AUTHOR=Tian Runfeng , Yang Yuan , van der Helm Frans C. T. , Dewald Julius P. A. 

TITLE=A Novel Approach for Modeling Neural Responses to Joint Perturbations Using the NARMAX Method and a Hierarchical Neural Network

JOURNAL=Frontiers in Computational Neuroscience

VOLUME=Volume 12 - 2018

YEAR=2018

URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2018.00096

DOI=10.3389/fncom.2018.00096

ISSN=1662-5188

ABSTRACT=The human nervous system is an ensemble of connected neuronal networks. Modeling and system identification of the human nervous system helps us understand how the brain processes sensory input and controls responses at the system level. This study aims to propose an advanced approach based on a hierarchical neural network and nonlinear system identification method to model neural activity in the nervous system in response to an external somatosensory input. The proposed approach incorporates basic concepts of Nonlinear AutoRegressive Moving Average Model with eXogenous input (NARMAX) and neural network to acknowledge nonlinear closed-loop neural interactions. Different from the commonly used non-parametric NARMAX method, the proposed approach replaced the polynomial nonlinear terms with a hierarchical neural network. The hierarchical neural network is built based on known neuroanatomical connections and corresponding transmission delays in neural pathways. The proposed method is applied to an experimental dataset, where cortical activities from ten young able-bodied individuals are extracted from electroencephalographic signals while applying a mechanical perturbation to their wrist joint. The results yielded by the proposed method were compared with those obtained by the non-parametric NARMAX and Volterra methods, evaluating by the variance accounted for (VAF). Both the proposed and non-parametric NARMAX methods yielded much better modeling results than the Volterra model. Furthermore, the proposed method modeled cortical responses with a mean VAF of 69.35% for a three-step ahead prediction, which is significantly better than non-parametric NARMAX (mean VAF 47.09%). This study provides a novel approach for precise modeling of cortical responses to sensory input. The results indicate that incorporation of the knowledge of neuroanatomical connections in building a realistic model will greatly improve the performance of system identification of the human nervous system.