Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
THE SYSTEMATIC-ERROR DETECTION AS A CLASSIFICATION PROBLEM
Autore:
GLUHCHEV G; SHALEV S;
Indirizzi:
INST INFORMAT TECHNOL,ACAD G BONCHEV ST,BL 29A SOFIA 1113 BULGARIA MANITOBA CANC TREATMENT & RES FDN WINNIPEG MB R3E 0V9 CANADA
Titolo Testata:
Pattern recognition letters
fascicolo: 12, volume: 17, anno: 1996,
pagine: 1233 - 1238
SICI:
0167-8655(1996)17:12<1233:TSDAAC>2.0.ZU;2-P
Fonte:
ISI
Lingua:
ENG
Soggetto:
PORTAL IMAGES; ACCURACY;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
CompuMath Citation Index
Science Citation Index Expanded
Citazioni:
6
Recensione:
Indirizzi per estratti:
Citazione:
G. Gluhchev e S. Shalev, "THE SYSTEMATIC-ERROR DETECTION AS A CLASSIFICATION PROBLEM", Pattern recognition letters, 17(12), 1996, pp. 1233-1238

Abstract

A classification approach to the detection of a systematic displacement Delta is described based on a single measurement mu = Delta + delta, where delta is a random error. Delta is supposed to be constant within a group of n measurements but may vary from one group to another. Normal distributions N(Delta; 0, sigma(Delta)(2)) and N(delta; 0, sigma(delta)(2)) are assumed for Delta and delta, respectively. Two classesA and B are defined that correspond to the presence and absence of a significant Delta. A classification rule: Delta is an element of A, if\mu\ less than or equal to beta, otherwise Delta is an element of B, is used, where beta is an optimal threshold in the sense of minimal average loss due to the classification errors. Also, an evaluation of the magnitude of the required correction is suggested based on the maximum likelihood estimation of d. Experiments have been carried out to evaluate the efficacy of the approach, For this, 5000 groups of 25 measurements each were simulated at different values of delta(Delta) and sigma(delta). Comparison was carried out with the rule suggested by Eel et al. (1993) in terms of (a) goodness, defined as a difference in percent between successful corrections and unsuccessful corrections, (b) magnitude of the residual systematic displacement Delta(r), and (c) average number of corrections. The obtained results have shown that the new approach outperforms Eel's rule for the tested parameters by about30% in goodness and about 10% in Delta(r) at sigma(Delta) = sigma(delta) = 2.0, but at the expense of a factor of 1.1 more corrections and measurement of all displacements. Eel et al. measure about 10% of the displacements. The approach may be used in different areas like radiation therapy, manufacture or process control.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 04/07/20 alle ore 21:10:23