A Novel Optimization-Based Convolution Neural Network to Estimate the Contribution of Sensory Inputs to Postural Stability During Quiet Standing

Adequate postural control is maintained by integrating signals from the visual, somatosensory, and vestibular systems. The purpose of this study is to propose a novel convolutional neural network (CNN)-based protocol that can evaluate the contributions of each sensory input for postural stability (calculated a sensory analysis index) using center of pressure (COP) signals in a quiet standing posture. Raw COP signals in the anterior/posterior and medial/lateral directions were extracted from 330 patients in a quiet standing with their eyes open for 20 seconds. The COP signals augmented using jittering and pooling techniques were transformed into the frequency domain. The sensory analysis indices were used as the output information from the deep learning models. A ResNet-50 CNN was combined with the k-nearest neighbor, random forest, and support vector machine classifiers for the training model. Additionally, a novel optimization process was proposed to include an encoding design variable that can group outputs into sub-classes along with hyperparameters. The results of optimization considering only hyperparameters showed low performance, with an accuracy of 55% or less and F-1 scores of 54% or less in all models. However, when optimization was performed using the encoding design variable, the performance was markedly increased in the CNN-classifier combined models (r = 0.975). These results suggest it is possible to evaluate the contribution of sensory inputs for postural stability using COP signals during a quiet standing. This study will facilitate the expanded dissemination of a system that can quantitatively evaluate the balance ability and rehabilitation progress of patients with dizziness.