Conformal Wearable for Quantification of Dorsiflexion for a Hemiplegic Ankle Pair with Distinction by Machine Learning

Abstract

Dorsiflexion of the ankle serves a critical role for the functionality of gait with regards to both the swing phase and stance phase. Hemiparesis can adversely influence the ability to conduct dorsiflexion of the ankle. Inertial sensor systems have been successfully demonstrated for objectively quantifying the disparity of a hemiplegic limb pair, which can be readily visualized. The gyroscope signal provides a kinematic representation that is clinically recognizable. These achievements to visualize through inertial sensors and distinguish by machine learning classification constitute an advance for the progressive rehabilitation for the ability to dorsiflex a hemiplegic affected ankle relative to the unaffected ankle. Conformal wearable and wireless inertial sensor systems that are inherently flexible can be readily be mounted about the dorsum of the ankle for quantifying dorsiflexion of the ankle based on the gyroscope signal. Wireless access to Cloud computing enables a convenient and remote means for signal data storage. The signal data can be consolidated to a feature set for machine learning classification to distinguish between a hemiplegic affected ankle and unaffected ankle pair. Using a multilayer perceptron neural network considerable machine learning classification accuracy is attained for distinguishing between dorsiflexion for a hemiplegic affected ankle and unaffected ankle. The amalgamation of conformal wearables, Cloud computing access, and machine learning imply the opportunity to conduct at home therapy with highly augmented clinical acuity for an optimal rehabilitation experience.