Scaling the kernel function based on the separating boundary in input space: a data-dependent way for improving the performance of kernel methods

DOI10.1016/J.INS.2011.08.028MaRDI QIDQ425515zbMATH OpenOpenAlexFDO

Authors Jiancheng Sun, Xiaohe Li, Jianguo Luo, Yaohui Bai, Yong Yang

Publication date 8 June 2012

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ins.2011.08.028

zbMATH Keywords

classificationkernel methodsRiemannian geometryconformal transformation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Advances in Neural Networks – ISNN 2005
• Learning the kernel matrix by maximizing a KFD-based class separability criterion
• Kernel Parameter Selection for Support Vector Machine Classification
• Conformal transformation of kernel functions: A data-dependent way to improve support vector machine classifiers
• Research on selection method of kernel function

Cites work

• scientific article; zbMATH DE number 1391397 (Why is no real title available?)
• Choosing multiple parameters for support vector machines
• Choosing the kernel parameters for support vector machines by the inter-cluster distance in the feature space
• Conformal transformation of kernel functions: A data-dependent way to improve support vector machine classifiers
• Induction of multiple fuzzy decision trees based on rough set technique
• Introduction to algorithms
• Learning the kernel matrix by maximizing a KFD-based class separability criterion
• Neighborhood Property–Based Pattern Selection for Support Vector Machines
• Structured large margin machines: sensitive to data distributions

Cited in

(6)

• Modeling and monitoring for handling nonlinear dynamic processes
• A high-order norm-product regularized multiple kernel learning framework for kernel optimization
• Advances in Neural Networks – ISNN 2005
• Modeling and monitoring of multimode transition process based on reconstruction
• Fault detection and diagnosis of non-linear non-Gaussian dynamic processes using kernel dynamic independent component analysis
• Structural multiple empirical kernel learning

Describes a project that uses

Uses Software

• UCI

This page was built for publication: Scaling the kernel function based on the separating boundary in input space: a data-dependent way for improving the performance of kernel methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q425515)