Virtual metrology modeling of time-dependent spectroscopic signals by a fused lasso algorithm

Chanhee Park, Seoung Bum Kim

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

This paper proposes a fused lasso model to identify significant features in the spectroscopic signals obtained from a semiconductor manufacturing process, and to construct a reliable virtual metrology (VM) model. Analysis of spectroscopic signals involves combinations of multiple samples collected over time, each with a vast number of highly correlated features. This leads to enormous amounts of data, which is a challenge even for modern-day computers to handle. To simplify such complex spectroscopic signals, dimension reduction is critical. The fused lasso is a regularized regression method that performs automatic variable selection for the predictive modeling of highly correlated datasets such as those of spectroscopic signals. Furthermore, the fused lasso is especially useful for analyzing high-dimensional data in which the features exhibit a natural order, as is the case in spectroscopic signals. In this paper, we conducted an experimental study to demonstrate the usefulness of a fused lasso-based VM model and compared it with other VM models based on the lasso and elastic-net models. The results showed that the VM model constructed with features selected by the fused lasso algorithm yields more accurate and robust predictions than the lasso- and elastic net-based VM models. To the best of our knowledge, ours is the first attempt to apply a fused lasso to VM modeling.

Original languageEnglish
Pages (from-to)51-58
Number of pages8
JournalJournal of Process Control
Volume42
DOIs
Publication statusPublished - 2016 Jun 1

Fingerprint

Lasso
Metrology
Modeling
Elastic Net
Model
Predictive Modeling
Semiconductor Manufacturing
Dimension Reduction
High-dimensional Data
Variable Selection
Experimental Study
Simplify
Semiconductor materials
Regression
Model-based
Prediction

Keywords

  • Feature selection
  • Fused lasso
  • Plasma etch
  • Predictive model
  • Spectroscopic signal
  • Virtual metrology

ASJC Scopus subject areas

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

Cite this

Virtual metrology modeling of time-dependent spectroscopic signals by a fused lasso algorithm. / Park, Chanhee; Kim, Seoung Bum.

In: Journal of Process Control, Vol. 42, 01.06.2016, p. 51-58.

Research output: Contribution to journalArticle

@article{c10cd8836227429e92f6edfacd960c01,
title = "Virtual metrology modeling of time-dependent spectroscopic signals by a fused lasso algorithm",
abstract = "This paper proposes a fused lasso model to identify significant features in the spectroscopic signals obtained from a semiconductor manufacturing process, and to construct a reliable virtual metrology (VM) model. Analysis of spectroscopic signals involves combinations of multiple samples collected over time, each with a vast number of highly correlated features. This leads to enormous amounts of data, which is a challenge even for modern-day computers to handle. To simplify such complex spectroscopic signals, dimension reduction is critical. The fused lasso is a regularized regression method that performs automatic variable selection for the predictive modeling of highly correlated datasets such as those of spectroscopic signals. Furthermore, the fused lasso is especially useful for analyzing high-dimensional data in which the features exhibit a natural order, as is the case in spectroscopic signals. In this paper, we conducted an experimental study to demonstrate the usefulness of a fused lasso-based VM model and compared it with other VM models based on the lasso and elastic-net models. The results showed that the VM model constructed with features selected by the fused lasso algorithm yields more accurate and robust predictions than the lasso- and elastic net-based VM models. To the best of our knowledge, ours is the first attempt to apply a fused lasso to VM modeling.",
keywords = "Feature selection, Fused lasso, Plasma etch, Predictive model, Spectroscopic signal, Virtual metrology",
author = "Chanhee Park and Kim, {Seoung Bum}",
year = "2016",
month = "6",
day = "1",
doi = "10.1016/j.jprocont.2016.04.002",
language = "English",
volume = "42",
pages = "51--58",
journal = "Journal of Process Control",
issn = "0959-1524",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Virtual metrology modeling of time-dependent spectroscopic signals by a fused lasso algorithm

AU - Park, Chanhee

AU - Kim, Seoung Bum

PY - 2016/6/1

Y1 - 2016/6/1

N2 - This paper proposes a fused lasso model to identify significant features in the spectroscopic signals obtained from a semiconductor manufacturing process, and to construct a reliable virtual metrology (VM) model. Analysis of spectroscopic signals involves combinations of multiple samples collected over time, each with a vast number of highly correlated features. This leads to enormous amounts of data, which is a challenge even for modern-day computers to handle. To simplify such complex spectroscopic signals, dimension reduction is critical. The fused lasso is a regularized regression method that performs automatic variable selection for the predictive modeling of highly correlated datasets such as those of spectroscopic signals. Furthermore, the fused lasso is especially useful for analyzing high-dimensional data in which the features exhibit a natural order, as is the case in spectroscopic signals. In this paper, we conducted an experimental study to demonstrate the usefulness of a fused lasso-based VM model and compared it with other VM models based on the lasso and elastic-net models. The results showed that the VM model constructed with features selected by the fused lasso algorithm yields more accurate and robust predictions than the lasso- and elastic net-based VM models. To the best of our knowledge, ours is the first attempt to apply a fused lasso to VM modeling.

AB - This paper proposes a fused lasso model to identify significant features in the spectroscopic signals obtained from a semiconductor manufacturing process, and to construct a reliable virtual metrology (VM) model. Analysis of spectroscopic signals involves combinations of multiple samples collected over time, each with a vast number of highly correlated features. This leads to enormous amounts of data, which is a challenge even for modern-day computers to handle. To simplify such complex spectroscopic signals, dimension reduction is critical. The fused lasso is a regularized regression method that performs automatic variable selection for the predictive modeling of highly correlated datasets such as those of spectroscopic signals. Furthermore, the fused lasso is especially useful for analyzing high-dimensional data in which the features exhibit a natural order, as is the case in spectroscopic signals. In this paper, we conducted an experimental study to demonstrate the usefulness of a fused lasso-based VM model and compared it with other VM models based on the lasso and elastic-net models. The results showed that the VM model constructed with features selected by the fused lasso algorithm yields more accurate and robust predictions than the lasso- and elastic net-based VM models. To the best of our knowledge, ours is the first attempt to apply a fused lasso to VM modeling.

KW - Feature selection

KW - Fused lasso

KW - Plasma etch

KW - Predictive model

KW - Spectroscopic signal

KW - Virtual metrology

UR - http://www.scopus.com/inward/record.url?scp=84963541945&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963541945&partnerID=8YFLogxK

U2 - 10.1016/j.jprocont.2016.04.002

DO - 10.1016/j.jprocont.2016.04.002

M3 - Article

AN - SCOPUS:84963541945

VL - 42

SP - 51

EP - 58

JO - Journal of Process Control

JF - Journal of Process Control

SN - 0959-1524

ER -