On the Performance of Deep Learning Models for Time Series Classification in Streaming

  1. Lara-Benítez, Pedro 1
  2. Manuel Carranza-García 1
  3. Francisco Martínez-Álvarez 2
  4. Riquelme, José C. 1
  1. 1 Universidad de Sevilla

    Universidad de Sevilla

    Sevilla, España

    ROR https://ror.org/03yxnpp24

  2. 2 Universidad Pablo de Olavide

    Universidad Pablo de Olavide

    Sevilla, España

    ROR https://ror.org/02z749649

15th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2020): Burgos, Spain ; September 2020
  1. Álvaro Herrero (coord.)
  2. Carlos Cambra (coord.)
  3. Daniel Urda (coord.)
  4. Javier Sedano (coord.)
  5. Héctor Quintián (coord.)
  6. Emilio Corchado (coord.)

Publisher: Springer Suiza

ISBN: 978-3-030-57801-5 978-3-030-57802-2

Year of publication: 2021

Pages: 144-154

Congress: International Conference on Soft Computing Models in Industrial and Environmental Applications SOCO (15. 2020. Burgos)

Type: Conference paper


Processing data streams arriving at high speed requires the development of models that can provide fast and accurate predictions. Although deep neural networks are the state-of-the-art for many machine learning tasks, their performance in real-time data streaming scenarios is a research area that has not yet been fully addressed. Nevertheless, there have been recent efforts to adapt complex deep learning models for streaming tasks by reducing their processing rate. The design of the asynchronous dual-pipeline deep learning framework allows to predict over incoming instances and update the model simultaneously using two separate layers. The aim of this work is to assess the performance of different types of deep architectures for data streaming classification using this framework. We evaluate models such as multi-layer perceptrons, recurrent, convolutional and temporal convolutional neural networks over several time-series datasets that are simulated as streams. The obtained results indicate that convolutional architectures achieve a higher performance in terms of accuracy and efficiency.