S
Samia Boukir
Researcher at University of Bordeaux
Publications - 26
Citations - 988
Samia Boukir is an academic researcher from University of Bordeaux. The author has contributed to research in topics: Random forest & Ensemble learning. The author has an hindex of 13, co-authored 26 publications receiving 827 citations.
Papers
More filters
Journal ArticleDOI
Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests
TL;DR: The Random Forests algorithm is chosen as a classifier: it runs efficiently on large datasets, and provides measures of feature importance for each class, and the relevance of full-waveform lidar features is demonstrated for building and vegetation area discrimination.
Journal ArticleDOI
Exploring issues of training data imbalance and mislabelling on random forest performance for large area land cover classification using the ensemble margin
TL;DR: New ensemble margin criteria are introduced to evaluate the performance of Random Forests in the context of large area land cover classification and the effect of different training data characteristics (imbalance and mislabelling) on classification accuracy and uncertainty is examined.
Journal ArticleDOI
Margin-based ordered aggregation for ensemble pruning
Li Guo,Samia Boukir +1 more
TL;DR: This paper presents a new ensemble pruning method which highly reduces the complexity of ensemble methods and performs better than complete bagging in terms of classification accuracy and is a very fast algorithm.
Journal ArticleDOI
Object-based change detection in wind storm-damaged forest using high-resolution multispectral images
TL;DR: An efficient, quasi-automatic object-based method for change mapping using high-spatial-resolution (HR) (5–10 m) satellite imagery is proposed and highlights the correlation between the ages of trees and their sensitivity to wind.
Journal ArticleDOI
Automated retrieval of forest structure variables based on multi-scale texture analysis of VHR satellite imagery
TL;DR: An automated forest variable estimation scheme based on linear regressions, which outperforms two well-established variable subset selection techniques and relies on random sampling in feature space, carefully addresses the multicollinearity issue in multiple-linear regression while ensuring accurate prediction of forest variables.