Estimating Driving Forces of Nonstationary Time Series with Slow Feature Analysis

TL;DR

This paper demonstrates that Slow Feature Analysis (SFA) can effectively estimate the underlying driving force of nonstationary time series, even with complex signals like tent and logistic maps, achieving high accuracy.

Contribution

The paper introduces the novel application of SFA to nonstationary time series for accurate estimation of underlying driving forces.

Findings

SFA can extract slowly varying features from rapidly changing signals.

High accuracy in estimating underlying driving forces demonstrated with tent and logistic maps.

Method is robust to constant offsets and scaling factors.

Abstract

Slow feature analysis (SFA) is a new technique for extracting slowly varying features from a quickly varying signal. It is shown here that SFA can be applied to nonstationary time series to estimate a single underlying driving force with high accuracy up to a constant offset and a factor. Examples with a tent map and a logistic map illustrate the performance.