On Mini-Batch Training with Varying Length Time Series
This addresses a practical issue in time series recognition for applications with irregular data lengths, though it is an incremental improvement over existing normalization techniques.
The paper tackles the problem of training neural networks on time series data with varying lengths by proposing a novel normalization method using Dynamic Time Warping (DTW) to set fixed sizes while preserving dataset features, achieving competitive performance compared to 18 other methods on 11 datasets from the UCR Time Series Archive.
In real-world time series recognition applications, it is possible to have data with varying length patterns. However, when using artificial neural networks (ANN), it is standard practice to use fixed-sized mini-batches. To do this, time series data with varying lengths are typically normalized so that all the patterns are the same length. Normally, this is done using zero padding or truncation without much consideration. We propose a novel method of normalizing the lengths of the time series in a dataset by exploiting the dynamic matching ability of Dynamic Time Warping (DTW). In this way, the time series lengths in a dataset can be set to a fixed size while maintaining features typical to the dataset. In the experiments, all 11 datasets with varying length time series from the 2018 UCR Time Series Archive are used. We evaluate the proposed method by comparing it with 18 other length normalization methods on a Convolutional Neural Network (CNN), a Long-Short Term Memory network (LSTM), and a Bidirectional LSTM (BLSTM).