Prediction of the number of defects in image sensors by VM using equipment QC Data

Toshiya Okazaki, Kosuke Okusa, Kyo Yoshida

Research output: Contribution to journalArticlepeer-review

Abstract

This paper describes methods and evaluation results of predicting the number of defects in image sensors using equipment QC data. Virtual metrology (VM) models are mainly used for measurable values such as dimensions and electrical characteristics. Herein, to predict countable values, we used a regression tree and stepwise AIC for variable selection as well as the 'hockey-stick regression model' and generalized linear model for regression, instead of the partial least squares (PLS) regression. The results showed an improved prediction performance in comparison with the conventional method. This method can be used to predict other countable values such as defects or dust particles.

Original languageEnglish
Article number8839510
Pages (from-to)434-437
Number of pages4
JournalIEEE Transactions on Semiconductor Manufacturing
Volume32
Issue number4
DOIs
Publication statusPublished - Nov 2019

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Prediction of the number of defects in image sensors by VM using equipment QC Data'. Together they form a unique fingerprint.

Cite this