An empirical survey of data augmentation for time series classification with neural networks.

In recent times, deep artificial neural networks have achieved many successes in pattern recognition. Part of this success can be attributed to the reliance on big data to increase generalization. However, in the field of time series recognition, many datasets are often very small. One method of add...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Brian Kenji Iwana, Seiichi Uchida
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/f69abd8bbc574c12a7b980e739932adf
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f69abd8bbc574c12a7b980e739932adf
record_format	dspace
spelling	oai:doaj.org-article:f69abd8bbc574c12a7b980e739932adf2021-12-02T20:09:12ZAn empirical survey of data augmentation for time series classification with neural networks.1932-620310.1371/journal.pone.0254841https://doaj.org/article/f69abd8bbc574c12a7b980e739932adf2021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0254841https://doaj.org/toc/1932-6203In recent times, deep artificial neural networks have achieved many successes in pattern recognition. Part of this success can be attributed to the reliance on big data to increase generalization. However, in the field of time series recognition, many datasets are often very small. One method of addressing this problem is through the use of data augmentation. In this paper, we survey data augmentation techniques for time series and their application to time series classification with neural networks. We propose a taxonomy and outline the four families in time series data augmentation, including transformation-based methods, pattern mixing, generative models, and decomposition methods. Furthermore, we empirically evaluate 12 time series data augmentation methods on 128 time series classification datasets with six different types of neural networks. Through the results, we are able to analyze the characteristics, advantages and disadvantages, and recommendations of each data augmentation method. This survey aims to help in the selection of time series data augmentation for neural network applications.Brian Kenji IwanaSeiichi UchidaPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 7, p e0254841 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Brian Kenji Iwana Seiichi Uchida An empirical survey of data augmentation for time series classification with neural networks.
description	In recent times, deep artificial neural networks have achieved many successes in pattern recognition. Part of this success can be attributed to the reliance on big data to increase generalization. However, in the field of time series recognition, many datasets are often very small. One method of addressing this problem is through the use of data augmentation. In this paper, we survey data augmentation techniques for time series and their application to time series classification with neural networks. We propose a taxonomy and outline the four families in time series data augmentation, including transformation-based methods, pattern mixing, generative models, and decomposition methods. Furthermore, we empirically evaluate 12 time series data augmentation methods on 128 time series classification datasets with six different types of neural networks. Through the results, we are able to analyze the characteristics, advantages and disadvantages, and recommendations of each data augmentation method. This survey aims to help in the selection of time series data augmentation for neural network applications.
format	article
author	Brian Kenji Iwana Seiichi Uchida
author_facet	Brian Kenji Iwana Seiichi Uchida
author_sort	Brian Kenji Iwana
title	An empirical survey of data augmentation for time series classification with neural networks.
title_short	An empirical survey of data augmentation for time series classification with neural networks.
title_full	An empirical survey of data augmentation for time series classification with neural networks.
title_fullStr	An empirical survey of data augmentation for time series classification with neural networks.
title_full_unstemmed	An empirical survey of data augmentation for time series classification with neural networks.
title_sort	empirical survey of data augmentation for time series classification with neural networks.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/f69abd8bbc574c12a7b980e739932adf
work_keys_str_mv	AT briankenjiiwana anempiricalsurveyofdataaugmentationfortimeseriesclassificationwithneuralnetworks AT seiichiuchida anempiricalsurveyofdataaugmentationfortimeseriesclassificationwithneuralnetworks AT briankenjiiwana empiricalsurveyofdataaugmentationfortimeseriesclassificationwithneuralnetworks AT seiichiuchida empiricalsurveyofdataaugmentationfortimeseriesclassificationwithneuralnetworks
_version_	1718375159564337152

An empirical survey of data augmentation for time series classification with neural networks.

Ejemplares similares