Nonlinear Forward Selection Component Analysis for Optical Emission Spectroscopy Wavelength Selection

Luca Puggini; Séan McLoone

doi:10.1109/ISSC.2016.7528446

Nonlinear Forward Selection Component Analysis for Optical Emission Spectroscopy Wavelength Selection

Luca Puggini, Séan McLoone

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

Semiconductor manufacturers are increasingly reliant on optical emission spectroscopy (OES) to source information on plasma characteristics and process change. However, OES data is characterized by high dimension and by highly correlated variables. This makes it difficult to interpret process behaviour using OES measurements. It is therefore desirable to obtain more compact representations of the data using dimensionality reduction techniques such as Forward Selection Component Analysis (FSCA). In this paper we investigate non-linear extensions of FSCA based on polynomial expansions and Extreme Learning Machines and show, through a combination of simulated examples and OES recordings from a semiconductor plasma etch process, that they can yield more compact representations that classical FSCA.

Original language	English
Title of host publication	2016 27th Irish Signals and Systems Conference, ISSC 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	6
ISBN (Electronic)	9781509034093
DOIs	https://doi.org/10.1109/ISSC.2016.7528446
Publication status	Published - 04 Aug 2016
Event	27th Irish Signals and Systems Conference, ISSC 2016 - Londonderry, United Kingdom Duration: 21 Jun 2016 → 22 Jun 2016

Conference

Conference	27th Irish Signals and Systems Conference, ISSC 2016
Country/Territory	United Kingdom
City	Londonderry
Period	21/06/2016 → 22/06/2016

ASJC Scopus subject areas

Signal Processing
Computer Networks and Communications
Electrical and Electronic Engineering

Access to Document

10.1109/ISSC.2016.7528446Licence: Unspecified

Cite this

@inproceedings{a55adc10f7684004bfc34817ce2db572,

title = "Nonlinear Forward Selection Component Analysis for Optical Emission Spectroscopy Wavelength Selection",

abstract = "Semiconductor manufacturers are increasingly reliant on optical emission spectroscopy (OES) to source information on plasma characteristics and process change. However, OES data is characterized by high dimension and by highly correlated variables. This makes it difficult to interpret process behaviour using OES measurements. It is therefore desirable to obtain more compact representations of the data using dimensionality reduction techniques such as Forward Selection Component Analysis (FSCA). In this paper we investigate non-linear extensions of FSCA based on polynomial expansions and Extreme Learning Machines and show, through a combination of simulated examples and OES recordings from a semiconductor plasma etch process, that they can yield more compact representations that classical FSCA.",

author = "Luca Puggini and S{\'e}an McLoone",

year = "2016",

month = aug,

day = "4",

doi = "10.1109/ISSC.2016.7528446",

language = "English",

booktitle = "2016 27th Irish Signals and Systems Conference, ISSC 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "27th Irish Signals and Systems Conference, ISSC 2016 ; Conference date: 21-06-2016 Through 22-06-2016",

}

Puggini, L & McLoone, S 2016, Nonlinear Forward Selection Component Analysis for Optical Emission Spectroscopy Wavelength Selection. in 2016 27th Irish Signals and Systems Conference, ISSC 2016., 7528446, Institute of Electrical and Electronics Engineers Inc., 27th Irish Signals and Systems Conference, ISSC 2016, Londonderry, United Kingdom, 21/06/2016. https://doi.org/10.1109/ISSC.2016.7528446

TY - GEN

T1 - Nonlinear Forward Selection Component Analysis for Optical Emission Spectroscopy Wavelength Selection

AU - Puggini, Luca

AU - McLoone, Séan

PY - 2016/8/4

Y1 - 2016/8/4

N2 - Semiconductor manufacturers are increasingly reliant on optical emission spectroscopy (OES) to source information on plasma characteristics and process change. However, OES data is characterized by high dimension and by highly correlated variables. This makes it difficult to interpret process behaviour using OES measurements. It is therefore desirable to obtain more compact representations of the data using dimensionality reduction techniques such as Forward Selection Component Analysis (FSCA). In this paper we investigate non-linear extensions of FSCA based on polynomial expansions and Extreme Learning Machines and show, through a combination of simulated examples and OES recordings from a semiconductor plasma etch process, that they can yield more compact representations that classical FSCA.

AB - Semiconductor manufacturers are increasingly reliant on optical emission spectroscopy (OES) to source information on plasma characteristics and process change. However, OES data is characterized by high dimension and by highly correlated variables. This makes it difficult to interpret process behaviour using OES measurements. It is therefore desirable to obtain more compact representations of the data using dimensionality reduction techniques such as Forward Selection Component Analysis (FSCA). In this paper we investigate non-linear extensions of FSCA based on polynomial expansions and Extreme Learning Machines and show, through a combination of simulated examples and OES recordings from a semiconductor plasma etch process, that they can yield more compact representations that classical FSCA.

UR - http://www.scopus.com/inward/record.url?scp=84992151487&partnerID=8YFLogxK

U2 - 10.1109/ISSC.2016.7528446

DO - 10.1109/ISSC.2016.7528446

M3 - Conference contribution

AN - SCOPUS:84992151487

BT - 2016 27th Irish Signals and Systems Conference, ISSC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 27th Irish Signals and Systems Conference, ISSC 2016

Y2 - 21 June 2016 through 22 June 2016

ER -

Nonlinear Forward Selection Component Analysis for Optical Emission Spectroscopy Wavelength Selection

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this