Extracting online information from dual and multiple data streams

Abstract

In this paper, we consider the challenging problem of finding shared information in multiple data streams simultaneously. The standard statistical method for doing this is the well-known canonical correlation analysis (CCA) approach. We begin by developing an online version of the CCA and apply it to reservoirs of an echo state network in order to capture shared temporal information in two data streams. We further develop the proposed method by forcing it to ignore shared information that is created from static values using derivative information. We finally develop a novel multi-set CCA method which can identify shared information in more than two data streams simultaneously. The comparative effectiveness of the proposed methods is illustrated using artificial and real benchmark datasets.