𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Feature reduction for classification of multidimensional data

✍ Scribed by H. Brunzell; J. Eriksson

Book ID
104160505
Publisher
Elsevier Science
Year
2000
Tongue
English
Weight
204 KB
Volume
33
Category
Article
ISSN
0031-3203

No coin nor oath required. For personal study only.

✦ Synopsis

This paper addresses the problem of classifying multidimensional data with relatively few training samples available. Classi"cation is often performed based on data from measurements or ratings of objects or events. These data are called features. It is sometimes di$cult to determine if all features are necessary for the classi"er. Since the number of training samples needed to design a classi"er grows with the dimension of the features, a way to reduce the dimension of the features without losing any essential information is needed. This paper presents a new method for feature reduction, and compares it with some methods presented earlier in the literature. This new method is found to have a more stable and predictable performance than the other methods.

πŸ“œ SIMILAR VOLUMES

Unsupervised feature dimension reduction
Unsupervised feature dimension reduction for classification of MR spectra
✍ R. Baumgartner; R. Somorjai; C. Bowman; T.C. Sorrell; C.E. Mountford; U. Himmelr πŸ“‚ Article πŸ“… 2004 πŸ› Elsevier Science 🌐 English βš– 299 KB

We present an unsupervised feature dimension reduction method for the classification of magnetic resonance spectra. The technique preserves spectral information, important for disease profiling. We propose to use this technique as a preprocessing step for computationally demanding wrapper-based feat

Logic classification and feature selecti
Logic classification and feature selection for biomedical data
✍ P. Bertolazzi; G. Felici; P. Festa; G. Lancia πŸ“‚ Article πŸ“… 2008 πŸ› Elsevier Science 🌐 English βš– 314 KB

In this paper we investigate logic classification and related feature selection algorithms for large biomedical data sets. When the data is in binary/logic form, the feature selection problem can be formulated as a Set Covering problem of very large dimensions, whose solution is computationally chal