CLeVer: a feature subset selection technique for multivariate time series

Authors:
Kiyoung Yang;Hyunjin Yoon;Cyrus Shahabi
Affiliations:
Computer Science Department, University of Southern California, Los Angeles, CA;Computer Science Department, University of Southern California, Los Angeles, CA;Computer Science Department, University of Southern California, Los Angeles, CA
Venue:
PAKDD'05 Proceedings of the 9th Pacific-Asia conference on Advances in Knowledge Discovery and Data Mining
Year:
2005

Citing 4
Cited 2

An introduction to variable and feature selection

The Journal of Machine Learning Research
Active feature selection using classes

PAKDD'03 Proceedings of the 7th Pacific-Asia conference on Advances in knowledge discovery and data mining
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)
Variable grouping in multivariate time series via correlation

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Classification of multivariate time series using two-dimensional singular value decomposition

Knowledge-Based Systems
A review on time series data mining

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Feature subset selection (FSS) is one of the data pre-processing techniques to identify a subset of the original features from a given dataset before performing any data mining tasks. We propose a novel FSS method for Multivariate Time Series (MTS) based on Common Principal Components, termed CLeVer. It utilizes the properties of the principal components to retain the correlation information among original features while traditional FSS techniques, such as Recursive Feature Elimination (RFE), may lose it. In order to evaluate the effectiveness of our selected subset of features, classification is employed as the target data mining task. Our experiments show that CLeVer outperforms RFE and Fisher Criterion by up to a factor of two in terms of classification accuracy, while requiring up to 2 orders of magnitude less processing time.