Case of Short Data Record for Both Training and Signal Detection
Abstract
Detection of a signal embedded in interference is a common problem encountered in radar, sonar and communication systems. In cases where it is known that the interference is low rank (or approximately so) the amount of data required for adaptation can be reduced by using reduced rank estimation methods. Three proposed methods for making the selection of basis vectors are the Cross Spectral Metric (CSM) method, the Principal Components Inverse (PCI) method and Multistage Wiener Filter (MWF). The examination here is for detection of a signal that may or may not be present within a given set of data. That is, training and signal detection must be performed using the same data set. The case of independent training and test data has been treated in.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2000
- Accession Number
- ADA405489
Entities
People
- Brian E. Freburger
- Donald W. Tufts
Organizations
- Naval Air Warfare Center