Tracking analysis of minimum kernel risk-sensitive loss algorithm under general non-Gaussian noise

Rastegarnia, A, Malekian, P, Khalili, A, Bazzi, WM and Sanei, S ORCID logoORCID: https://orcid.org/0000-0002-3437-2801, 2018. Tracking analysis of minimum kernel risk-sensitive loss algorithm under general non-Gaussian noise. IEEE Transactions on Circuits and Systems II: Express Briefs. ISSN 1549-7747

[thumbnail of 12252_Sanei.pdf]
Preview
Text
12252_Sanei.pdf - Post-print

Download (544kB) | Preview

Abstract

In this paper the steady-state tracking performance of minimum kernel risk-sensitive loss (MKRSL) in a non-stationary environment is analyzed. In order to model a non-stationary environment, a first-order random-walk model is used to describe the variations of optimum weight vector over time. Moreover, the measurement noise is considered to have non-Gaussian distribution. The energy conservation relation is utilized to extract an approximate closed-form expression for the steady-state excess mean square error (EMSE). Our analysis shows that unlike for the stationary case, the EMSE curve is not an increasing function of step-size parameter. Hence, the optimum step-size which minimizes the EMSE is derived. We also discuss that our approach can be used to extract steady-state EMSE for a general class of adaptive filters. The simulation results with different noise distributions support the theoretical derivations.

Item Type: Journal article
Publication Title: IEEE Transactions on Circuits and Systems II: Express Briefs
Creators: Rastegarnia, A., Malekian, P., Khalili, A., Bazzi, W.M. and Sanei, S.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 30 November 2018
ISSN: 1549-7747
Identifiers:
Number
Type
10.1109/tcsii.2018.2874969
DOI
Divisions: Schools > School of Science and Technology
Record created by: Linda Sullivan
Date Added: 23 Oct 2018 14:50
Last Modified: 23 Oct 2018 14:50
URI: https://irep.ntu.ac.uk/id/eprint/34720

Actions (login required)

Edit View Edit View

Statistics

Views

Views per month over past year

Downloads

Downloads per month over past year