A novel clustering and declustering algorithm for fuzzy classification of wafer defects

Tarek A. El Doker, David R Scott

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

4 Citations (Scopus)

Abstract

A method has been developed for enhancing the efficiency and accuracy of wafer defect analysis for yield improvement. This multi-step fuzzy algorithm has been developed for automatic clustering and classification of wafer defects. The algorithm utilizes a combination of new and existing feature measurements to identify and match defects with those referenced in a defect classes library. The process is more efficient than other approaches like pair-wise K-Nearest Neighbor (K-NN) classifiers and other fuzzy methods, which can be computationally very expensive. The algorithm also offers improved accuracy and the ability to decluster defects in cases where more than one overlap.

Original languageEnglish (US)
Title of host publicationBiennial University/Government/Industry Microelectronics Symposium - Proceedings
Pages103-106
Number of pages4
StatePublished - 2003
Event15th Biennial University/Government/Industry Microelectronics Symposium - Boise, ID, United States
Duration: Jun 30 2003Jul 2 2003

Other

Other15th Biennial University/Government/Industry Microelectronics Symposium
CountryUnited States
CityBoise, ID
Period6/30/037/2/03

Fingerprint

Defects
Classifiers

ASJC Scopus subject areas

  • Media Technology
  • Electrical and Electronic Engineering

Cite this

El Doker, T. A., & Scott, D. R. (2003). A novel clustering and declustering algorithm for fuzzy classification of wafer defects. In Biennial University/Government/Industry Microelectronics Symposium - Proceedings (pp. 103-106)

A novel clustering and declustering algorithm for fuzzy classification of wafer defects. / El Doker, Tarek A.; Scott, David R.

Biennial University/Government/Industry Microelectronics Symposium - Proceedings. 2003. p. 103-106.

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

El Doker, TA & Scott, DR 2003, A novel clustering and declustering algorithm for fuzzy classification of wafer defects. in Biennial University/Government/Industry Microelectronics Symposium - Proceedings. pp. 103-106, 15th Biennial University/Government/Industry Microelectronics Symposium, Boise, ID, United States, 6/30/03.
El Doker TA, Scott DR. A novel clustering and declustering algorithm for fuzzy classification of wafer defects. In Biennial University/Government/Industry Microelectronics Symposium - Proceedings. 2003. p. 103-106
El Doker, Tarek A. ; Scott, David R. / A novel clustering and declustering algorithm for fuzzy classification of wafer defects. Biennial University/Government/Industry Microelectronics Symposium - Proceedings. 2003. pp. 103-106
@inproceedings{1f0d4927a45842f285552e46333bd0b8,
title = "A novel clustering and declustering algorithm for fuzzy classification of wafer defects",
abstract = "A method has been developed for enhancing the efficiency and accuracy of wafer defect analysis for yield improvement. This multi-step fuzzy algorithm has been developed for automatic clustering and classification of wafer defects. The algorithm utilizes a combination of new and existing feature measurements to identify and match defects with those referenced in a defect classes library. The process is more efficient than other approaches like pair-wise K-Nearest Neighbor (K-NN) classifiers and other fuzzy methods, which can be computationally very expensive. The algorithm also offers improved accuracy and the ability to decluster defects in cases where more than one overlap.",
author = "{El Doker}, {Tarek A.} and Scott, {David R}",
year = "2003",
language = "English (US)",
pages = "103--106",
booktitle = "Biennial University/Government/Industry Microelectronics Symposium - Proceedings",

}

TY - GEN

T1 - A novel clustering and declustering algorithm for fuzzy classification of wafer defects

AU - El Doker, Tarek A.

AU - Scott, David R

PY - 2003

Y1 - 2003

N2 - A method has been developed for enhancing the efficiency and accuracy of wafer defect analysis for yield improvement. This multi-step fuzzy algorithm has been developed for automatic clustering and classification of wafer defects. The algorithm utilizes a combination of new and existing feature measurements to identify and match defects with those referenced in a defect classes library. The process is more efficient than other approaches like pair-wise K-Nearest Neighbor (K-NN) classifiers and other fuzzy methods, which can be computationally very expensive. The algorithm also offers improved accuracy and the ability to decluster defects in cases where more than one overlap.

AB - A method has been developed for enhancing the efficiency and accuracy of wafer defect analysis for yield improvement. This multi-step fuzzy algorithm has been developed for automatic clustering and classification of wafer defects. The algorithm utilizes a combination of new and existing feature measurements to identify and match defects with those referenced in a defect classes library. The process is more efficient than other approaches like pair-wise K-Nearest Neighbor (K-NN) classifiers and other fuzzy methods, which can be computationally very expensive. The algorithm also offers improved accuracy and the ability to decluster defects in cases where more than one overlap.

UR - http://www.scopus.com/inward/record.url?scp=0041940131&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0041940131&partnerID=8YFLogxK

M3 - Conference contribution

SP - 103

EP - 106

BT - Biennial University/Government/Industry Microelectronics Symposium - Proceedings

ER -