A semiconductor yields prediction using stepwise support vector machine

Daewoong An, Hyo Heon Ko, Turghun Gulambar, Jihyun Kim, Jun-Geol Baek, Sung Shick Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

It is crucial to prevent low yields in the semiconductor industry. Since many factors affect variation in yield and they are deeply related, preventing low yield is difficult. There have been substantial researches in the field of yield prediction. Many researchers had used statistical methods. Many studies have shown that artificial neural network (ANN) achieved better performance than traditional statistical methods. However, despite ANN's superior performance some problems such as over-fitting and poor explanatory power arise. In order to overcome these limitations, a relatively new machine learning technique, support vector machine (SVM), is introduced to classify the yield. SVM is simple enough to be analyzed mathematically, and it leads to high performances in practical applications. This study presents a new efficient classification methodology, Stepwise-SVM, for detecting high and low yields. Stepwise-SVM is a step-by-step adjustment of parameters to classify actual high and low yield lot precisely. The objective of this paper is to examine the feasibility of SVM and stepwise-SVM in the yield classification. The experimental results show that SVM and stepwise-SVM provides a promising alternative to yield classification for the field data.

Original languageEnglish
Title of host publication2009 IEEE International Symposium on Assembly and Manufacturing, ISAM 2009
Pages130-136
Number of pages7
DOIs
Publication statusPublished - 2009 Dec 1
Event2009 IEEE International Symposium on Assembly and Manufacturing, ISAM 2009 - Seoul, Korea, Republic of
Duration: 2009 Nov 172009 Nov 20

Other

Other2009 IEEE International Symposium on Assembly and Manufacturing, ISAM 2009
CountryKorea, Republic of
CitySeoul
Period09/11/1709/11/20

Fingerprint

Support vector machines
Semiconductor materials
Statistical methods
Learning systems
Neural networks
Industry

Keywords

  • Semiconductor manufacturing process
  • Semiconductor yield classification
  • Support vector machine

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering

Cite this

An, D., Ko, H. H., Gulambar, T., Kim, J., Baek, J-G., & Kim, S. S. (2009). A semiconductor yields prediction using stepwise support vector machine. In 2009 IEEE International Symposium on Assembly and Manufacturing, ISAM 2009 (pp. 130-136). [5376916] https://doi.org/10.1109/ISAM.2009.5376916

A semiconductor yields prediction using stepwise support vector machine. / An, Daewoong; Ko, Hyo Heon; Gulambar, Turghun; Kim, Jihyun; Baek, Jun-Geol; Kim, Sung Shick.

2009 IEEE International Symposium on Assembly and Manufacturing, ISAM 2009. 2009. p. 130-136 5376916.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

An, D, Ko, HH, Gulambar, T, Kim, J, Baek, J-G & Kim, SS 2009, A semiconductor yields prediction using stepwise support vector machine. in 2009 IEEE International Symposium on Assembly and Manufacturing, ISAM 2009., 5376916, pp. 130-136, 2009 IEEE International Symposium on Assembly and Manufacturing, ISAM 2009, Seoul, Korea, Republic of, 09/11/17. https://doi.org/10.1109/ISAM.2009.5376916
An D, Ko HH, Gulambar T, Kim J, Baek J-G, Kim SS. A semiconductor yields prediction using stepwise support vector machine. In 2009 IEEE International Symposium on Assembly and Manufacturing, ISAM 2009. 2009. p. 130-136. 5376916 https://doi.org/10.1109/ISAM.2009.5376916
An, Daewoong ; Ko, Hyo Heon ; Gulambar, Turghun ; Kim, Jihyun ; Baek, Jun-Geol ; Kim, Sung Shick. / A semiconductor yields prediction using stepwise support vector machine. 2009 IEEE International Symposium on Assembly and Manufacturing, ISAM 2009. 2009. pp. 130-136
@inproceedings{64ccb1cb8a424dec87460324fd287ae7,
title = "A semiconductor yields prediction using stepwise support vector machine",
abstract = "It is crucial to prevent low yields in the semiconductor industry. Since many factors affect variation in yield and they are deeply related, preventing low yield is difficult. There have been substantial researches in the field of yield prediction. Many researchers had used statistical methods. Many studies have shown that artificial neural network (ANN) achieved better performance than traditional statistical methods. However, despite ANN's superior performance some problems such as over-fitting and poor explanatory power arise. In order to overcome these limitations, a relatively new machine learning technique, support vector machine (SVM), is introduced to classify the yield. SVM is simple enough to be analyzed mathematically, and it leads to high performances in practical applications. This study presents a new efficient classification methodology, Stepwise-SVM, for detecting high and low yields. Stepwise-SVM is a step-by-step adjustment of parameters to classify actual high and low yield lot precisely. The objective of this paper is to examine the feasibility of SVM and stepwise-SVM in the yield classification. The experimental results show that SVM and stepwise-SVM provides a promising alternative to yield classification for the field data.",
keywords = "Semiconductor manufacturing process, Semiconductor yield classification, Support vector machine",
author = "Daewoong An and Ko, {Hyo Heon} and Turghun Gulambar and Jihyun Kim and Jun-Geol Baek and Kim, {Sung Shick}",
year = "2009",
month = "12",
day = "1",
doi = "10.1109/ISAM.2009.5376916",
language = "English",
isbn = "9781424446278",
pages = "130--136",
booktitle = "2009 IEEE International Symposium on Assembly and Manufacturing, ISAM 2009",

}

TY - GEN

T1 - A semiconductor yields prediction using stepwise support vector machine

AU - An, Daewoong

AU - Ko, Hyo Heon

AU - Gulambar, Turghun

AU - Kim, Jihyun

AU - Baek, Jun-Geol

AU - Kim, Sung Shick

PY - 2009/12/1

Y1 - 2009/12/1

N2 - It is crucial to prevent low yields in the semiconductor industry. Since many factors affect variation in yield and they are deeply related, preventing low yield is difficult. There have been substantial researches in the field of yield prediction. Many researchers had used statistical methods. Many studies have shown that artificial neural network (ANN) achieved better performance than traditional statistical methods. However, despite ANN's superior performance some problems such as over-fitting and poor explanatory power arise. In order to overcome these limitations, a relatively new machine learning technique, support vector machine (SVM), is introduced to classify the yield. SVM is simple enough to be analyzed mathematically, and it leads to high performances in practical applications. This study presents a new efficient classification methodology, Stepwise-SVM, for detecting high and low yields. Stepwise-SVM is a step-by-step adjustment of parameters to classify actual high and low yield lot precisely. The objective of this paper is to examine the feasibility of SVM and stepwise-SVM in the yield classification. The experimental results show that SVM and stepwise-SVM provides a promising alternative to yield classification for the field data.

AB - It is crucial to prevent low yields in the semiconductor industry. Since many factors affect variation in yield and they are deeply related, preventing low yield is difficult. There have been substantial researches in the field of yield prediction. Many researchers had used statistical methods. Many studies have shown that artificial neural network (ANN) achieved better performance than traditional statistical methods. However, despite ANN's superior performance some problems such as over-fitting and poor explanatory power arise. In order to overcome these limitations, a relatively new machine learning technique, support vector machine (SVM), is introduced to classify the yield. SVM is simple enough to be analyzed mathematically, and it leads to high performances in practical applications. This study presents a new efficient classification methodology, Stepwise-SVM, for detecting high and low yields. Stepwise-SVM is a step-by-step adjustment of parameters to classify actual high and low yield lot precisely. The objective of this paper is to examine the feasibility of SVM and stepwise-SVM in the yield classification. The experimental results show that SVM and stepwise-SVM provides a promising alternative to yield classification for the field data.

KW - Semiconductor manufacturing process

KW - Semiconductor yield classification

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=77949388943&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949388943&partnerID=8YFLogxK

U2 - 10.1109/ISAM.2009.5376916

DO - 10.1109/ISAM.2009.5376916

M3 - Conference contribution

AN - SCOPUS:77949388943

SN - 9781424446278

SP - 130

EP - 136

BT - 2009 IEEE International Symposium on Assembly and Manufacturing, ISAM 2009

ER -