Auto-associative Multivariate Regression Trees for Cluster Analysis

Smyth, Christine; Coomans, Danny; Everingham, Yvette; Hancock, Tim

doi:10.1016/j.chemolab.2005.09.001

Cited by 13 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The clusters are found in the response space and the explanatory variables that form the tree are deemed to be important in determining the clusters. To allow multivariate regression trees to be applied in the traditional clustering framework where there are no response variables, AAMRTs were suggested [11,16]. AAMRTs replicate the explanatory variables as response variables and grow the tree using identical response and explanatory datasets.…”

Section: Auto-associative Multivariate Regression Treesmentioning

confidence: 99%

“…FOMs have been shown to provide an accurate estimate of the natural number of clusters [14,16]. FOMs assess the 'predictive power' of a clustering algorithm by leaving out a variable j, clustering the data (into k clusters), then calculating the root mean square error (RMSE) of j relative to the cluster means:…”

Section: Cluster Number Estimationmentioning

confidence: 99%

“…Nodes that are deemed sufficiently homogenous are 'terminal nodes'. It has been shown that by duplicating the explanatory variables as the response variables (referred to as an AAMRT), a regression tree can be grown on a dataset consisting of only explanatory variables, and the observational units in the terminal nodes can be regarded as the clusters of the dataset [11,16]. Obviously, each regression tree can give an individual co-occurrence matrix.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predictive weighting for cluster ensembles

Smyth

Coomans

2007

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

An ensemble of regression models predicts by taking a weighted average of the predictions made by individual models. Calculating the weights such that they reflect the accuracy of individual models (post processing the ensemble) has been shown to increase the ensemble's accuracy. However, post processing cluster ensembles has not received as much attention because of the inherent difficulty in assessing the accuracy of an individual cluster model. By enforcing the notion that clusters must be 'predictable', this paper suggests a means of implicitly post processing cluster ensembles by drawing analogies with regression post processing techniques. The product of the post processing procedure is an intelligently weighted co-occurrence matrix. A new technique, similarity-based k-means (SBK), is developed to split this matrix into clusters. The results using three real life datasets underpinned by chemical and biological phenomena show that splitting an intelligently weighted co-occurrence matrix gives accuracy that approaches supervised classification methods.

show abstract

Section: Auto-associative Multivariate Regression Treesmentioning

confidence: 99%

Section: Cluster Number Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predictive weighting for cluster ensembles

Smyth

Coomans

2007

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The clusters are found in the response space and the explanatory variables that form the tree are deemed to be important in determining the clusters. To allow multivariate regression trees to be applied in the traditional clustering framework where there are no response variables, auto-associative multivariate regression trees (AAMRTs) were suggested [4], [5]. AAMRTs replicate the explanatory variables as response variables and grow the tree using identical response and explanatory datasets.…”

Section: Yimentioning

confidence: 99%

“…Previous literature has shown that multivariate regression trees double effectively as a clustering technique [4], [5]. If clustering in a low dimensional setting, the explanatory variables are replicated as the response variables (autoassociative multivariate regression tree), and the clusters are found in the entire variable space.…”

Section: Introductionmentioning

confidence: 99%

Clustering Microarrays with Predictive Weighted Ensembles

Smyth

Coomans

2007

2007 IEEE Symposium on Computational Intelligence and Bioinformatics and Computational Biology

View full text Add to dashboard Cite

Cluster ensembles seek a consensus across many individual partitions and the resulting solution is usually stable. Cluster ensembles are well suited to the analysis of DNA microarrays, where the tremendous size of the dataset can thwart the discovery of stable groups.Post processing cluster ensembles, where each individual partition is weighted according to its relative accuracy improves the performance of the ensemble whilst maintaining its stability. However, weighted cluster ensembles remain relatively unexplored, primarily because there are no common means of assessing the accuracy of individual clustering solutions. This paper describes a technique of creating weighted cluster ensembles suitable for use with microarray datasets. A regression technique is used to obtain individual cluster solutions. Each solution is then weighted according to its predictive accuracy. The consensus partition is obtained using a novel modification to the traditional k-means algorithm which further enforces the predictability of the solution. An estimate of the natural number of clusters can also be obtained using the modified k-means algorithm. Furthermore, a valuable byproduct of this weighted ensemble approach is a variable importance list. The methodology is applied on two well-known microarray datasets with promising results.

show abstract

Warming of surface water in the large and shallow lakes across the Yangtze River Basin, China, and its driver analysis

Sun

Wang

et al. 2022

Environ Sci Pollut Res

View full text Add to dashboard Cite

Auto-associative Multivariate Regression Trees for Cluster Analysis

Cited by 13 publications

References 14 publications

Predictive weighting for cluster ensembles

Predictive weighting for cluster ensembles

Clustering Microarrays with Predictive Weighted Ensembles

Warming of surface water in the large and shallow lakes across the Yangtze River Basin, China, and its driver analysis

Contact Info

Product

Resources

About