Autoregressive models for biomedical signal processing
This work addresses the issue of biased signal processing for researchers in computational neuroscience and biomedical engineering, offering a new paradigm for applications like brain-computer interfaces and epilepsy studies.
The authors tackled the problem of biased autoregressive model estimators in biomedical signal processing due to measurement errors and model uncertainties, by presenting a framework with an overparameterised loss function and an alternating optimization algorithm, resulting in successful denoising and parameter reconstruction.
Autoregressive models are ubiquitous tools for the analysis of time series in many domains such as computational neuroscience and biomedical engineering. In these domains, data is, for example, collected from measurements of brain activity. Crucially, this data is subject to measurement errors as well as uncertainties in the underlying system model. As a result, standard signal processing using autoregressive model estimators may be biased. We present a framework for autoregressive modelling that incorporates these uncertainties explicitly via an overparameterised loss function. To optimise this loss, we derive an algorithm that alternates between state and parameter estimation. Our work shows that the procedure is able to successfully denoise time series and successfully reconstruct system parameters. This new paradigm can be used in a multitude of applications in neuroscience such as brain-computer interface data analysis and better understanding of brain dynamics in diseases such as epilepsy.