MAXIMUM-LIKELIHOOD ESTIMATION OF A PROCESS WITH RANDOM TRANSITIONS (FAILURES).

Bernard Friedland

Research output: Contribution to journalConference articlepeer-review

Abstract

A process with random transitions is represented by the difference equation x//n equals x//n// minus //1 plus u//n where u//n is a nonlinear function of a gaussian sequence w//n. The nonlinear function has a threshold that results in a finite probability of no failure at every step. Maximum likelihood estimation of the sequence X//n equals left brace x//0,. . . ,x//n right brace given a sequence of observations Y//n equals left brace y//1,. . . ,y//n right brace gives rise to a two point boundary-value (TPBV) problem, the solution of which is suggested by the analogy with a nonlinear electrical ladder network. Examples comparing the nonlinear filter that gives an approximate solution of the TPBV problem with a linear recursive filter are given, and show the advantages of the former.

Original languageEnglish (US)
Pages (from-to)427-432
Number of pages6
JournalProceedings of the IEEE Conference on Decision and Control
StatePublished - 1978
Externally publishedYes
EventProc IEEE Conf Decis Control Incl Symp Adapt Processes 17th - San Diego, CA, USA
Duration: Jan 10 1979Jan 12 1979

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Modeling and Simulation
  • Control and Optimization

Fingerprint

Dive into the research topics of 'MAXIMUM-LIKELIHOOD ESTIMATION OF A PROCESS WITH RANDOM TRANSITIONS (FAILURES).'. Together they form a unique fingerprint.

Cite this