Deep Neural Network Ensembles for Time Series Classification

Hassan Ismail Fawaz, Germain Forestier, Jonathan Weber, Lhassane Idoumghar, Pierre-Alain Muller
3/15/2019
cs.LGstat.ML

Official code: hfawaz/ijcnn19ensemble (112 stars, GPL-3.0, last commit 2023-08-31).

Abstract

Deep neural networks have revolutionized many fields such as computer vision and natural language processing. Inspired by this recent success, deep learning started to show promising results for Time Series Classification (TSC). However, neural networks are still behind the state-of-the-art TSC algorithms, that are currently composed of ensembles of 37 non deep learning based classifiers. We attribute this gap in performance due to the lack of neural network ensembles for TSC. Therefore in this paper, we show how an ensemble of 60 deep learning models can significantly improve upon the current state-of-the-art performance of neural networks for TSC, when evaluated over the UCR/UEA archive: the largest publicly available benchmark for time series analysis. Finally, we show how our proposed Neural Network Ensemble (NNE) is the first time series classifier to outperform COTE while reaching similar performance to the current state-of-the-art ensemble HIVE-COTE.

View on arXivView PDF

Code Implementations(1)

hfawaz/ijcnn19ensembleOfficial100%
GPL-3.0

Deep Neural Network Ensembles for Time Series Classification

11238PythonMar 7, 20193 years agoGPL-3.0
deep-learningdeep-neural-networksensembletime-series-classification

Similar Papers

InceptionTime: Finding AlexNet for Time Series Classification

88% match1 repo7542019

Deep learning for time series classification: a review

87% match1 repo1.7k2018

Deep Unsupervised Domain Adaptation for Time Series Classification: a Benchmark

87% match1 repo312023

Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline

87% match1 repo7192016

TSPP: A Unified Benchmarking Tool for Time-series Forecasting

85% match1 repo14.8k2023

Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures

85% match2022

Cite this paper

@article{fawaz2019deep,
  title  = {Deep Neural Network Ensembles for Time Series Classification},
  author = {Hassan Ismail Fawaz and Germain Forestier and Jonathan Weber and Lhassane Idoumghar and Pierre-Alain Muller},
  year   = {2019},
  eprint = {1903.06602},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1903.06602}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1903.06602.svg)](https://codeofpaper.com/paper/1903.06602)

Discussion