Derivative Estimation from Coarse, Irregular, Noisy Samples: An MLE-Spline Approach

TL;DR

This paper proposes a spline-based maximum-likelihood estimator for numerical differentiation from coarse, irregular, noisy samples, offering improved accuracy and computational efficiency over existing methods.

Contribution

It introduces a novel spline parameterization and recursive algorithms for derivative estimation under challenging sampling conditions.

Findings

Outperforms high-gain observers and super-twisting differentiators in noisy, coarse sampling scenarios.

Provides a flexible tradeoff between smoothness and computational speed.

Demonstrates effectiveness through simulations in practical systems.

Abstract

We address numerical differentiation under coarse, non-uniform sampling and Gaussian noise. A maximum-likelihood estimator with $L_2$-norm constraint on a higher-order derivative is obtained, yielding spline-based solution. We introduce a non-standard parameterization of quadratic splines and develop recursive online algorithms. Two formulations -- quadratic and zero-order -- offer tradeoff between smoothness and computational speed. Simulations demonstrate superior performance over high-gain observers and super-twisting differentiators under coarse sampling and high noise, benefiting systems where higher sampling rates are impractical.