Rapid compound pattern classification by recursive partitioning of feature space. An application in flow cytometry

doi:10.1016/0167-8655(95)00016-A

Pattern Recognition Letters

Volume 16, Issue 7, July 1995, Pages 703-709

https://doi.org/10.1016/0167-8655(95)00016-A Get rights and content

Abstract

A method is described for rapidly classifying a set of points in real space. A set is mapped to a low-dimensional vector via a discriminating, recursive partition of feature space obtained pragmatically by the CART algorithm.

References (15)

S. Crawford
Extensions to the CART algorithm
Internat. J. Man-Machine Studies
(1989)
R. Allman et al.
Flow cytometric analysis of heterogeneous bacterial populations
L. Breiman et al.
Classification and Regression Trees
(1984)
W. Buntine
A Theory of Learning Classification Rules
J.H. Friedman et al.
An algorithm for finding best matches in logarithmic expected time
ACM Trans. Math. Software
(1977)
K.-S. Fu et al.
Statistical Pattern Classification Using Contextual Information
(1980)
I.J. Good et al.
Nonparametric roughness penalties for probability densities
Biometrika
(1971)

There are more references available in the full text version of this article.

Cited by (7)

Nearest neighbour group-based classification
2010, Pattern Recognition
Citation Excerpt :
Group-based classification is an example of the use of context to aid decision making [3] which has been found beneficial in such diverse fields as speech recognition, optical character recognition, document classification and remote sensing [1]. For example, the compound classification of collections of cells in flow cytometry, based around the classification and regression tree (CART) algorithm, is presented in [9]. However, in group-based classification we assume that the application domain allows us to utilise a priori knowledge that the whole group of unlabeled samples belong to the same, but unknown, class.
The purpose of group-based classification (GBC) is to determine the class label for a set of test samples, utilising the prior knowledge that the samples belong to same, but unknown class. This can be seen as a simplification of the well studied, but computationally complex, non-sequential compound classification problem. In this paper, we extend three variants of the nearest neighbour algorithm to develop a number of non-parametric group-based classification techniques. The performances of the proposed techniques are then evaluated on both synthetic and real-world data sets and their performance compared with techniques that label test samples individually. The results show that, while no one algorithm clearly outperforms all others on all data sets, the proposed group-based classification techniques have the potential to outperform the individual-based techniques, especially as the (group) size of the test set increases. In addition, it is shown that algorithms that pool information from the whole test set perform better than two-stage approaches that undertake a vote based on the class labels of individual test samples.
Concept Developments in Flow Cytometry
2008, Cellular Diagnostics: Basic principles, methods and clinical applications of flow cytometry
A morphological approach for feature space partitioning
2006, IEEE Geoscience and Remote Sensing Letters
Pattern recognition in flow cytometry
2001, Cytometry
Flow cytometry and cell sorting of heterogeneous microbial populations: The importance of single-cell analyses
1996, Microbiological Reviews
The application of flow cytometry to the estimation of bacterial antibiotic susceptibility
1995, Journal of Antimicrobial Chemotherapy

View all citing articles on Scopus

View full text

Rapid compound pattern classification by recursive partitioning of feature space. An application in flow cytometry

Abstract

Internat. J. Man-Machine Studies

Flow cytometric analysis of heterogeneous bacterial populations

Classification and Regression Trees

A Theory of Learning Classification Rules

An algorithm for finding best matches in logarithmic expected time

ACM Trans. Math. Software

Statistical Pattern Classification Using Contextual Information

Nonparametric roughness penalties for probability densities

Biometrika