The Use of Gaussian Processes in System Identification

Abstract

Gaussian processes are used in machine learning to learn input-output mappings from observed data. Gaussian process regression is based on imposing a Gaussian process prior on the unknown regressor function and statistically conditioning it on the observed data. In system identification, Gaussian processes are used to form time series prediction models such as non-linear finite-impulse response (NFIR) models as well as non-linear autoregressive (NARX) models. Gaussian process state-space models (GPSS) can be used to learn the dynamic and measurement models for a state-space representation of the input-output data. Temporal and spatio-temporal Gaussian processes can be directly used to form regressor on the data in the time domain. The aim of this article is to briefly outline the main directions in system identification methods using Gaussian processes. KeywordsGaussian process regression, non-linear system identification, GP-NFIR model, GP-ARX model, GP-NOE model, Gaussian process state-space model, temporal Gaussian process, state-space Gaussian process arXiv:1907.06066v1 [stat.ML]

Remaining Useful Life Prediction using Gaussian Process Regression Model

“…Whereas the probability distribution describes random variables which are scalars or vectors, the GP as a stochastic process governs the properties of a function (Rasmussen & Williams, 2005). The GPR refers to a statistics based methodology where the Gaussian processes are used as prior models for the Bayesian regression functions that are fitted to the observed data (Särkkä, 2019). Given a set of observed data points, there is an infinite number of possible functions that can fit these points.…”