Efficient Classification via Partial Co-Training for Virtual Metrology

Conference Paper

Developing accurate and cost-effective classification techniques to facilitate virtual metrology is a critical task for modern manufacturing. In this paper, we consider the scenario in which labeling data is expensive, causing a shortage of labeled data. As a consequence, conventional classification methods suffer from a high risk of overfitting. To address this issue, we develop a novel semi-supervised classification method, namely Partial Cotraining with Logistic Regression (PCT-LR). PCT-LR finds a subset of the original features to generate a partial view, and uses this partial view to provide side information to support the complete view that includes all features. Both views are cooptimized in a Bayesian inference with a Gaussian process prior and a logistic regression classifier. The proposed method is validated with two industrial examples. Experiment results suggest that the amount of required labeled data can be reduced by up to 18% without loss in accuracy.

Full Text

Duke Authors

Cited Authors

  • Nguyen, C; Li, X; Blanton, S

Published Date

  • September 1, 2020

Published In

Volume / Issue

  • 2020-September /

Start / End Page

  • 753 - 760

Electronic International Standard Serial Number (EISSN)

  • 1946-0759

International Standard Serial Number (ISSN)

  • 1946-0740

International Standard Book Number 13 (ISBN-13)

  • 9781728189567

Digital Object Identifier (DOI)

  • 10.1109/ETFA46521.2020.9212012

Citation Source

  • Scopus