Time Series Similarity Score Functions to Monitor and Interact with the Training and Denoising Process of a Time Series Diffusion Model applied to a Human Activity Recognition Dataset based on IMUs

TL;DR

This paper explores similarity score functions to monitor and improve the training of time series diffusion models for human activity recognition, reducing training epochs while maintaining classification accuracy.

Contribution

It introduces adapted similarity metrics for better monitoring and fine-tuning of diffusion model training on sensor data, enhancing efficiency.

Findings

Significantly reduced training epochs without loss of classification performance.

Adapted similarity metric improves monitoring of the diffusion process.

Optimized training process saves computational resources.

Abstract

Denoising diffusion probabilistic models are able to generate synthetic sensor signals. The training process of such a model is controlled by a loss function which measures the difference between the noise that was added in the forward process and the noise that was predicted by the diffusion model. This enables the generation of realistic data. However, the randomness within the process and the loss function itself makes it difficult to estimate the quality of the data. Therefore, we examine multiple similarity metrics and adapt an existing metric to overcome this issue by monitoring the training and synthetisation process using those metrics. The adapted metric can even be fine-tuned on the input data to comply with the requirements of an underlying classification task. We were able to significantly reduce the amount of training epochs without a performance reduction in the classification task. An optimized training process not only saves resources, but also reduces the time for training generative models.