IMUDiffusion: A Diffusion Model for Multivariate Time Series Synthetisation for Inertial Motion Capturing Systems

TL;DR

IMUDiffusion introduces a probabilistic diffusion model that generates realistic multivariate time series for human activity analysis, significantly improving classifier performance with synthetic data augmentation.

Contribution

The paper presents IMUDiffusion, a novel diffusion-based model for generating high-quality synthetic multivariate time series of human activities, enhancing data diversity and model robustness.

Findings

Synthetic data improves classifier macro F1-score by up to 30%.

IMUDiffusion accurately captures human activity dynamics.

Generated data enhances model performance in limited data scenarios.

Abstract

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.