Automatic Error Detection in Gaussian Processes Regression Modeling for Production Scheduling

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschung

Standard

Automatic Error Detection in Gaussian Processes Regression Modeling for Production Scheduling. / Scholz-Reiter, Bernd; Heger, Jens.
ADVCOMP 2011: The Fifth International Conference on Advanced Engineering Computing and Applications in Sciences. IARIA XPS Press, 2011. S. 66-71.

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschung

Harvard

Scholz-Reiter, B & Heger, J 2011, Automatic Error Detection in Gaussian Processes Regression Modeling for Production Scheduling. in ADVCOMP 2011: The Fifth International Conference on Advanced Engineering Computing and Applications in Sciences. IARIA XPS Press, S. 66-71, 5th International Conference on Advanced Engineering Computing and Applications in Sciences - ADVCOMP 2011, Lissabon, Portugal, 20.11.11. <http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.676.9499&rep=rep1&type=pdf>

APA

Scholz-Reiter, B., & Heger, J. (2011). Automatic Error Detection in Gaussian Processes Regression Modeling for Production Scheduling. In ADVCOMP 2011: The Fifth International Conference on Advanced Engineering Computing and Applications in Sciences (S. 66-71). IARIA XPS Press. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.676.9499&rep=rep1&type=pdf

Vancouver

Scholz-Reiter B, Heger J. Automatic Error Detection in Gaussian Processes Regression Modeling for Production Scheduling. in ADVCOMP 2011: The Fifth International Conference on Advanced Engineering Computing and Applications in Sciences. IARIA XPS Press. 2011. S. 66-71

Bibtex

@inbook{dd4c6690b7c446d3967c38aec04a8ee9,
title = "Automatic Error Detection in Gaussian Processes Regression Modeling for Production Scheduling",
abstract = "In the application field of production, scheduling with dispatching rules is facing the problem that no rule performs globally better than any other. Therefore, machine learning techniques can be used to calculate estimates of rule performances and select the best rule for each system state. A number of estimates are of poor quality and lead to a wrong selection of rules. Motivated by this problem, to further stabilize the selection approach a general approach, to automatically detect {\textquoteleft}faulty{\textquoteright} estimates from regression models is introduced and analyzed in this paper. Therefore, different models are learned and if their estimates differ strongly, it is likely that at least one model delivers poor estimates.Additionally, a difference-threshold for our example data is defined. As a machine learning technique, we use Gaussian process regression with different covariance functions (kernels). The results have shown that our automatic detection",
keywords = "Engineering",
author = "Bernd Scholz-Reiter and Jens Heger",
year = "2011",
language = "English",
isbn = "978-1-61208-172-4",
pages = "66--71",
booktitle = "ADVCOMP 2011",
publisher = "IARIA XPS Press",
address = "Denmark",
note = "5th International Conference on Advanced Engineering Computing and Applications in Sciences - ADVCOMP 2011, ADVCOMP 2011 ; Conference date: 20-11-2011 Through 25-11-2011",
url = "https://www.iaria.org/conferences2011/ADVCOMP11.html",

}

RIS

TY - CHAP

T1 - Automatic Error Detection in Gaussian Processes Regression Modeling for Production Scheduling

AU - Scholz-Reiter, Bernd

AU - Heger, Jens

N1 - Conference code: 5

PY - 2011

Y1 - 2011

N2 - In the application field of production, scheduling with dispatching rules is facing the problem that no rule performs globally better than any other. Therefore, machine learning techniques can be used to calculate estimates of rule performances and select the best rule for each system state. A number of estimates are of poor quality and lead to a wrong selection of rules. Motivated by this problem, to further stabilize the selection approach a general approach, to automatically detect ‘faulty’ estimates from regression models is introduced and analyzed in this paper. Therefore, different models are learned and if their estimates differ strongly, it is likely that at least one model delivers poor estimates.Additionally, a difference-threshold for our example data is defined. As a machine learning technique, we use Gaussian process regression with different covariance functions (kernels). The results have shown that our automatic detection

AB - In the application field of production, scheduling with dispatching rules is facing the problem that no rule performs globally better than any other. Therefore, machine learning techniques can be used to calculate estimates of rule performances and select the best rule for each system state. A number of estimates are of poor quality and lead to a wrong selection of rules. Motivated by this problem, to further stabilize the selection approach a general approach, to automatically detect ‘faulty’ estimates from regression models is introduced and analyzed in this paper. Therefore, different models are learned and if their estimates differ strongly, it is likely that at least one model delivers poor estimates.Additionally, a difference-threshold for our example data is defined. As a machine learning technique, we use Gaussian process regression with different covariance functions (kernels). The results have shown that our automatic detection

KW - Engineering

UR - http://www.logdynamics.de/papers_conferences.html?pubID=489

M3 - Article in conference proceedings

SN - 978-1-61208-172-4

SP - 66

EP - 71

BT - ADVCOMP 2011

PB - IARIA XPS Press

T2 - 5th International Conference on Advanced Engineering Computing and Applications in Sciences - ADVCOMP 2011

Y2 - 20 November 2011 through 25 November 2011

ER -