Convolutional Neural Networks for Time-dependent Classification of Variable-length Time Series
This work addresses classification challenges for partial time series data, which is incremental by building on existing CNN methods with adaptive pooling and timestamp encoding.
The paper tackled the problem of classifying variable-length partial time series by addressing trade-offs in temporal correlations and feature collapse, and introduced Adaptive Multi-scale Pooling and Temporal Encoding to improve accuracy, especially on short data, as shown in experiments on private and public datasets.
Time series data are often obtained only within a limited time range due to interruptions during observation process. To classify such partial time series, we need to account for 1) the variable-length data drawn from 2) different timestamps. To address the first problem, existing convolutional neural networks use global pooling after convolutional layers to cancel the length differences. This architecture suffers from the trade-off between incorporating entire temporal correlations in long data and avoiding feature collapse for short data. To resolve this tradeoff, we propose Adaptive Multi-scale Pooling, which aggregates features from an adaptive number of layers, i.e., only the first few layers for short data and more layers for long data. Furthermore, to address the second problem, we introduce Temporal Encoding, which embeds the observation timestamps into the intermediate features. Experiments on our private dataset and the UCR/UEA time series archive show that our modules improve classification accuracy especially on short data obtained as partial time series.