Hyperspectral Remote Sensing Image Classification Based on Rotation Forest

Abstract : In this letter, an ensemble learning approach, Rotation Forest, has been applied to hyperspectral remote sensing image classification for the first time. The framework of Rotation Forest is to project the original data into a new feature space using transformation methods for each base classifier (decision tree), then the base classifier can train in different new spaces for the purpose of encouraging both individual accuracy and diversity within the ensemble simultaneously. Principal component analysis (PCA), maximum noise fraction, independent component analysis, and local Fisher discriminant analysis are introduced as feature transformation algorithms in the original Rotation Forest. The performance of Rotation Forest was evaluated based on several criteria: different data sets, sensitivity to the number of training samples, ensemble size and the number of features in a subset. Experimental results revealed that Rotation Forest, especially with PCA transformation, could produce more accurate results than bagging, AdaBoost, and Random Forest. They indicate that Rotation Forests are promising approaches for generating classifier ensemble of hyperspectral remote sensing.
Type de document :
Article dans une revue
IEEE Geoscience and Remote Sensing Letters, IEEE - Institute of Electrical and Electronics Engineers, 2014, 11 (1), pp.239-243. 〈10.1109/LGRS.2013.2254108〉
Liste complète des métadonnées

http://hal.univ-grenoble-alpes.fr/hal-01128445
Contributeur : Vincent Couturier-Doux <>
Soumis le : lundi 9 mars 2015 - 17:08:36
Dernière modification le : lundi 9 avril 2018 - 12:22:34

Lien texte intégral

Identifiants

Citation

Junshi Xia, Peijun Du, Xivan He, Jocelyn Chanussot. Hyperspectral Remote Sensing Image Classification Based on Rotation Forest. IEEE Geoscience and Remote Sensing Letters, IEEE - Institute of Electrical and Electronics Engineers, 2014, 11 (1), pp.239-243. 〈10.1109/LGRS.2013.2254108〉. 〈hal-01128445〉

Partager

Métriques

Consultations de la notice

169