Convolutional Neural Networks for Time-dependent Classification of Variable-length Time Series

TL;DR

This paper introduces Adaptive Multi-scale Pooling and Temporal Encoding to improve classification of variable-length, time-dependent time series data, especially for short partial observations, using convolutional neural networks.

Contribution

It proposes novel modules that adaptively aggregate features and embed timestamps, addressing length variability and temporal information in time series classification.

Findings

Improved accuracy on short, partial time series data.

Effective handling of variable-length time series.

Enhanced convolutional neural network performance.

Abstract

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.