IMUDiffusion: A Diffusion Model for Multivariate Time Series Synthetisation for Inertial Motion Capturing Systems
This work addresses data scarcity issues for researchers and practitioners in sports and daily activity monitoring using inertial sensors, offering an incremental improvement through synthetic data generation.
The paper tackled the problem of limited and costly labeled motion data for human activity recognition by proposing IMUDiffusion, a diffusion model for generating synthetic multivariate time series, which improved a baseline classifier's macro F1-score by almost 30% in some cases.
Kinematic sensors are often used to analyze movement behaviors in sports and daily activities due to their ease of use and lack of spatial restrictions, unlike video-based motion capturing systems. Still, the generation, and especially the labeling of motion data for specific activities can be time-consuming and costly. Additionally, many models struggle with limited data, which limits their performance in recognizing complex movement patterns. To address those issues, generating synthetic data can help expand the diversity and variability. In this work, we propose IMUDiffusion, a probabilistic diffusion model specifically designed for multivariate time series generation. Our approach enables the generation of high-quality time series sequences which accurately capture the dynamics of human activities. Moreover, by joining our dataset with synthetic data, we achieve a significant improvement in the performance of our baseline human activity classifier. In some cases, we are able to improve the macro F1-score by almost 30%. IMUDiffusion provides a valuable tool for generating realistic human activity movements and enhance the robustness of models in scenarios with limited training data.