Artifacts Mitigation in Sensors for Spasticity Assessment. (16th September 2020)

• Record Type: Journal Article
• Authors: Yalçın, Çağrı; Sam, Mathew; Bu, Yifeng; Amit, Moran; Skalsky, Andrew J.; Yip, Michael; Ng, Tse Nga; Garudadri, Harinath
• Other Names: Kim Woo Soo guestEditor.; Paik Jamie guestEditor.
• Is Part Of: Advanced intelligent systems. Volume 3:Number 3(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-09-16
• Subjects: artifact mitigations -- neural networks -- spasticity -- wearable sensors; Artificial intelligence -- Periodicals; Robotics -- Periodicals; Control theory -- Periodicals; 006.3
• DOI: 10.1002/aisy.202000106
• Languages: English
• ISSNs: 2640-4567

Abstract

Abstract : Spasticity is a pathological condition that can occur in people with neuromuscular disorders. Objective, repeatable metrics are needed for evaluation to provide appropriate treatment and to monitor patient condition. Herein, an instrumented bimodal glove with force and movement sensors for spasticity assessment is presented. To mitigate noise artifacts, machine learning techniques are used, specifically a multitask neural network, to calibrate the instrumented glove signals against the ground truth from sensors integrated in a robotic arm. The motorized robotic arm system offers adjustable resistance to simulate different levels of muscle stiffness in spasticity, and the sensors on the robot provide ground‐truth measurements of angular displacement and force applied during flexion and extension maneuvers. The robotic sensor measurements are used to train the instrumented glove data through multitask learning. After processing through the neural network, the Pearson correlation coefficients between the processed signals and the ground truth are above 0.92, demonstrating successful signal calibration and noise mitigation. Abstract : An instrument to augment spasticity assessment with objective metrics is presented. A programmable robotic arm provided the ground truth for the sensors on an instrumented glove worn by the clinician. A neural network was trained to mitigate noise in force and angular displacement and estimate power at different resistance levels, achieving a Pearson correlation of 0.92 with the ground truth.