Output details
13 - Electrical and Electronic Engineering, Metallurgy and Materials
Queen's University Belfast
Max separation clustering for feature extraction from Optical Emission Spectroscopy Data
This paper describes a novel clustering algorithm for identifying distinctive features in correlated high-dimensional data sets. The algorithm is targeted at optical emission spectroscopy (OES) data from plasma etch processes used in the semiconductor industry as a means of summarising the dominant patterns which may serve as signatures for process monitoring and control applications. Following a successful pilot, Intel who co-sponsored the research with Enterprise Ireland, have licensed a software application incorporating the algorithm and this is currently being deployed in its fabrication facilities worldwide, Intel (Resracher in residence).