Exploring issues of training data imbalance and mislabelling on random forest performance for large area land cover classification using the ensemble margin-Reference-Cited by-同舟云学术

Exploring issues of training data imbalance and mislabelling on random forest performance for large area land cover classification using the ensemble margin

Published:2015-07 Issue: Volume:105 Page:155-168
ISSN:0924-2716
Container-title:ISPRS Journal of Photogrammetry and Remote Sensing
language:en
Short-container-title:ISPRS Journal of Photogrammetry and Remote Sensing

Author:

Mellor Andrew,Boukir Samia,Haywood Andrew,Jones Simon

Publisher

Elsevier BV

Subject

Computers in Earth Sciences,Computer Science Applications,Engineering (miscellaneous),Atomic and Molecular Physics, and Optics

Reference55 articles.

1. Satellite remote sensing of forest resources: three decades of research development;Boyd;Prog. Phys. Geogr.,2005

2. Identifying and Eliminating Mislabeled Training Instances;Bradley,1996

3. Bagging predictors;Breiman;Mach. Learn.,1996

4. Random forests;Breiman;Mach. Learn.,2001

5. Assessing agreement on classification tasks: the Kappa statistic;Carletta;Comput. Linguist.,1996

Cited by 203 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Revealing the impact of spatial bias in survey design for habitat mapping: A tale of two sampling designs;Remote Sensing Applications: Society and Environment;2024-11

2. Advancements in mapping areas suitable for wetland habitats across the conterminous United States;Science of The Total Environment;2024-11

3. Few-shot satellite image classification for bringing deep learning on board OPS-SAT;Expert Systems with Applications;2024-10

4. Prediction of ionic liquid surface tension via a generalized interpretable Structure‐Surface Tension Relationship model;AIChE Journal;2024-08-07

5. Deep learning-based gap filling for near real-time seamless daily global sea surface salinity using satellite observations;International Journal of Applied Earth Observation and Geoinformation;2024-08