SELECT: An Orthogonal Feature-Selection Method.
Abstract
A new preprocessing method that has found considerable use for chemical applications is presented. Features are selected that are useful for class discrimination, orthogonal, and at least in part, retain identity to the original measurements. A brief introduction to chemical pattern recognition is presented followed by a description of the method and an application to mass spectral data analysis. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 01, 1974
- Accession Number
- AD0783707
Entities
People
- B. R. Kowalski
- C. F. Bender
Organizations
- University of Washington