Exploring issues of training data imbalance and mislabelling on random forest performance for large area land cover classification using the ensemble margin
Authors:
- Andrew MellorAMAndrew Mellor
- Samia BoukirSBSamia Boukir
- Andrew HaywoodAHAndrew Haywood
- Simon JonesSJSimon Jones
Top Cited Papers
- 1 July 2015
- journal article
- research article
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 105, 155-168
Abstract
No abstract availableKeywords
This publication has 38 references indexed in Scilit:
- The Performance of Random Forests in an Operational Setting for Large Area Sclerophyll Forest ClassificationRemote Sensing, 2013
- An Operational Scheme for Deriving Standardised Surface Reflectance from Landsat TM/ETM+ and SPOT HRG Imagery for Eastern AustraliaRemote Sensing, 2013
- Evaluating effectiveness of down-sampling for stratified designs and unbalanced prevalence in Random Forest models of tree species distributions in NevadaEcological Modelling, 2012
- Satellite image-based maps: Scientific inference or pretty pictures?Remote Sensing of Environment, 2011
- Incorporating Spatial Variability Measures in Land-cover Classification using Random ForestProcedia Environmental Sciences, 2011
- Retrieving forest structure variables based on image texture analysis and IKONOS-2 imageryRemote Sensing of Environment, 2006
- A Multiple Resampling Method for Learning from Imbalanced Data SetsComputational Intelligence, 2004
- The significance of border training patterns in classification by a feedforward neural network using back propagation learningInternational Journal of Remote Sensing, 1999
- Optical remote-sensing techniques for the assessment of forest inventory and biophysical parametersProgress in Physical Geography: Earth and Environment, 1998
- Boosting the margin: a new explanation for the effectiveness of voting methodsThe Annals of Statistics, 1998