Data Augmentation for Time Series Classification using Convolutional Neural Networks - Archive ouverte HAL Access content directly
Conference Papers Year :

Data Augmentation for Time Series Classification using Convolutional Neural Networks

(1, 2) , (3) , (1, 2)
1
2
3

Abstract

Time series classification has been around for decades in the data-mining and machine learning communities. In this paper, we investigate the use of convolutional neural networks (CNN) for time series classification. Such networks have been widely used in many domains like computer vision and speech recognition, but only a little for time series classification. We design a convolu-tional neural network that consists of two convolutional layers. One drawback with CNN is that they need a lot of training data to be efficient. We propose two ways to circumvent this problem: designing data-augmentation techniques and learning the network in a semi-supervised way using training time series from different datasets. These techniques are experimentally evaluated on a benchmark of time series datasets.
Fichier principal
Vignette du fichier
AALTD16_paper_9.pdf (1.12 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

halshs-01357973 , version 1 (30-08-2016)

Identifiers

  • HAL Id : halshs-01357973 , version 1

Cite

Arthur Le Guennec, Simon Malinowski, Romain Tavenard. Data Augmentation for Time Series Classification using Convolutional Neural Networks. ECML/PKDD Workshop on Advanced Analytics and Learning on Temporal Data, Sep 2016, Riva Del Garda, Italy. ⟨halshs-01357973⟩
7384 View
12449 Download

Share

Gmail Facebook Twitter LinkedIn More