An adaptive optimal ensemble classifier via bagging and rank aggregation with applications to high dimensional data
Open Access
- 18 August 2010
- journal article
- Published by Springer Science and Business Media LLC in BMC Bioinformatics
- Vol. 11 (1), 427
- https://doi.org/10.1186/1471-2105-11-427
Abstract
Generally speaking, different classifiers tend to work well for certain types of data and conversely, it is usually not known a priori which algorithm will be optimal in any given classification application. In addition, for most classification problems, selecting the best performing classification algorithm amongst a number of competing algorithms is a difficult task for various reasons. As for example, the order of performance may depend on the performance measure employed for such a comparison. In this work, we present a novel adaptive ensemble classifier constructed by combining bagging and rank aggregation that is capable of adaptively changing its performance depending on the type of data that is being classified. The attractive feature of the proposed classifier is its multi-objective nature where the classification results can be simultaneously optimized with respect to several performance measures, for example, accuracy, sensitivity and specificity. We also show that our somewhat complex strategy has better predictive performance as judged on test samples than a more naive approach that attempts to directly identify the optimal classifier based on the training data performances of the individual classifiers. We illustrate the proposed method with two simulated and two real-data examples. In all cases, the ensemble classifier performs at the level of the best individual classifier comprising the ensemble or better. For complex high-dimensional datasets resulting from present day high-throughput experiments, it may be wise to consider a number of classification algorithms combined with dimension reduction techniques rather than a fixed standard algorithm set a priori.Keywords
This publication has 26 references indexed in Scilit:
- Gene expression profiling of peripheral blood cells for early detection of breast cancerBreast Cancer Research, 2010
- RankAggreg, an R package for weighted rank aggregationBMC Bioinformatics, 2009
- Breast Cancer Diagnosis from Proteomic Mass Spectrometry Data: A Comparative EvaluationStatistical Applications in Genetics and Molecular Biology, 2008
- Classification of Breast Cancer versus Normal Samples from Mass Spectrometry Profiles Using Linear Discriminant Analysis of Important Features Selected by Random ForestStatistical Applications in Genetics and Molecular Biology, 2008
- Weighted rank aggregation of cluster validation measures: a Monte Carlo cross-entropy approachBioinformatics, 2007
- Reproducibility of SELDI-TOF protein patterns in serum: comparing datasets from different experimentsBioinformatics, 2004
- Adaptive Regression by MixingJournal of the American Statistical Association, 2001
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997
- A Coefficient of Agreement for Nominal ScalesEducational and Psychological Measurement, 1960
- VERIFICATION OF FORECASTS EXPRESSED IN TERMS OF PROBABILITYMonthly Weather Review, 1950