CLeVer : a Feature Subset Selection Technique for Multivariate Time Series ? ( Full Version )

Feature subset selection (FSS) is one of the techniques to preprocess the data before performing any data mining tasks, e.g., classification and clustering. FSS provides both cost-effective predictors and a better understanding of the underlying process that generated data. We propose a novel method of FSS for Multivariate Time Series (MTS) based on Common Principal Component Analysis, termed CLeVer. Traditional FSS techniques, such as Recursive Feature Elimination (RFE) and Fisher Criterion (FC), have been applied to MTS datasets, e.g., Electro Encephalogram (EEG) datasets. However, these techniques may lose the correlation information among features, while our proposed technique utilizes the properties of the principal component analysis to retain that information. In order to evaluate the effectiveness of our selected subset of features, we employ classification as the target data mining task. Our exhaustive sets of experiments show that CLeVer outperforms RFE and FC by up to 100% in terms of classification accuracy, while requiring significantly less processing time (up to 2 orders of magnitude) than RFE and FC.