A Supervised Feature Subset Selection Technique for Multivariate Time Series

Feature subset selection (FSS) is a known technique to pre-process 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 Corona, a simple yet effective supervised feature subset selection technique for Multivariate Time Series (MTS). Traditional FSS techniques, such as Recursive Feature Elimination (RFE) and Fisher Criterion (FC), have been applied to MTS datasets, e.g., Brain Computer Interface (BCI) datasets. However, these techniques may lose the correlation information among MTS variables, since each variable is considered separately when an MTS item is vectorized before applying RFE and FC. Corona maintains the correlation information by utilizing the correlation coefficient matrix of each MTS item as features to be employed for SVM. Our exhaustive sets of experiments show that Corona consistently outperforms RFE and FC by up to 100% in terms of classification accuracy, and takes more than one order of magnitude less time than RFE and FC in terms of the overall processing time.