Accession Number:

AD0645744

Title:

ON MINIMUM-MEAN-SQUARED ERROR NONLINEAR FILTERING.

Descriptive Note:

Technical rept.,

Corporate Author:

PRINCETON UNIV N J DEPT OF ELECTRICAL ENGINEERING

Personal Author(s):

• Haddad,A. H.
• Thomas,J. B.

Report Date:

1966-08-01

Pagination or Media Count:

158.0

Abstract:

The study is concerned with the minimum-mean-squared error MMSE nonlinear filtering of signals in additive noise. Methods of analysis, representation, and classification of non-linear systems are treated. Integral representations and their applicability to random inputs and MMSE filtering are emphasized. The general MMSE nonlinear filtering problem is discussed briefly the restriction of the filter to general classes of systems or input processes is considered. Usually the general solutions to the problem are difficult and in many cases are impractical therefore restriction to special classes of systems and special classes of input processes is investigated. Author

Descriptors:

• *SIGNAL TO NOISE RATIO
• *ELECTROMAGNETIC WAVE FILTERS
• *INFORMATION THEORY
• OPTIMIZATION
• STOCHASTIC PROCESSES
• NONLINEAR SYSTEMS
• FUNCTIONAL ANALYSIS
• POWER SERIES

Subject Categories:

• Statistics and Probability
• Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE