Improving Time Series Classification Algorithms Using Octave-Convolutional Layers

TL;DR

This paper introduces the use of Octave Convolutions in various CNN-based models to enhance univariate time series classification accuracy with minimal additional parameters.

Contribution

It demonstrates that replacing standard convolutions with OctConv layers improves performance across multiple CNN architectures for time series classification.

Findings

Significant accuracy improvements on benchmark datasets.

ALSTM-OctFCN matches top ensemble classifiers statistically.

Minimal increase in model complexity with improved results.

Abstract

Deep learning models utilizing convolution layers have achieved state-of-the-art performance on univariate time series classification tasks. In this work, we propose improving CNN based time series classifiers by utilizing Octave Convolutions (OctConv) to outperform themselves. These network architectures include Fully Convolutional Networks (FCN), Residual Neural Networks (ResNets), LSTM-Fully Convolutional Networks (LSTM-FCN), and Attention LSTM-Fully Convolutional Networks (ALSTM-FCN). The proposed layers significantly improve each of these models with minimally increased network parameters. In this paper, we experimentally show that by substituting convolutions with OctConv, we significantly improve accuracy for time series classification tasks for most of the benchmark datasets. In addition, the updated ALSTM-OctFCN performs statistically the same as the top two time series classifers, TS-CHIEF and HIVE-COTE (both ensemble models). To further explore the impact of the OctConv layers, we perform ablation tests of the augmented model compared to their base model.