The effect of unlabeled samples in reducing the small sample size problem and mitigating the Hughes phenomenon
- 1 January 1994
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 32 (5) , 1087-1095
- https://doi.org/10.1109/36.312897
Abstract
No abstract availableKeywords
This publication has 11 references indexed in Scilit:
- Using Partially Labeled Data For Normal Mixture Identification With Application To Class DefinitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Analyzing high-dimensional multispectral dataIEEE Transactions on Geoscience and Remote Sensing, 1993
- The airborne visible/infrared imaging spectrometer (AVIRIS)Remote Sensing of Environment, 1993
- Feature extraction based on decision boundariesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- MODIS: advanced facility instrument for studies of the Earth as a systemIEEE Transactions on Geoscience and Remote Sensing, 1989
- Mixture Densities, Maximum Likelihood and the EM AlgorithmSIAM Review, 1984
- Maximum Likelihood from Incomplete Data Via the EM AlgorithmJournal of the Royal Statistical Society Series B: Statistical Methodology, 1977
- Variance comparisons for unbiased estimators of probability of correct classification (Corresp.)IEEE Transactions on Information Theory, 1976
- Nonparametric Bayes error estimation using unclassified samplesIEEE Transactions on Information Theory, 1973
- On the mean accuracy of statistical pattern recognizersIEEE Transactions on Information Theory, 1968