A versatile computational algorithm for time-series data analysis and machine-learning models

Abstract Here we introduce Local Topological Recurrence Analysis (LoTRA), a simple computational approach for analyzing time-series data. Its versatility is elucidated using simulated data, Parkinsonian gait, and in vivo brain dynamics. We also show that this algorithm can be used to build a remarka...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Taylor Chomiak, Neilen P. Rasiah, Leonardo A. Molina, Bin Hu, Jaideep S. Bains, Tamás Füzesi
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Neurology. Diseases of the nervous system RC346-429
Acceso en línea:	https://doaj.org/article/0d501efbd1784cc1a4ba7c35db5bc8dd
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0d501efbd1784cc1a4ba7c35db5bc8dd
record_format	dspace
spelling	oai:doaj.org-article:0d501efbd1784cc1a4ba7c35db5bc8dd2021-11-14T12:27:00ZA versatile computational algorithm for time-series data analysis and machine-learning models10.1038/s41531-021-00240-42373-8057https://doaj.org/article/0d501efbd1784cc1a4ba7c35db5bc8dd2021-11-01T00:00:00Zhttps://doi.org/10.1038/s41531-021-00240-4https://doaj.org/toc/2373-8057Abstract Here we introduce Local Topological Recurrence Analysis (LoTRA), a simple computational approach for analyzing time-series data. Its versatility is elucidated using simulated data, Parkinsonian gait, and in vivo brain dynamics. We also show that this algorithm can be used to build a remarkably simple machine-learning model capable of outperforming deep-learning models in detecting Parkinson’s disease from a single digital handwriting test.Taylor ChomiakNeilen P. RasiahLeonardo A. MolinaBin HuJaideep S. BainsTamás FüzesiNature PortfolioarticleNeurology. Diseases of the nervous systemRC346-429ENnpj Parkinson's Disease, Vol 7, Iss 1, Pp 1-6 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Neurology. Diseases of the nervous system RC346-429
spellingShingle	Neurology. Diseases of the nervous system RC346-429 Taylor Chomiak Neilen P. Rasiah Leonardo A. Molina Bin Hu Jaideep S. Bains Tamás Füzesi A versatile computational algorithm for time-series data analysis and machine-learning models
description	Abstract Here we introduce Local Topological Recurrence Analysis (LoTRA), a simple computational approach for analyzing time-series data. Its versatility is elucidated using simulated data, Parkinsonian gait, and in vivo brain dynamics. We also show that this algorithm can be used to build a remarkably simple machine-learning model capable of outperforming deep-learning models in detecting Parkinson’s disease from a single digital handwriting test.
format	article
author	Taylor Chomiak Neilen P. Rasiah Leonardo A. Molina Bin Hu Jaideep S. Bains Tamás Füzesi
author_facet	Taylor Chomiak Neilen P. Rasiah Leonardo A. Molina Bin Hu Jaideep S. Bains Tamás Füzesi
author_sort	Taylor Chomiak
title	A versatile computational algorithm for time-series data analysis and machine-learning models
title_short	A versatile computational algorithm for time-series data analysis and machine-learning models
title_full	A versatile computational algorithm for time-series data analysis and machine-learning models
title_fullStr	A versatile computational algorithm for time-series data analysis and machine-learning models
title_full_unstemmed	A versatile computational algorithm for time-series data analysis and machine-learning models
title_sort	versatile computational algorithm for time-series data analysis and machine-learning models
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/0d501efbd1784cc1a4ba7c35db5bc8dd
work_keys_str_mv	AT taylorchomiak aversatilecomputationalalgorithmfortimeseriesdataanalysisandmachinelearningmodels AT neilenprasiah aversatilecomputationalalgorithmfortimeseriesdataanalysisandmachinelearningmodels AT leonardoamolina aversatilecomputationalalgorithmfortimeseriesdataanalysisandmachinelearningmodels AT binhu aversatilecomputationalalgorithmfortimeseriesdataanalysisandmachinelearningmodels AT jaideepsbains aversatilecomputationalalgorithmfortimeseriesdataanalysisandmachinelearningmodels AT tamasfuzesi aversatilecomputationalalgorithmfortimeseriesdataanalysisandmachinelearningmodels AT taylorchomiak versatilecomputationalalgorithmfortimeseriesdataanalysisandmachinelearningmodels AT neilenprasiah versatilecomputationalalgorithmfortimeseriesdataanalysisandmachinelearningmodels AT leonardoamolina versatilecomputationalalgorithmfortimeseriesdataanalysisandmachinelearningmodels AT binhu versatilecomputationalalgorithmfortimeseriesdataanalysisandmachinelearningmodels AT jaideepsbains versatilecomputationalalgorithmfortimeseriesdataanalysisandmachinelearningmodels AT tamasfuzesi versatilecomputationalalgorithmfortimeseriesdataanalysisandmachinelearningmodels
_version_	1718429211096514560

A versatile computational algorithm for time-series data analysis and machine-learning models

Ejemplares similares