ARAN - Access to Research at NUI Galway

Analysis of the Effects of Unexpected Outliers in the Classification of Spectroscopy Data

ARAN - Access to Research at NUI Galway

Show simple item record

dc.contributor.author Glavin, Frank G. en
dc.contributor.author Madden, Michael G. en
dc.date.accessioned 2009-09-03T11:44:59Z en
dc.date.available 2009-09-03T11:44:59Z en
dc.date.issued 2009 en
dc.identifier.citation Glavin, F. G., & Madden, M. G. (2009). Analysis of the Effects of Unexpected Outliers in the Classifcation of Spectroscopy Data. Paper presented at the 20th Irish Conference on Artificial Intelligence and Cognitive Science en
dc.identifier.uri http://hdl.handle.net/10379/303 en
dc.description.abstract Multi-class classification algorithms are very widely used, but we argue that they are not always ideal from a theoretical perspective, because they assume all classes are characterised by the data, whereas in many applications, training data for some classes may be entirely absent, rare, or statistically unrepresentative. We evaluate one- sided classifiers as an alternative, since they assume that only one class (the target) is well characterised. We consider a task of identifying whether a substance contains a chlorinated solvent, based on its chemical spectrum. For this application, it is not really feasible to collect a statistically representative set of outliers, since that group may contain anything apart from the target chlorinated solvents. Using a new one-sided classification toolkit, we compare a One-Sided k-NN algorithm with two well- known binary classification algorithms, and conclude that the one-sided classier is more robust to unexpected outliers. en
dc.format application/pdf en
dc.language.iso en en
dc.subject One-Class en
dc.subject Support Vector Machine en
dc.subject Classification en
dc.subject One-Sided en
dc.subject k-Nearest Neighbour en
dc.subject Spectroscopy Analysis en
dc.subject.lcsh Spectrum analysis en
dc.subject.lcsh Support vector machines en
dc.subject.lcsh Classification en
dc.title Analysis of the Effects of Unexpected Outliers in the Classification of Spectroscopy Data en
dc.type Article en
dc.description.peer-reviewed peer-reviewed en

Files in this item

This item appears in the following Collection(s)

Show simple item record