Regularized Bilinear Discriminant Analysis for Multivariate Time Series Data

TL;DR

This paper introduces a regularized bilinear discriminant analysis method tailored for multivariate time series data, addressing singularity issues and demonstrating superior classification performance over existing methods.

Contribution

It proposes RBLDA with regularization for MTS data, providing an efficient implementation and model selection algorithm, and compares its effectiveness against RLDA and BLDA.

Findings

RBLDA outperforms RLDA and BLDA in classification accuracy.

The proposed model selection algorithm is computationally efficient.

RBLDA offers improved visualization of MTS data.

Abstract

In recent years, the methods on matrix-based or bilinear discriminant analysis (BLDA) have received much attention. Despite their advantages, it has been reported that the traditional vector-based regularized LDA (RLDA) is still quite competitive and could outperform BLDA on some benchmark datasets. Nevertheless, it is also noted that this finding is mainly limited to image data. In this paper, we propose regularized BLDA (RBLDA) and further explore the comparison between RLDA and RBLDA on another type of matrix data, namely multivariate time series (MTS). Unlike image data, MTS typically consists of multiple variables measured at different time points. Although many methods for MTS data classification exist within the literature, there is relatively little work in exploring the matrix data structure of MTS data. Moreover, the existing BLDA can not be performed when one of its within-class matrices is singular. To address the two problems, we propose RBLDA for MTS data classification, where each of the two within-class matrices is regularized via one parameter. We develop an efficient implementation of RBLDA and an efficient model selection algorithm with which the cross validation procedure for RBLDA can be performed efficiently. Experiments on a number of real MTS data sets are conducted to evaluate the proposed algorithm and compare RBLDA with several closely related methods, including RLDA and BLDA. The results reveal that RBLDA achieves the best overall recognition performance and the proposed model selection algorithm is efficient; Moreover, RBLDA can produce better visualization of MTS data than RLDA.