A Multiple Continuous Signal Alignment Algorithm with Gaussian Process Profiles and an Application to Paleoceanography
Aligning signals is essential for integrating fragmented knowledge in each signal or resolving signal classification problems. Motif finding, or profile analysis, is a preferred method for multiple signal alignments and can be classified into two categories, depending on whether the profile is constructive or latent. Existing methods in these categories have some limitations: constructive profiles are defined over finite sets and inferred latent profiles are often too abstract to represent the integrated information. Here we present a novel alignment method, the multiple continuous Signal Alignment algorithm with Gaussian Process Regression profiles (SA-GPR), which addresses the limitations of currently available methods. We present a novel stack construction algorithm as an example of our SA-GPR in the field of paleoceanography. Specifically, we create a dual-proxy stack of six high-resolution sediment cores from the Northeast Atlantic using alignments based on both radiocarbon age estimates and the oxygen isotope ratio of benthic foraminifera, which is a proxy for changes in global ice volume and deep-water temperature.