Minimum Variance Generalized State Estimators for Multiple Sensors with Different Delay Rates

Authors

Franck O. Hounkpevi, Marquette University
Edwin E. Yaz, Marquette UniversityFollow

Document Type

Article

Publication Date

4-2007

Publisher

Elsevier

Source Publication

Signal Processing

Source ISSN

0165-1684

Original Item ID

DOI: 10.1016/j.sigpro.2006.06.017

Abstract

In this paper, linear minimum variance unbiased state estimation is considered for signals with sensor delay. The solutions that have been proposed for the sensor delay problem so far only involve sensors with identical delay characteristics. However, in a true sensor network system, there may be multiple sensors which may not have the same delay characteristics. Therefore, the main goal of this research is to extend and generalize the existing solutions by modeling multiple sensors having different delay characteristics. The probability of occurrence of the delay is assumed to be known from the queuing characteristics. Illustrative examples are provided to support the theory developed in this work. Simulation comparison of the solution developed in this framework to the traditional Kalman Filter shows superiority and efficiency of our technique in the case of sensor delay. Furthermore, the robustness of the proposed method is also shown by simulations.

Comments

Signal Processing, Vol. 87, No. 4 (April 2007): 602-613. DOI.

Recommended Citation

Hounkpevi, Franck O. and Yaz, Edwin E., "Minimum Variance Generalized State Estimators for Multiple Sensors with Different Delay Rates" (2007). Electrical and Computer Engineering Faculty Research and Publications. 740.
https://epublications.marquette.edu/electric_fac/740