Data Augmentation for Multivariate Time Series Classification: An Experimental Study

TL;DR

This study evaluates how various data augmentation techniques can improve multivariate time series classification accuracy, demonstrating significant gains on UCR datasets and emphasizing the importance of data diversity for effective modeling.

Contribution

It systematically explores and adapts data augmentation methods for multivariate time series classification, establishing a new benchmark and highlighting their impact on model performance.

Findings

Achieved accuracy improvements in 10 out of 13 datasets

Demonstrated the importance of diverse augmentation strategies

Highlighted the role of data augmentation in small datasets

Abstract

Our study investigates the impact of data augmentation on the performance of multivariate time series models, focusing on datasets from the UCR archive. Despite the limited size of these datasets, we achieved classification accuracy improvements in 10 out of 13 datasets using the Rocket and InceptionTime models. This highlights the essential role of sufficient data in training effective models, paralleling the advancements seen in computer vision. Our work delves into adapting and applying existing methods in innovative ways to the domain of multivariate time series classification. Our comprehensive exploration of these techniques sets a new standard for addressing data scarcity in time series analysis, emphasizing that diverse augmentation strategies are crucial for unlocking the potential of both traditional and deep learning models. Moreover, by meticulously analyzing and applying a variety of augmentation techniques, we demonstrate that strategic data enrichment can enhance model accuracy. This not only establishes a benchmark for future research in time series analysis but also underscores the importance of adopting varied augmentation approaches to improve model performance in the face of limited data availability.