Kernel Parameter Optimization in Stretched Kernel-Based Fuzzy Clustering

2013 ◽  
pp. 49-57 ◽  
Author(s):  
Chunhong Lu ◽  
Zhaomin Zhu ◽  
Xiaofeng Gu
Keyword(s):  
Parameter Optimization ◽  
Fuzzy Clustering ◽  
Kernel Parameter

scholarly journals Fault diagnosis of bearing based on relevance vector machine classifier with improved binary bat algorithm for feature selection and parameter optimization

2017 ◽  
Vol 9 (1) ◽  
pp. 168781401668529 ◽  
Author(s):  
Sheng-wei Fei
Keyword(s):  
Feature Selection ◽  
Fault Diagnosis ◽  
Parameter Optimization ◽  
Bat Algorithm ◽  
Relevance Vector Machine ◽  
Experimental Results ◽  
Machine Method ◽  
Training Samples ◽  
Kernel Parameter

In this article, fault diagnosis of bearing based on relevance vector machine classifier with improved binary bat algorithm is proposed, and the improved binary bat algorithm is used to select the appropriate features and kernel parameter of relevance vector machine. In the improved binary bat algorithm, the new velocities updating method of the bats is presented in order to ensure the decreasing of the probabilities of changing their position vectors’ elements when the position vectors’ elements of the bats are equal to the current best location’s element, and the increasing of the probabilities of changing their position vectors’ elements when the position vectors’ elements of the bats are unequal to the current best location’s element, which are helpful to strengthen the optimization ability of binary bat algorithm. The traditional relevance vector machine trained by the training samples with the unreduced features can be used to compare with the proposed improved binary bat algorithm–relevance vector machine method. The experimental results indicate that improved binary bat algorithm–relevance vector machine has a stronger fault diagnosis ability of bearing than the traditional relevance vector machine trained by the training samples with the unreduced features, and fault diagnosis of bearing based on improved binary bat algorithm–relevance vector machine is feasible.

Parameter Optimization of SVM Based on Maximum Variance – Entropy Criterion

2013 ◽  
Vol 373-375 ◽  
pp. 1053-1059
Author(s):  
Jian Liao ◽  
Shao Lei Zhou ◽  
Xian Jun Shi
Keyword(s):  
Parameter Optimization ◽  
Feature Space ◽  
Pso Algorithm ◽  
Parameter Selection ◽  
Support Vector ◽  
Svm Classifier ◽  
Maximum Variance ◽  
Kernel Parameter ◽  
Biquadratic Filter ◽  
Entropy Criterion

Kernel parameter selection of support vector machine (SVM) is difficult in practical application. A parameter selection algorithm of SVM was proposed based on data maximum variance - entropy criterion by analyzing the principle of SVM classifier. The algorithm uses data maximum variance - entropy criterion to measure the linear separability of dataset in the feature space, and combines with particle swarm optimization (PSO) algorithm for parameter optimization. The experiment results on datasets from UCI show that the algorithm is excellence in accuracy and improves the training performance of SVM. To further verify the effectiveness of the algorithm, applying the method in fault diagnosis of biquadratic filter circuit, results prove it improves the diagnostic accuracy.

scholarly journals Kernel Parameter Optimization for Kriging Based on Structural Risk Minimization Principle

2017 ◽  
Vol 2017 ◽  
pp. 1-9 ◽  
Author(s):  
Hua Su ◽  
Chunlin Gong ◽  
Liangxian Gu
Keyword(s):  
Parameter Optimization ◽  
Surrogate Model ◽  
Optimization Method ◽  
Nonuniform Distribution ◽  
Risk Minimization ◽  
Structural Risk Minimization ◽  
Kriging Surrogate Model ◽  
Generalization Ability ◽  
Kernel Parameter ◽  
Structural Risk

An improved kernel parameter optimization method based on Structural Risk Minimization (SRM) principle is proposed to enhance the generalization ability of traditional Kriging surrogate model. This article first analyses the importance of the generalization ability as an assessment criteria of surrogate model from the perspective of statistics and proves the applicability to Kriging. Kernel parameter optimization method is used to improve the fitting precision of Kriging model. With the smoothness measure of the generalization ability and the anisotropy kernel function, the modified Kriging surrogate model and its analysis process are established. Several benchmarks are tested to verify the effectiveness of the modified method under two different sampling states: uniform distribution and nonuniform distribution. The results show that the proposed Kriging has better generalization ability and adaptability, especially for nonuniform distribution sampling.

Sign in / Sign up

Export Citation Format

Share Document