A Novel Differential Geometric Approach toward Robust Signal Detection.
Abstract
We present a new approach toward robust signal detection which is based on techniques rooted in differential geometry. These methods, as opposed to the commonly employed classical saddlepoint criteria, readily admit the quantitive measure of the degree of robustness over very general classes of admissible noise distributions. Our approach thus is seen to make possible investigations of the quantative tradeoff between optimal performance and robustness, and we illustrate the application of this differential geometric approach via various specific examples. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- May 22, 1986
- Accession Number
- ADA170035
Entities
People
- D. R. Halverson
- M. W. Thompson
Organizations
- Texas A&M University