Time–frequency time–space LSTM for robust classification of physiological signals

Abstract Automated analysis of physiological time series is utilized for many clinical applications in medicine and life sciences. Long short-term memory (LSTM) is a deep recurrent neural network architecture used for classification of time-series data. Here time–frequency and time–space properties...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor principal: Tuan D. Pham
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/388b4a827ec147799ddb5b88df51f304
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:388b4a827ec147799ddb5b88df51f304
record_format dspace
spelling oai:doaj.org-article:388b4a827ec147799ddb5b88df51f3042021-12-02T11:45:01ZTime–frequency time–space LSTM for robust classification of physiological signals10.1038/s41598-021-86432-72045-2322https://doaj.org/article/388b4a827ec147799ddb5b88df51f3042021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-86432-7https://doaj.org/toc/2045-2322Abstract Automated analysis of physiological time series is utilized for many clinical applications in medicine and life sciences. Long short-term memory (LSTM) is a deep recurrent neural network architecture used for classification of time-series data. Here time–frequency and time–space properties of time series are introduced as a robust tool for LSTM processing of long sequential data in physiology. Based on classification results obtained from two databases of sensor-induced physiological signals, the proposed approach has the potential for (1) achieving very high classification accuracy, (2) saving tremendous time for data learning, and (3) being cost-effective and user-comfortable for clinical trials by reducing multiple wearable sensors for data recording.Tuan D. PhamNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Tuan D. Pham
Time–frequency time–space LSTM for robust classification of physiological signals
description Abstract Automated analysis of physiological time series is utilized for many clinical applications in medicine and life sciences. Long short-term memory (LSTM) is a deep recurrent neural network architecture used for classification of time-series data. Here time–frequency and time–space properties of time series are introduced as a robust tool for LSTM processing of long sequential data in physiology. Based on classification results obtained from two databases of sensor-induced physiological signals, the proposed approach has the potential for (1) achieving very high classification accuracy, (2) saving tremendous time for data learning, and (3) being cost-effective and user-comfortable for clinical trials by reducing multiple wearable sensors for data recording.
format article
author Tuan D. Pham
author_facet Tuan D. Pham
author_sort Tuan D. Pham
title Time–frequency time–space LSTM for robust classification of physiological signals
title_short Time–frequency time–space LSTM for robust classification of physiological signals
title_full Time–frequency time–space LSTM for robust classification of physiological signals
title_fullStr Time–frequency time–space LSTM for robust classification of physiological signals
title_full_unstemmed Time–frequency time–space LSTM for robust classification of physiological signals
title_sort time–frequency time–space lstm for robust classification of physiological signals
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/388b4a827ec147799ddb5b88df51f304
work_keys_str_mv AT tuandpham timefrequencytimespacelstmforrobustclassificationofphysiologicalsignals
_version_ 1718395274085269504