Neural net based variable structure multiple model reducing mode set jump delay

Daebum Choi, Byungha Ahn, Hanseok Ko

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Variable structure multiple model (VSMM) is one of the most powerful algorithms for effectively tracking single maneuvering target. Although VSMM is developed specifically to improve the interactive multiple model (IMM) method focused to reducing computational cost and improving tracking performance, it presents an inherent limitation in the form of the presence of mode set jump delay (MJD). In this paper, MJD as an undesirable phenomenon in VSMM is described and analyzed. In order to eliminate the MJD, a neural network based VSMM that automatically selects the optimal mode set as achieved by supervised training is proposed. Through representative simulations we show the proposed algorithm outperforming over the conventional digraph switching VSMM in terms of tracking error.

Original languageEnglish
Title of host publicationIEEE Workshop on Statistical Signal Processing Proceedings
Pages142-145
Number of pages4
Publication statusPublished - 2001 Dec 1
Externally publishedYes
Event2001 IEEE Workshop on Statitical Signal Processing Proceedings - Singapore, Singapore
Duration: 2001 Aug 62001 Aug 8

Other

Other2001 IEEE Workshop on Statitical Signal Processing Proceedings
CountrySingapore
CitySingapore
Period01/8/601/8/8

Fingerprint

Neural networks
Costs

ASJC Scopus subject areas

  • Signal Processing

Cite this

Choi, D., Ahn, B., & Ko, H. (2001). Neural net based variable structure multiple model reducing mode set jump delay. In IEEE Workshop on Statistical Signal Processing Proceedings (pp. 142-145)

Neural net based variable structure multiple model reducing mode set jump delay. / Choi, Daebum; Ahn, Byungha; Ko, Hanseok.

IEEE Workshop on Statistical Signal Processing Proceedings. 2001. p. 142-145.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Choi, D, Ahn, B & Ko, H 2001, Neural net based variable structure multiple model reducing mode set jump delay. in IEEE Workshop on Statistical Signal Processing Proceedings. pp. 142-145, 2001 IEEE Workshop on Statitical Signal Processing Proceedings, Singapore, Singapore, 01/8/6.
Choi D, Ahn B, Ko H. Neural net based variable structure multiple model reducing mode set jump delay. In IEEE Workshop on Statistical Signal Processing Proceedings. 2001. p. 142-145
Choi, Daebum ; Ahn, Byungha ; Ko, Hanseok. / Neural net based variable structure multiple model reducing mode set jump delay. IEEE Workshop on Statistical Signal Processing Proceedings. 2001. pp. 142-145
@inproceedings{8da745eec2784ca8b9265e1d9ec3228c,
title = "Neural net based variable structure multiple model reducing mode set jump delay",
abstract = "Variable structure multiple model (VSMM) is one of the most powerful algorithms for effectively tracking single maneuvering target. Although VSMM is developed specifically to improve the interactive multiple model (IMM) method focused to reducing computational cost and improving tracking performance, it presents an inherent limitation in the form of the presence of mode set jump delay (MJD). In this paper, MJD as an undesirable phenomenon in VSMM is described and analyzed. In order to eliminate the MJD, a neural network based VSMM that automatically selects the optimal mode set as achieved by supervised training is proposed. Through representative simulations we show the proposed algorithm outperforming over the conventional digraph switching VSMM in terms of tracking error.",
author = "Daebum Choi and Byungha Ahn and Hanseok Ko",
year = "2001",
month = "12",
day = "1",
language = "English",
pages = "142--145",
booktitle = "IEEE Workshop on Statistical Signal Processing Proceedings",

}

TY - GEN

T1 - Neural net based variable structure multiple model reducing mode set jump delay

AU - Choi, Daebum

AU - Ahn, Byungha

AU - Ko, Hanseok

PY - 2001/12/1

Y1 - 2001/12/1

N2 - Variable structure multiple model (VSMM) is one of the most powerful algorithms for effectively tracking single maneuvering target. Although VSMM is developed specifically to improve the interactive multiple model (IMM) method focused to reducing computational cost and improving tracking performance, it presents an inherent limitation in the form of the presence of mode set jump delay (MJD). In this paper, MJD as an undesirable phenomenon in VSMM is described and analyzed. In order to eliminate the MJD, a neural network based VSMM that automatically selects the optimal mode set as achieved by supervised training is proposed. Through representative simulations we show the proposed algorithm outperforming over the conventional digraph switching VSMM in terms of tracking error.

AB - Variable structure multiple model (VSMM) is one of the most powerful algorithms for effectively tracking single maneuvering target. Although VSMM is developed specifically to improve the interactive multiple model (IMM) method focused to reducing computational cost and improving tracking performance, it presents an inherent limitation in the form of the presence of mode set jump delay (MJD). In this paper, MJD as an undesirable phenomenon in VSMM is described and analyzed. In order to eliminate the MJD, a neural network based VSMM that automatically selects the optimal mode set as achieved by supervised training is proposed. Through representative simulations we show the proposed algorithm outperforming over the conventional digraph switching VSMM in terms of tracking error.

UR - http://www.scopus.com/inward/record.url?scp=0035555561&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035555561&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0035555561

SP - 142

EP - 145

BT - IEEE Workshop on Statistical Signal Processing Proceedings

ER -