Unbiased FIR, Kalman, and game theory H∞ filtering under bernoulli distributed random delays and packet dropouts

It is known that due to uncertain delays and missing data wireless sensor networks (WSNs) may incur a significant loss in performance. In this work, we solve the problem in discrete-time state-space by developing the unbiased finite impulse response (UFIR) filter, Kalman filter (KF), and game theory...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) Vol. 442; pp. 89 - 97
Main Authors: Uribe-Murcia, Karen, Shmaliy, Yuriy S., Andrade-Lucio, José A.
Format: Journal Article
Language:English
Published: Elsevier B.V 28.06.2021
Subjects:
Bernoulli distribution
Delayed data
Packet dropouts
Unbiased FIR filter
Bernoulli distribution
Delayed data
Packet dropouts
Unbiased FIR filter
ISSN:0925-2312, 1872-8286
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:It is known that due to uncertain delays and missing data wireless sensor networks (WSNs) may incur a significant loss in performance. In this work, we solve the problem in discrete-time state-space by developing the unbiased finite impulse response (UFIR) filter, Kalman filter (KF), and game theory H∞ filter for systems with randomly delayed data and packet dropouts. The binary Bernoulli distribution is adopted for WSN channels to model the arrival data with supposedly known delay-time probability. The effectiveness of the UFIR filter, KF, and H∞ filter is compared experimentally in terms of accuracy and robustness employing the GPS-measured vehicle coordinates transmitted with latency over WSN.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2021.01.127