Dimension estimation using weighted correlation dimension method

DOI10.1155/2015/837185MaRDI QIDQ1723541zbMATH OpenOpenAlexWikidataFDO

Authors Yuanhong Liu, Zhiwei Yu, Ming Zeng, Shun Wang

Publication date 19 February 2019

Published in Discrete Dynamics in Nature and Society (Search for Journal in Brave)

Copyright license Creative Commons Attribution 3.0 Unported

Full work available at URL https://doi.org/10.1155/2015/837185

Mathematics Subject Classification ID

Measures of association (correlation, canonical correlation, etc.) (62H20) Factor analysis and principal components; correspondence analysis (62H25)

Review text

Summary: Dimension reduction is an important tool for feature extraction and has been widely used in many fields including image processing, discrete-time systems, and fault diagnosis. As a key parameter of the dimension reduction, intrinsic dimension represents the smallest number of variables which is used to describe a complete dataset. Among all the dimension estimation methods, correlation dimension (CD) method is one of the most popular ones, which always assumes that the effect of every point on the intrinsic dimension estimation is identical. However, it is different when the distribution of a dataset is nonuniform. Intrinsic dimension estimated by the high density area is more reliable than the ones estimated by the low density or boundary area. In this paper, a novel weighted correlation dimension (WCD) approach is proposed. The vertex degree of an undirected graph is invoked to measure the contribution of each point to the intrinsic dimension estimation. In order to improve the adaptability of WCD estimation, \(k\)-means clustering algorithm is adopted to adaptively select the linear portion of the log-log sequence \((\log \delta_k, \log C(n, \delta_k))\). Various factors that affect the performance of WCD are studied. Experiments on synthetic and real datasets show the validity and the advantages of the development of technique.

Recommendations

• Intrinsic dimension estimation of manifolds by incising balls
• Intrinsic dimension estimation: advances and open problems
• Novel high intrinsic dimensionality estimators
• Intrinsic dimension estimation: relevant techniques and a benchmark framework
• Intrinsic dimension estimation based on local adjacency information

Cites work

• An axiomatic approach to intrinsic dimension of a dataset
• Box-counting dimensions of fractal interpolation surfaces derived from fractal interpolation functions
• Data dimensionality estimation methods: A survey.
• Eigenvector weighting function in face recognition
• Finite correlation dimension for stochastic systems with power-law spectra
• Hausdorff Dimension, Its Properties, and Its Surprises
• Linear control of fractional-order financial chaotic systems with input saturation
• Locally linear discriminate embedding for face recognition
• Measuring the strangeness of strange attractors
• On Local Intrinsic Dimension Estimation and Its Applications
• Robust PLS approach for KPI-related prediction and diagnosis against outliers and missing data

Cited in

(3)

• Application of rotational spectrum for correlation dimension estimation
• Intrinsic dimension estimation based on local adjacency information
• Recognition of the scale-free interval for calculating the correlation dimension using machine learning from chaotic time series

This page was built for publication: Dimension estimation using weighted correlation dimension method

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1723541)