Analysis of the Effect of Unexpected Outliers in the Classification of Spectroscopy Data
This addresses a practical issue in spectroscopy classification for chemical analysis, where collecting outlier data is infeasible, though it is incremental as it applies an existing one-sided approach to a specific domain.
The paper tackled the problem of multi-class classification being theoretically unsuited for tasks where some classes lack representative training data, by evaluating one-sided classifiers for identifying chlorinated solvents in spectroscopy data, finding that the one-sided k-NN algorithm is more robust to unexpected outliers compared to binary classifiers.
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 characterized 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 characterized. 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 \emph{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 classifier is more robust to unexpected outliers.