Scattering computing of metal-media complex structure and structure with cavity has been one of the problems in electromagnetic (EM scattering theoretical calculation field for many years. A novel method, substituting...
详细信息
ISBN:
(纸本)9780769533056
Scattering computing of metal-media complex structure and structure with cavity has been one of the problems in electromagnetic (EM scattering theoretical calculation field for many years. A novel method, substituting datamining modeling for original theoretical modeling, is proposed creatively in this paper, attempting to solve the problem by machinelearningtheory. datamining modeling is to construct "EM scattering training model", applying regression analysis algorithm on measurement data, to achieve the effect superior to that theoretical modeling can have. Given an example of regressive estimation of some inlet backscattering RCS curve, both original least square algorithm and support vector regression are used, so an applicable datamining model. is established initially for EM scattering computing.
the integration of fuzzy sets and rough sets can lead to a hybrid soft-computing technique which has been applied successfully to many fields such as machinelearning, patternrecognition and image processing. the key...
详细信息
the integration of fuzzy sets and rough sets can lead to a hybrid soft-computing technique which has been applied successfully to many fields such as machinelearning, patternrecognition and image processing. the key to this soft-computing technique is how to set up and make use of the fuzzy attribute reduct in fuzzy rough set theory. Given a fuzzy information system, we may find many fuzzy attribute reducts and each of them can have different contributions to decision-making. If only one of the fuzzy attribute reducts, which may be the most important one, is selected to induce decision rules, some useful information hidden in the other reducts for the decision-making will be losing unavoidably. To sufficiently make use of the information provided by every individual fuzzy attribute reduct in a fuzzy information system, this paper presents a novel induction of multiple fuzzy decision trees based on rough set technique. the induction consists of three stages. First several fuzzy attribute reducts are found by a similarity based approach, and then a fuzzy decision tree for each fuzzy attribute reduct is generated according to the fuzzy ID3 algorithm. the fuzzy integral is finally considered as a fusion tool to integrate the generated decision trees, which combines together all outputs of the multiple fuzzy decision trees and forms the final decision result. An illustration is given to show the proposed fusion scheme. A numerical experiment on real data indicates that the proposed multiple tree induction is superior to the single tree induction based on the individual reduct or on the entire feature set for learning problems with many attributes. Crown Copyright (c) 2008 Published by Elsevier Inc. All rights reserved.
A model selection method based on tabu search is proposed to build support vector machines (binary decision functions) of reduced complexity and efficient generalization. the aim is to build a fast and efficient suppo...
详细信息
A model selection method based on tabu search is proposed to build support vector machines (binary decision functions) of reduced complexity and efficient generalization. the aim is to build a fast and efficient support vector machines classifier. A criterion is defined to evaluate the decision function quality which blends recognition rate and the complexity of a binary decision functions together. the selection of the simplification level by vector quantization, of a feature subset and of support vector machines hyperparameters are performed by tabu search method to optimize the defined decision function quality criterion in order to find a good sub-optimal model on tractable times.
In this paper, Associations algorithms and Support Vector machines (SVM) are applied to analyse years of solar catalogues data and to study the associations between eruptive filaments/prominences and Coronal Mass Ejec...
详细信息
Decision tree classification is a common method used in datamining. It has been used for predicting medical diagnoses. Among datamining methods for classification, decision trees have several advantages such as they...
详细信息
ISBN:
(纸本)9780769530994
Decision tree classification is a common method used in datamining. It has been used for predicting medical diagnoses. Among datamining methods for classification, decision trees have several advantages such as they are simple to understand and interpret, they are able to handle both numerical and categorical attributes. However, it is well-known that when Gini index is used or classification, the method biases multivalued attributes. In addition to having difficulty when the number of classes is large, the method also tends to favor tests that result in equalsized partitions and purity in all partitions. In this paper, we modify the Gini-based decision tree method. To overcome the known problems, we normalize the Gini indexes by taking into account information about the splitting status of all attributes. Instead of using the Gini index for attribute selection as usual, we use ratios of Gini indexes and their splitting values in order to reduce the biases. We report our experiments with several benchmark medical data bases. Comparisons between our method and other known classification algorithms are provided.
Classifier ensemble is now an active area of research in machinelearning and patternrecognition. Fuzzy classification is an important application of fuzzy set. In this paper, we propose a fuzzy classifier with kener...
详细信息
ISBN:
(纸本)9780769533056
Classifier ensemble is now an active area of research in machinelearning and patternrecognition. Fuzzy classification is an important application of fuzzy set. In this paper, we propose a fuzzy classifier with kenerl fuzzy C-means Clustering(KFCMC) algorithm. Based on such fuzzy classifier,the approaches of constructing fuzzy classifier ensemble system are introduced these approaches include individual fuzzy classifier generation, individual fuzzy classifier reliability compution, fuzzy classifier set selection, and classifiers ensemble etc. Our aim is building accurate and diverse classifiers. Experiment results show that our proposed approaches are effective.
A novel similarity measure based on spatial overlapping relation is proposed in this paper which calculates the similarity between a pair of data points by using the mutual overlapping relation between them in a multi...
详细信息
ISBN:
(纸本)9780769533056
A novel similarity measure based on spatial overlapping relation is proposed in this paper which calculates the similarity between a pair of data points by using the mutual overlapping relation between them in a multi-dimensional space. A spatial overlapping based hierarchical clustering method SOHC was also developed and implemented aimed to justify the effectiveness of the proposed similarity measure. SOHC works well both in low-dimensional and high-dimensional datasets, and is able to cluster arbitrary shape of clusters. Moreover, it can work for both numerical and categorical attributes in a uniform way. Experimental results carried out on some public datasets collected from the UCI machinelearning repository and predictive toxicology domain show that SOHC is a promising clustering method in datamining.
Representation of an object in image for machinelearning applications (recognition, retrieval, identification, etc.) has to be based on a previously chosen feature. Binary shape is a very popular and commendable one....
详细信息
ISBN:
(纸本)9783540698111
Representation of an object in image for machinelearning applications (recognition, retrieval, identification, etc.) has to be based on a previously chosen feature. Binary shape is a very popular and commendable one. It has many advantages and can be successfully used in many applications, especially in engineering. To achieve better characteristics, various shape transformations are used. Obviously, they should be robust to as many shape deformations as it is possible. In this paper results of exhaustive exploration of a new method are presented. this method is based on transformation from Cartesian to polar coordinates, but it overcomes few problems, that were not solved yet. Above all, the proposed transform is more robust to occlusion and noise, two the most challenging problems.
In this study, we critically analyse and compare performances of several global optimization (GO) approaches with our hybrid GLPτS method, which uses meta-heuristic rules and a local search in the final stage of find...
详细信息
ISBN:
(纸本)9781605580463
In this study, we critically analyse and compare performances of several global optimization (GO) approaches with our hybrid GLPτS method, which uses meta-heuristic rules and a local search in the final stage of finding a global solution. We also critically investigate a Stochastic Genetic Algorithm (StGA) method to demonstrate that there are some loopholes in its algorithm and assumptions. Subsequently, we employ the GLPτS method for neural network (NN) supervised learning, when using our intelligent system for solving real-world patternrecognition and classification problem. In the preprocessing data phase, our system also uses Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) for dimensionality reduction and minimization of the chosen number of features for the classification problem. Finally, the reported results are compared with Backpropagation (BP) to demonstrate the competitive properties and the efficiency of our system. Copyright 2008 ACM.
this paper presents a stagewise least square (SLS) loss function for classification. It uses a least square form within each stage to approximate a bounded monotonic nonconvex loss function in a stagewise manner. Seve...
详细信息
ISBN:
(纸本)9781605603179
this paper presents a stagewise least square (SLS) loss function for classification. It uses a least square form within each stage to approximate a bounded monotonic nonconvex loss function in a stagewise manner. Several benefits are obtained from using the SLS loss function, such as: (i) higher generalization accuracy and better scalability than classical least square loss;(ii) improved performance and robustness than convex loss (e.g., hinge loss of SVM);(iii) computational advantages compared with nonconvex loss (e.g. ramp loss in ψ-learning);(iv) ability to resist myopia of Empirical Risk Minimization and to boost the margin without boosting the complexity of the classifier. In addition, it naturally results in a kernel machine which is as sparse as SVM, yet much faster and simpler to train. A fast online learning algorithm with an integrated sparsification procedure is also provided. Experimental results on several benchmarks confirm the advantages of the proposed approach.
暂无评论