Robustness of the detection probability for the sign detector /
The sign detector and robustness have been studied in many applications. Users of the sign detector need to know when this tool is appropriate, especially when parameters of the noise, such as the variance, are unknown. This thesis attempts to determine the appropriateness of the sign detector by...
| Main Author: | |
|---|---|
| Format: | Thesis eBook |
| Language: | English |
| Published: |
[Place of publication not identified] :
[publisher not identified] ;
2003.
|
| Subjects: | |
| Online Access: | Link to OAKTrust copy |
| Summary: | The sign detector and robustness have been studied in many applications. Users of the sign detector need to know when this tool is appropriate, especially when parameters of the noise, such as the variance, are unknown. This thesis attempts to determine the appropriateness of the sign detector by investigating the robustness of the detector's detection probability for various values of the noise variance. First, we examine the robustness when densities that are closed under k[sq. root][theta]-compression (Gaussian, Laplace, hyperbolic secant, etc.) are used. Then we examine the robustness for unbiased perturbations on a generalized Gaussian density. |
|---|---|
| Item Description: | "Major subject: Electrical Engineering". Vita. |
| Physical Description: | v, 83 leaves : illustrations ; 28 cm. Also available online. Issued also on microfiche from Lange Micrographics. |
| Bibliography: | Includes bibliographical references (leaf 32). |