LSTM Fully Convolutional Networks for Time Series Classification

TL;DR

This paper introduces LSTM-FCN and ALSTM-FCN models that combine convolutional networks with LSTM and attention mechanisms, significantly improving time series classification accuracy with minimal preprocessing.

Contribution

The paper presents novel LSTM-FCN and ALSTM-FCN models that enhance fully convolutional networks for time series classification, incorporating attention and fine-tuning techniques.

Findings

LSTM-FCN achieves state-of-the-art accuracy.

Attention mechanism improves model interpretability.

Fine-tuning further enhances performance.

Abstract

Fully convolutional neural networks (FCN) have been shown to achieve state-of-the-art performance on the task of classifying time series sequences. We propose the augmentation of fully convolutional networks with long short term memory recurrent neural network (LSTM RNN) sub-modules for time series classification. Our proposed models significantly enhance the performance of fully convolutional networks with a nominal increase in model size and require minimal preprocessing of the dataset. The proposed Long Short Term Memory Fully Convolutional Network (LSTM-FCN) achieves state-of-the-art performance compared to others. We also explore the usage of attention mechanism to improve time series classification with the Attention Long Short Term Memory Fully Convolutional Network (ALSTM-FCN). Utilization of the attention mechanism allows one to visualize the decision process of the LSTM cell. Furthermore, we propose fine-tuning as a method to enhance the performance of trained models. An overall analysis of the performance of our model is provided and compared to other techniques.