Nonlinear projective filtering I: Application to real time series

TL;DR

This paper presents a nonlinear filtering method using locally linear phase space projections to reduce noise in real-time time series data, demonstrated through fetal electrocardiogram extraction.

Contribution

It introduces a novel nonlinear filtering technique based on phase space projections for real-time noise reduction in time series.

Findings

Effective noise reduction in real-time signals

Successful extraction of fetal ECG from abdominal recordings

Applicable to various real-time time series data

Abstract

We discuss applications of nonlinear filtering of time series by locally linear phase space projections. Noise can be reduced whenever the error due to the manifold approximation is smaller than the noise in the system. Examples include the real time extraction of the fetal electrocardiogram from abdominal recordings.