200 University Avenue West WaterlooONN2L 3G1 Canada

We propose a new shape-based, query-by-example, image database retrieval method that is able to match a query image to one of the images in the database, based on a whole or partial match. The proposed method has two key components: the architecture of the retrieval and the features used. Both play a role in the overall retrieval efficacy. The proposed architecture is based on the analysis of connected components and holes in the query and database images. The features we propose to use are geometric in nature, and are invariant to translation, rotation and scale. Each of the suggested three features is not new per se, but combining them to produce a compact and efficient feature vector is. We use hand-sketched, rotated and scaled query images to test the proposed method using a database of 500 logo images. We compare the performance of the suggested features with the performance of the moment invariants (a set of commonly-used shape features). The suggested features match the moment invariants in rotated and scaled queries and consistently surpass them in hand-sketched queries. Moreover, results clearly show that the proposed architecture significantly increases the performance of the two feature sets. © 2002 World Scientific Publishing Company.

关键词： Database systems

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：