Sensitivity of Support Vector Machines to Random Feature Selection in Classification of Hyperspectral Data.
Björn WaskeSebastian van der LindenJón Atli BenediktssonAndreas RabePatrick HostertPublished in: IEEE Trans. Geosci. Remote. Sens. (2010)
Keyphrases
- support vector
- feature selection
- hyperspectral data
- classification accuracy
- hyperspectral
- support vector machine
- hyperspectral imagery
- hyperspectral images
- random projections
- feature set
- multispectral
- machine learning
- feature ranking
- feature extraction
- feature space
- text classification
- high dimensionality
- svm classifier
- infrared
- unsupervised learning
- dimensionality reduction
- model selection
- dimension reduction
- pattern recognition
- hyperplane
- support vector machine svm
- kernel function
- text categorization
- svm classification
- image segmentation
- high dimensional
- feature vectors
- nearest neighbor
- data compression
- feature subset
- principal components
- sample size