14
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Insights into LSTM Fully Convolutional Networks for Time Series Classification

      Preprint
      , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Long Short Term Memory Fully Convolutional Neural Networks (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN) have shown to achieve state-of-the-art performance on the task of classifying time series signals on the old University of California-Riverside (UCR) time series repository. However, there has been no study on why LSTM-FCN and ALSTM-FCN perform well. In this paper, we perform a series of ablation tests (3627 experiments) on LSTM-FCN and ALSTM-FCN to provide a better understanding of the model and each of its sub-module. Results from the ablation tests on ALSTM-FCN and LSTM-FCN show that the these blocks perform better when applied in a conjoined manner. Two z-normalizing techniques, z-normalizing each sample independently and z-normalizing the whole dataset, are compared using a Wilcoxson signed-rank test to show a statistical difference in performance. In addition, we provide an understanding of the impact dimension shuffle has on LSTM-FCN by comparing its performance with LSTM-FCN when no dimension shuffle is applied. Finally, we demonstrate the performance of the LSTM-FCN when the LSTM block is replaced by a GRU, basic RNN, and Dense Block.

          Related collections

          Most cited references7

          • Record: found
          • Abstract: not found
          • Conference Proceedings: not found

          Squeeze-and-Excitation Networks

            Bookmark
            • Record: found
            • Abstract: not found
            • Conference Proceedings: not found

            Time series classification from scratch with deep neural networks: A strong baseline

              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              LSTM Fully Convolutional Networks for Time Series Classification

                Bookmark

                Author and article information

                Journal
                27 February 2019
                Article
                1902.10756
                67530036-8935-41f2-ba15-4c177ff5cd9b

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                History
                Custom metadata
                7 pages, 4 tables, 1 figure
                cs.LG stat.ML

                Machine learning,Artificial intelligence
                Machine learning, Artificial intelligence

                Comments

                Comment on this article