Multivariate control charts based on hybrid novelty scores

Gulanbaier Tuerhong, Seoung Bum Kim, Pilsung Kang, Sungzoon Cho

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

We propose a new nonparametric multivariate control chart that integrates a novelty score. The proposed control chart uses as its monitoring statistic a hybrid novelty score, calculated based on the distance to local observations as well as on the distance to the convex hull constructed by its neighbors. The control limits of the proposed control chart were established based on a bootstrap method. A rigorous simulation study was conducted to examine the properties of the proposed control chart under various scenarios and compare it with existing multivariate control charts in terms of average run length (ARL) performance. The simulation results showed that the proposed control chart outperformed both the parametric and nonparametric Hotelling's T 2 control charts, especially in nonnormal situations. Moreover, experimental results with real semiconductor data demonstrated the applicability and effectiveness of the proposed control chart. To increase the capability to detect small mean shift, we propose an exponentially weighted hybrid novelty score control chart. Simulation results indicated that exponentially weighted hybrid score charts outperformed the hybrid novelty score based control charts.

Original languageEnglish
Pages (from-to)115-131
Number of pages17
JournalCommunications in Statistics: Simulation and Computation
Volume43
Issue number1
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Multivariate Control Charts
Control Charts
Average Run Length
Mean Shift
Control charts
Bootstrap Method
Chart
Convex Hull
Statistic
Semiconductors
Simulation
Integrate
Simulation Study
Monitoring
Scenarios

Keywords

  • Data mining
  • Multivariate control charts
  • Novelty score
  • Quality control

ASJC Scopus subject areas

  • Modelling and Simulation
  • Statistics and Probability

Cite this

Multivariate control charts based on hybrid novelty scores. / Tuerhong, Gulanbaier; Kim, Seoung Bum; Kang, Pilsung; Cho, Sungzoon.

In: Communications in Statistics: Simulation and Computation, Vol. 43, No. 1, 01.01.2014, p. 115-131.

Research output: Contribution to journalArticle

@article{3515d93b1e4a4741b1ccfdb8dddafaed,
title = "Multivariate control charts based on hybrid novelty scores",
abstract = "We propose a new nonparametric multivariate control chart that integrates a novelty score. The proposed control chart uses as its monitoring statistic a hybrid novelty score, calculated based on the distance to local observations as well as on the distance to the convex hull constructed by its neighbors. The control limits of the proposed control chart were established based on a bootstrap method. A rigorous simulation study was conducted to examine the properties of the proposed control chart under various scenarios and compare it with existing multivariate control charts in terms of average run length (ARL) performance. The simulation results showed that the proposed control chart outperformed both the parametric and nonparametric Hotelling's T 2 control charts, especially in nonnormal situations. Moreover, experimental results with real semiconductor data demonstrated the applicability and effectiveness of the proposed control chart. To increase the capability to detect small mean shift, we propose an exponentially weighted hybrid novelty score control chart. Simulation results indicated that exponentially weighted hybrid score charts outperformed the hybrid novelty score based control charts.",
keywords = "Data mining, Multivariate control charts, Novelty score, Quality control",
author = "Gulanbaier Tuerhong and Kim, {Seoung Bum} and Pilsung Kang and Sungzoon Cho",
year = "2014",
month = "1",
day = "1",
doi = "10.1080/03610918.2012.698775",
language = "English",
volume = "43",
pages = "115--131",
journal = "Communications in Statistics Part B: Simulation and Computation",
issn = "0361-0918",
publisher = "Taylor and Francis Ltd.",
number = "1",

}

TY - JOUR

T1 - Multivariate control charts based on hybrid novelty scores

AU - Tuerhong, Gulanbaier

AU - Kim, Seoung Bum

AU - Kang, Pilsung

AU - Cho, Sungzoon

PY - 2014/1/1

Y1 - 2014/1/1

N2 - We propose a new nonparametric multivariate control chart that integrates a novelty score. The proposed control chart uses as its monitoring statistic a hybrid novelty score, calculated based on the distance to local observations as well as on the distance to the convex hull constructed by its neighbors. The control limits of the proposed control chart were established based on a bootstrap method. A rigorous simulation study was conducted to examine the properties of the proposed control chart under various scenarios and compare it with existing multivariate control charts in terms of average run length (ARL) performance. The simulation results showed that the proposed control chart outperformed both the parametric and nonparametric Hotelling's T 2 control charts, especially in nonnormal situations. Moreover, experimental results with real semiconductor data demonstrated the applicability and effectiveness of the proposed control chart. To increase the capability to detect small mean shift, we propose an exponentially weighted hybrid novelty score control chart. Simulation results indicated that exponentially weighted hybrid score charts outperformed the hybrid novelty score based control charts.

AB - We propose a new nonparametric multivariate control chart that integrates a novelty score. The proposed control chart uses as its monitoring statistic a hybrid novelty score, calculated based on the distance to local observations as well as on the distance to the convex hull constructed by its neighbors. The control limits of the proposed control chart were established based on a bootstrap method. A rigorous simulation study was conducted to examine the properties of the proposed control chart under various scenarios and compare it with existing multivariate control charts in terms of average run length (ARL) performance. The simulation results showed that the proposed control chart outperformed both the parametric and nonparametric Hotelling's T 2 control charts, especially in nonnormal situations. Moreover, experimental results with real semiconductor data demonstrated the applicability and effectiveness of the proposed control chart. To increase the capability to detect small mean shift, we propose an exponentially weighted hybrid novelty score control chart. Simulation results indicated that exponentially weighted hybrid score charts outperformed the hybrid novelty score based control charts.

KW - Data mining

KW - Multivariate control charts

KW - Novelty score

KW - Quality control

UR - http://www.scopus.com/inward/record.url?scp=84882407506&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84882407506&partnerID=8YFLogxK

U2 - 10.1080/03610918.2012.698775

DO - 10.1080/03610918.2012.698775

M3 - Article

VL - 43

SP - 115

EP - 131

JO - Communications in Statistics Part B: Simulation and Computation

JF - Communications in Statistics Part B: Simulation and Computation

SN - 0361-0918

IS - 1

ER -