Minimax Predictors for Signals Having a Bonded kth Derivative

D. W. Kelsey; A. H. Haddad

doi:10.1016/0016-0032(74)90136-7

Minimax Predictors for Signals Having a Bonded kth Derivative

D. W. Kelsey^*, A. H. Haddad

^*Corresponding author for this work

Electrical and Computer Engineering

Research output: Contribution to journal › Article › peer-review

5 Scopus citations

Abstract

Predictors are derived which minimize the maximum possible mean-squared prediction error for signals observed in white noise and having a bounded kth derivative. Expressions are given for the resulting worst-case error and a suboptimal solution is presented which, for the case k = 2, performs nearly as well as the optimal and is far easier to implement.

Original language	English (US)
Pages (from-to)	29-44
Number of pages	16
Journal	Journal of the Franklin Institute
Volume	297
Issue number	1
DOIs	https://doi.org/10.1016/0016-0032(74)90136-7
State	Published - Jan 1974

ASJC Scopus subject areas

Control and Systems Engineering
Signal Processing
Computer Networks and Communications
Applied Mathematics

Access to Document

10.1016/0016-0032(74)90136-7

Cite this

@article{6d03b9fd49e64f45a6ff330491448055,

title = "Minimax Predictors for Signals Having a Bonded kth Derivative",

abstract = "Predictors are derived which minimize the maximum possible mean-squared prediction error for signals observed in white noise and having a bounded kth derivative. Expressions are given for the resulting worst-case error and a suboptimal solution is presented which, for the case k = 2, performs nearly as well as the optimal and is far easier to implement.",

author = "Kelsey, {D. W.} and Haddad, {A. H.}",

note = "Funding Information: * This work was supported by the Joint Services Electronics Program (U.S. Army, Navy, and Air Force) under Contract DAAR07-67-C-0199. t Presently with the Center for Naval Analyses, Washington, D.C.",

year = "1974",

month = jan,

doi = "10.1016/0016-0032(74)90136-7",

language = "English (US)",

volume = "297",

pages = "29--44",

journal = "Journal of the Franklin Institute",

issn = "0016-0032",

publisher = "Elsevier Ltd",

number = "1",

}

TY - JOUR

T1 - Minimax Predictors for Signals Having a Bonded kth Derivative

AU - Kelsey, D. W.

AU - Haddad, A. H.

N1 - Funding Information: * This work was supported by the Joint Services Electronics Program (U.S. Army, Navy, and Air Force) under Contract DAAR07-67-C-0199. t Presently with the Center for Naval Analyses, Washington, D.C.

PY - 1974/1

Y1 - 1974/1

N2 - Predictors are derived which minimize the maximum possible mean-squared prediction error for signals observed in white noise and having a bounded kth derivative. Expressions are given for the resulting worst-case error and a suboptimal solution is presented which, for the case k = 2, performs nearly as well as the optimal and is far easier to implement.

AB - Predictors are derived which minimize the maximum possible mean-squared prediction error for signals observed in white noise and having a bounded kth derivative. Expressions are given for the resulting worst-case error and a suboptimal solution is presented which, for the case k = 2, performs nearly as well as the optimal and is far easier to implement.

UR - http://www.scopus.com/inward/record.url?scp=0015961428&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0015961428&partnerID=8YFLogxK

U2 - 10.1016/0016-0032(74)90136-7

DO - 10.1016/0016-0032(74)90136-7

M3 - Article

AN - SCOPUS:0015961428

SN - 0016-0032

VL - 297

SP - 29

EP - 44

JO - Journal of the Franklin Institute

JF - Journal of the Franklin Institute

IS - 1

ER -

Minimax Predictors for Signals Having a Bonded kth Derivative

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this