Assessing Low Back Movement with Motion Tape Sensor Data Through Deep Learning
🤖 AI Summary
This study addresses the challenges of remote, precise assessment of lower back movement, which are hindered by the high cost of sensors, data noise from wearable devices, and limited training samples. To overcome these limitations, the authors propose MT-AIM, a novel classification framework that integrates conditional generative modeling with kinematic joint feature prediction. Leveraging low-cost fabric-based Motion Tape sensors, the approach employs generative data augmentation to enhance action recognition performance under conditions of small datasets and high sensor noise. Evaluated on lower back motion classification tasks, MT-AIM achieves state-of-the-art accuracy, effectively bridging the gap between physiological sensing and biomechanical motion analysis.
Application Category
📝 Abstract
Back pain is a pervasive issue affecting a significant portion of the population, often worsened by certain movements of the lower back. Assessing these movements is important for helping clinicians prescribe appropriate physical therapy. However, it can be difficult to monitor patients’ movements remotely outside the clinic. High-fidelity data from motion capture sensors can be used to classify different movements, but these sensors are costly and impractical for use in free-living environments. Motion Tape (MT), a new fabric-based wearable sensor, addresses these issues by being low cost and portable. Despite these advantages, novelty and variability in sensor stability make the MT dataset small scale and inherent to noise. In this work, we propose the Motion-Tape Augmentation Inference Model (MT-AIM), a deep learning classification pipeline trained on MT data. In order to address the challenges of limited sample size and noise present within the MT dataset, MT-AIM leverages conditional generative models to generate synthetic MT data of a desired movement, as well as predicting joint kinematics as additional features. This combination of synthetic data generation and feature augmentation enables MT-AIM to achieve state-of-the-art accuracy in classifying lower back movements, bridging the gap between physiological sensing and movement analysis.
Problem
Research questions and friction points this paper is trying to address.
low back movement assessment
wearable sensor
remote monitoring
motion classification
noisy data
Innovation
Methods, ideas, or system contributions that make the work stand out.
Motion Tape
deep learning
conditional generative model
data augmentation
movement classification
🔎 Similar Papers
No similar papers found.
