Time-Series Estimation from Randomly Time-Warped Observations

TL;DR

This paper introduces a simple, computationally efficient algorithm for estimating signals from large sets of randomly time-warped observations, demonstrated on streaming biomedical data.

Contribution

It presents a novel, low-cost method for signal estimation from warped observations when many samples are available.

Findings

Algorithm is computationally simple and scalable.

Effective on streaming biomedical signals.

Reduces computational burden compared to inverse-warping methods.

Abstract

We consider the problem of estimating a signal from its warped observations. Such estimation is commonly performed by altering the observations through some inverse-warping, or solving a computationally demanding optimization formulation. While these may be unavoidable if observations are few, when large amounts of warped observations are available, the cost of running such algorithms can be prohibitive. We consider the scenario where we have many observations, and propose a computationally simple algorithm for estimating the function of interest. We demonstrate the utility of the algorithm on streaming biomedical signals.