Empirically derived basis functions for unsupervised classification of radial profile data
Date
2010
Authors
Pretty, David
Vega, J
Ochando, M A
Tabares, F L
Journal Title
Journal ISSN
Volume Title
Publisher
Elsevier
Abstract
We present an analysis of empirically derived basis vectors for feature detection in radial profile data. Our aim is to classify broad and peaked profiles using unsupervised techniques. Radial data often contains a continuum of profile shapes from broad to peaked, as such clustering methods may be unreliable. Previously, ad hoc heuristic measures had been used for classification of profiles from raw data (without tomographic reconstruction), which required significant manual inspection of the data. Here, we apply a singular value decomposition (SVD) to a training data matrix consisting of a concatenation of multichannel bolometry time series data from 103 TJ-H plasma discharges with good representation of the range of profiles. The second largest spatial basis vector (topo) has radial roots either side of the plasma centre, and can intuitively be interpreted as a peakedness perturbation. The inverted topo matrix can be used to process new data for automated profile classification. Finally, we show an application of this method using support vector machines to locate other signals related to the radiation profile.
Description
Keywords
Keywords: Basis functions; Basis vector; Clustering methods; Feature detection; Manual inspection; matrix; Multi-channel; Plasma discharge; Profile classification; Profile shapes; Radial profiles; SVD; Time-series data; Tomographic reconstruction; Training data; Un Profile classification; Support vector machine; SVD
Citation
Collections
Source
Fusion Engineering and Design
Type
Journal article
Book Title
Entity type
Access Statement
License Rights
DOI
10.1016/j.fusengdes.2010.01.020
Restricted until
2037-12-31