Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery

By Jonathan Cheung-Wai Chan, Desiré Paelinckx. 2008

857 citations recorded by the source corpus.

Subfields: Atmospheric Science, Ecology, Media Technology

View Paper: https://www.semanticscholar.org/paper/b4b4a54f3817f24e0131dead3a0befbdcd8f3cd6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Ecology

In Media Technology

Citations in the corpus

Basic Tenets of Classification Algorithms K-Nearest-Neighbor, Support Vector Machine, Random Forest and Neural Network: A Review (2020, background): “However, the straight-line distance, also called the Euclidean distance, is a popular and familiar choice [48].”
Tree Species Classification in Boreal Forests With Hyperspectral Data (2013, methodology): “Some of the selected bands in this study are in common with previous studies, while others are not [18], [21].”
Assessment of Low Density Full-Waveform Airborne Laser Scanning for Individual Tree Detection and Tree Species Classification (2014, background): “The former enables a much faster construction of trees and the latter the possibility of evaluating the relative importance of each input feature [49].”
A 30-m landsat-derived cropland extent product of Australia and China using random forest machine learning algorithm on Google Earth Engine cloud computing platform (2018, neutral): “The RF classi ﬁ er is more robust than single decision tree (Chan and Paelinckx, 2008) and easier to be implemented than many other advanced classi ﬁ ers such as Support Vector Mission (SVM) (Pelletier et al., 2016) as recently established by Xiong et al. (2017a).”
Use of UK-DMC 2 and ALOS PALSAR for studying the age of oil palm trees in southern peninsular Malaysia (2013, result): “Most of the studies reported that the RF classifier gave higher accuracy than the traditional decision tree classifiers (Deschamps et al. 2012; Rodriguez-Galiano et al. 2012), neural network classifier (Chan and Paelinckx 2008), and maximum-likelihood classifier (Ok, Akar, and Gungor 2012).”
Efficient corn and soybean mapping with temporal extendability: A multi-year experiment using Landsat imagery (2014, background): “…likelihood, spectral angle, single classification trees (Lawrence, Wood, & Sheley, 2006; Na, Zhang, Li, Yu, & Liu, 2010), and neural network (Chan & Paelinckx, 2008), ii) RF classifier is able to take numerous input variables and perform rapid classificationwithout being severely affected…”
Implementation of machine-learning classification in remote sensing: an applied review (2018, methodology): “In this case, however, as the models are built, they are adapted in an attempt to minimize the errors of the previous trees (Freund and Schapire 1997; Chan and Paelinckx 2008).”
Random forests and stochastic gradient boosting for predicting tree canopy cover: Comparing tuning processes and model performance (2016, background): “Chan and Paelinckx (2008) compared RF with Adaboost for mapping ecotopes from airborne hyperspectral imagery and found both models to work well, with RF having the advantage of faster training time and greater stability and robustness, while Adaboost had a slight advantage in accuracy.”
Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review (2020, background): “based on boosting, are not sensitive to noise or overtraining [137], [138], the above-stated value for Mtry might be too”
Contextual classification of lidar data and building object detection in urban areas (2014, methodology): “Besides generative classifiers modelling the joint distribution of the data and labels (Bishop, 2006), modern discriminative methods such as AdaBoost (Chan and Paelinckx, 2008), Support Vector Machines (SVM) (Mountrakis et al., 2011), and Random Forests (RF) (Breiman, 2001; Gislason et al., 2006) ar”
A survey of multiple classifier systems as hybrid systems (2014, methodology): “Works on hyperspectral images acquired by the HyMap sensor have been addressed to build vegetation thematic maps [170], comparing RF and decision tree-based Adaboost, as well as two feature selection methods: the out-ofbag and a best-first search wrapper feature subset selection method.”