Max Separation Clustering for Feature Extraction From Optical Emission Spectroscopy Data

This paper proposes max separation clustering (MSC), a new non-hierarchical clustering method used for feature extraction from optical emission spectroscopy (OES) data for plasma etch process control applications. OES data is high dimensional and inherently highly redundant with the result that it i...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on semiconductor manufacturing 2011-11, Vol.24 (4), p.480-488
Main Authors: Flynn, B., McLoone, S.
Format: Article
Language:English
Subjects:
Applied sciences
Clustering
Clustering algorithms
Dry etching
Electronics
Exact sciences and technology
Feature extraction
max separation clustering
Metrology
Microelectronic fabrication (materials and surfaces technology)
non-hierarchical clustering
Optical emission spectroscopy
Plasma diagnostics
plasma etch
Plasma measurement
Plasmas
Recognition
Representations
Semiconductor electronics. Microelectronics. Optoelectronics. Solid state devices
semiconductor manufacturing
Semiconductors
Separation
Separation processes
Signal to noise ratio
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes max separation clustering (MSC), a new non-hierarchical clustering method used for feature extraction from optical emission spectroscopy (OES) data for plasma etch process control applications. OES data is high dimensional and inherently highly redundant with the result that it is difficult if not impossible to recognize useful features and key variables by direct visualization. MSC is developed for clustering variables with distinctive patterns and providing effective pattern representation by a small number of representative variables. The relationship between signal-to-noise ratio (SNR) and clustering performance is highlighted, leading to a requirement that low SNR signals be removed before applying MSC. Experimental results on industrial OES data show that MSC with low SNR signal removal produces effective summarization of the dominant patterns in the data.
ISSN:0894-6507
1558-2345
DOI:10.1109/TSM.2011.2158122