Integral Transforms from Finite Data: An Application of Gaussian Process Regression to Fourier Analysis

TL;DR

This paper introduces a Gaussian process regression method for estimating Fourier transforms from finite data without assuming periodicity or bandlimitedness, improving accuracy in spectral analysis.

Contribution

The paper presents a novel approach using Gaussian process regression to estimate Fourier transforms directly from finite data without traditional assumptions.

Findings

Sharper spectral density estimates in simulations

Effective in noise-free and noisy data

Validated on atmospheric CO2 and brain signals

Abstract

Computing accurate estimates of the Fourier transform of analog signals from discrete data points is important in many fields of science and engineering. The conventional approach of performing the discrete Fourier transform of the data implicitly assumes periodicity and bandlimitedness of the signal. In this paper, we use Gaussian process regression to estimate the Fourier transform (or any other integral transform) without making these assumptions. This is possible because the posterior expectation of Gaussian process regression maps a finite set of samples to a function defined on the whole real line, expressed as a linear combination of covariance functions. We estimate the covariance function from the data using an appropriately designed gradient ascent method that constrains the solution to a linear combination of tractable kernel functions. This procedure results in a posterior expectation of the analog signal whose Fourier transform can be obtained analytically by exploiting linearity. Our simulations show that the new method leads to sharper and more precise estimation of the spectral density both in noise-free and noise-corrupted signals. We further validate the method in two real-world applications: the analysis of the yearly fluctuation in atmospheric CO2 level and the analysis of the spectral content of brain signals.