Optimal false alarm controlled support vector data description for multivariate process monitoring

Younghoon Kim, Seoung Bum Kim

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

One-class classification plays a key role in the detection of outliers and abnormalities. Recently, several attempts have been made to extend the application of one-class classification techniques to statistical process control problems, where many of these one-class classification-based approaches have used a support vector data description algorithm. The monitoring statistics for a support vector data description-based control chart are sufficiently defined. However, the control limits are not obvious because the procedure used to derive the control limit does not include a method for controlling the false alarm rate (i.e., Type I error rate), which clearly limits its use in process monitoring. In this study, we propose a new multivariate control chart based on a technique for optimal false alarm-controlled support vector data description, which minimizes the radius of a spherically shaped boundary so that it includes the normal data that are equal to an assigned constant value. By modifying this constant value, users can precisely control the proportion of abnormal data determined by the spherically shaped boundary, which equals the expected Type I error rate. We demonstrated the usefulness of the proposed charts in experiments with simulated data and real process data based on a thin film transistor-liquid crystal display.

Original languageEnglish
JournalJournal of Process Control
DOIs
Publication statusAccepted/In press - 2017

Fingerprint

Support Vector Data Description
Data description
Process Monitoring
Process monitoring
One-class Classification
False Alarm
Type I Error Rate
Statistical process control
Multivariate Control Charts
Thin film transistors
Thin-film Transistor
Liquid crystal displays
Liquid Crystal Display
Statistical Process Control
False Alarm Rate
Control Charts
Chart
Statistics
Outlier
Control Problem

Keywords

  • Control chart
  • Machine learning
  • One-class classification
  • Process control
  • Support vector data description

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Modelling and Simulation
  • Computer Science Applications
  • Industrial and Manufacturing Engineering

Cite this

@article{1f92631a48ec435186616160917bdc6c,
title = "Optimal false alarm controlled support vector data description for multivariate process monitoring",
abstract = "One-class classification plays a key role in the detection of outliers and abnormalities. Recently, several attempts have been made to extend the application of one-class classification techniques to statistical process control problems, where many of these one-class classification-based approaches have used a support vector data description algorithm. The monitoring statistics for a support vector data description-based control chart are sufficiently defined. However, the control limits are not obvious because the procedure used to derive the control limit does not include a method for controlling the false alarm rate (i.e., Type I error rate), which clearly limits its use in process monitoring. In this study, we propose a new multivariate control chart based on a technique for optimal false alarm-controlled support vector data description, which minimizes the radius of a spherically shaped boundary so that it includes the normal data that are equal to an assigned constant value. By modifying this constant value, users can precisely control the proportion of abnormal data determined by the spherically shaped boundary, which equals the expected Type I error rate. We demonstrated the usefulness of the proposed charts in experiments with simulated data and real process data based on a thin film transistor-liquid crystal display.",
keywords = "Control chart, Machine learning, One-class classification, Process control, Support vector data description",
author = "Younghoon Kim and Kim, {Seoung Bum}",
year = "2017",
doi = "10.1016/j.jprocont.2017.10.012",
language = "English",
journal = "Journal of Process Control",
issn = "0959-1524",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Optimal false alarm controlled support vector data description for multivariate process monitoring

AU - Kim, Younghoon

AU - Kim, Seoung Bum

PY - 2017

Y1 - 2017

N2 - One-class classification plays a key role in the detection of outliers and abnormalities. Recently, several attempts have been made to extend the application of one-class classification techniques to statistical process control problems, where many of these one-class classification-based approaches have used a support vector data description algorithm. The monitoring statistics for a support vector data description-based control chart are sufficiently defined. However, the control limits are not obvious because the procedure used to derive the control limit does not include a method for controlling the false alarm rate (i.e., Type I error rate), which clearly limits its use in process monitoring. In this study, we propose a new multivariate control chart based on a technique for optimal false alarm-controlled support vector data description, which minimizes the radius of a spherically shaped boundary so that it includes the normal data that are equal to an assigned constant value. By modifying this constant value, users can precisely control the proportion of abnormal data determined by the spherically shaped boundary, which equals the expected Type I error rate. We demonstrated the usefulness of the proposed charts in experiments with simulated data and real process data based on a thin film transistor-liquid crystal display.

AB - One-class classification plays a key role in the detection of outliers and abnormalities. Recently, several attempts have been made to extend the application of one-class classification techniques to statistical process control problems, where many of these one-class classification-based approaches have used a support vector data description algorithm. The monitoring statistics for a support vector data description-based control chart are sufficiently defined. However, the control limits are not obvious because the procedure used to derive the control limit does not include a method for controlling the false alarm rate (i.e., Type I error rate), which clearly limits its use in process monitoring. In this study, we propose a new multivariate control chart based on a technique for optimal false alarm-controlled support vector data description, which minimizes the radius of a spherically shaped boundary so that it includes the normal data that are equal to an assigned constant value. By modifying this constant value, users can precisely control the proportion of abnormal data determined by the spherically shaped boundary, which equals the expected Type I error rate. We demonstrated the usefulness of the proposed charts in experiments with simulated data and real process data based on a thin film transistor-liquid crystal display.

KW - Control chart

KW - Machine learning

KW - One-class classification

KW - Process control

KW - Support vector data description

UR - http://www.scopus.com/inward/record.url?scp=85032979858&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032979858&partnerID=8YFLogxK

U2 - 10.1016/j.jprocont.2017.10.012

DO - 10.1016/j.jprocont.2017.10.012

M3 - Article

AN - SCOPUS:85032979858

JO - Journal of Process Control

JF - Journal of Process Control

SN - 0959-1524

ER -