Pattern Localization in Time Series through Signal-To-Model Alignment in Latent Space

TL;DR

This paper introduces a machine learning-based method for accurately locating predefined patterns in time series data by aligning signals in a learned latent space, improving over existing techniques.

Contribution

The authors propose a novel latent space mapping approach that enhances pattern localization accuracy in time series, outperforming current methods.

Findings

Significant improvement over state-of-the-art in non-destructive testing data

Effective latent space mapping enhances pattern alignment accuracy

Method demonstrates robustness across different datasets

Abstract

In this paper, we study the problem of locating a predefined sequence of patterns in a time series. In particular, the studied scenario assumes a theoretical model is available that contains the expected locations of the patterns. This problem is found in several contexts, and it is commonly solved by first synthesizing a time series from the model, and then aligning it to the true time series through dynamic time warping. We propose a technique that increases the similarity of both time series before aligning them, by mapping them into a latent correlation space. The mapping is learned from the data through a machine-learning setup. Experiments on data from non-destructive testing demonstrate that the proposed approach shows significant improvements over the state of the art.