Robust Augmentation for Multivariate Time Series Classification
This addresses the problem of limited training data for researchers and practitioners in time series classification, but it is incremental as it applies existing augmentation methods to this domain.
The paper tackles overfitting in neural networks for multivariate time series classification, particularly with small datasets, by showing that simple augmentation methods like cutout and mixup improve robustness and performance, with accuracy gains of 1% to 45% on 18 datasets using InceptionTime.
Neural networks are capable of learning powerful representations of data, but they are susceptible to overfitting due to the number of parameters. This is particularly challenging in the domain of time series classification, where datasets may contain fewer than 100 training examples. In this paper, we show that the simple methods of cutout, cutmix, mixup, and window warp improve the robustness and overall performance in a statistically significant way for convolutional, recurrent, and self-attention based architectures for time series classification. We evaluate these methods on 26 datasets from the University of East Anglia Multivariate Time Series Classification (UEA MTSC) archive and analyze how these methods perform on different types of time series data.. We show that the InceptionTime network with augmentation improves accuracy by 1% to 45% in 18 different datasets compared to without augmentation. We also show that augmentation improves accuracy for recurrent and self attention based architectures.