Validating visual clusters in large datasets: fixed point clusters of spectral features.

DOI10.1016/S0167-9473(02)00077-4MaRDI QIDQ1852887zbMATH OpenWikidataFDO

Authors Norbert Christlieb, Christian Hennig

Publication date 21 January 2003

Published in Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL http://hdl.handle.net/20.500.11850/145993

zbMATH Keywords

Classification plotsContamination modelData visualizationDiscriminant coordinatesOutliersSky surveysStellar populations

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Pattern recognition, speech recognition (68T10) Computing methodologies and applications (68U99)

Review text

Finding clusters in large datasets is a difficult task. Almost all computationally feasible methods are related to \(k\)-means and need a clear partition structure of the data, while most such datasets contain masking outliers and other deviations from the usual models of partitioning cluster analysis. It is possible to look for clusters informally using graphic tools like the grand tour, but the meaning and the validity of such patterns is unclear. In this paper, a three-step-approach is suggested: In the first step, data visualization methods like the grand tour are used to find cluster candidate subsets of the data. In the second step, reproducible clusters are generated from them by means of fixed point clustering, a method to find a single cluster at a time based on the Mahalanobis distance. In the third step, the validity of the clusters is assessed by the use of classification plots. The approach is applied to an astronomical dataset of spectra from the Hamburg/ESO survey.

Recommendations

• Clustering large number of extragalactic spectra of galaxies and quasars through canopies
• Scalable visual assessment of cluster tendency for large data sets
• scientific article; zbMATH DE number 1792110
• Some computational issues in cluster analysis with no a priori metric
• Fast cluster tendency assessment for big, high-dimensional data

Cites work

• A procedure for the detection of multivariate outliers.
• Clustering and outlier identification: fixed point cluster analysis.
• Finding Groups in Data
• Finite mixture models
• How Many Clusters? Which Clustering Method? Answers Via Model-Based Cluster Analysis
• scientific article; zbMATH DE number 47593 (Why is no real title available?)
• scientific article; zbMATH DE number 3626442 (Why is no real title available?)
• scientific article; zbMATH DE number 3074541 (Why is no real title available?)
• The Grand Tour: A Tool for Viewing Multidimensional Data
• The Masking Breakdown Point of Multivariate Outlier Identification Rules
• Trimmed \(k\)-means: An attempt to robustify quantizers
• Visual clustering and classification: The Oronsay particle size dataset revisited
• What clusters are generated by normal mixtures?

Cited in

(11)

• The importance of the scales in heterogeneous robust clustering
• Clusters, outliers, and regression: Fixed point clusters
• Scalable visual assessment of cluster tendency for large data sets
• Clustering large number of extragalactic spectra of galaxies and quasars through canopies
• Robust linear clustering
• Visual cluster validity for prototype generator clustering models
• Exploring the number of groups in robust model-based clustering
• A fresh look at mean-shift based modal clustering
• Matrix reduction by cross-multiplication as alternative method of matrix inversion and solving systems of linear equations
• Distance-based parametric bootstrap tests for clustering of species ranges
• Experiments with, and on, algorithms for maximum likelihood clustering

Describes a project that uses

Uses Software

• XGobi
• clusfind

This page was built for publication: Validating visual clusters in large datasets: fixed point clusters of spectral features.

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1852887)