Enhancing Activity Recognition After Stroke: Generative Adversarial Networks for Kinematic Data Augmentation

TL;DR

This paper demonstrates that using Conditional Generative Adversarial Networks to generate synthetic kinematic data significantly improves the accuracy of activity recognition models in stroke rehabilitation, enabling better patient monitoring and personalized therapy.

Contribution

The study introduces a novel application of cGANs for realistic data augmentation in stroke activity recognition, surpassing traditional methods in generating complex movement patterns.

Findings

Synthetic data increased classification accuracy from 66.1% to 80.0%.

Models trained with synthetic data better captured complex movement dynamics.

Enhanced data diversity improved model generalization for stroke activity recognition.

Abstract

The generalizability of machine learning (ML) models for wearable monitoring in stroke rehabilitation is often constrained by the limited scale and heterogeneity of available data. Data augmentation addresses this challenge by adding computationally derived data to real data to enrich the variability represented in the training set. Traditional augmentation methods, such as rotation, permutation, and time-warping, have shown some benefits in improving classifier performance, but often fail to produce realistic training examples. This study employs Conditional Generative Adversarial Networks (cGANs) to create synthetic kinematic data from a publicly available dataset, closely mimicking the experimentally measured reaching movements of stroke survivors. This approach not only captures the complex temporal dynamics and common movement patterns after stroke, but also significantly enhances the training dataset. By training deep learning models on both synthetic and experimental data, we enhanced task classification accuracy: models incorporating synthetic data attained an overall accuracy of 80.0%, significantly higher than the 66.1% seen in models trained solely with real data. These improvements allow for more precise task classification, offering clinicians the potential to monitor patient progress more accurately and tailor rehabilitation interventions more effectively.