Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative Teacher
This addresses the challenge of limited data for time series classification, which is a common issue in domains like healthcare or finance, though it is an incremental improvement over existing augmentation methods.
The authors tackled the problem of small time series classification datasets by proposing guided warping, a novel data augmentation method that deterministically warps sample patterns using Dynamic Time Warping and shapeDTW, and evaluated it on 85 UCR datasets with CNNs and RNNs, achieving improved performance.
Neural networks have become a powerful tool in pattern recognition and part of their success is due to generalization from using large datasets. However, unlike other domains, time series classification datasets are often small. In order to address this problem, we propose a novel time series data augmentation called guided warping. While many data augmentation methods are based on random transformations, guided warping exploits the element alignment properties of Dynamic Time Warping (DTW) and shapeDTW, a high-level DTW method based on shape descriptors, to deterministically warp sample patterns. In this way, the time series are mixed by warping the features of a sample pattern to match the time steps of a reference pattern. Furthermore, we introduce a discriminative teacher in order to serve as a directed reference for the guided warping. We evaluate the method on all 85 datasets in the 2015 UCR Time Series Archive with a deep convolutional neural network (CNN) and a recurrent neural network (RNN). The code with an easy to use implementation can be found at https://github.com/uchidalab/time_series_augmentation .