Self-Attention-Guided Recurrent Neural Network and Motion Perception for Intelligent Prediction of Chronic Diseases

Parkinson’s disease is a common chronic disease that affects a large number of people. In the real world, however, Parkinson’s disease can result in a loss of physical performance, which is classified as a movement disorder by clinicians. Parkinson’s disease is currently diagnosed primarily through...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Baojuan Ma, Fengyan Zhang, Baoling Ma
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Medicine (General) R5-920 Medical technology R855-855.5
Acceso en línea:	https://doaj.org/article/622cf7f75664481dbb2a9b1d8b00483f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:622cf7f75664481dbb2a9b1d8b00483f
record_format	dspace
spelling	oai:doaj.org-article:622cf7f75664481dbb2a9b1d8b00483f2021-11-08T02:36:11ZSelf-Attention-Guided Recurrent Neural Network and Motion Perception for Intelligent Prediction of Chronic Diseases2040-230910.1155/2021/6382619https://doaj.org/article/622cf7f75664481dbb2a9b1d8b00483f2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/6382619https://doaj.org/toc/2040-2309Parkinson’s disease is a common chronic disease that affects a large number of people. In the real world, however, Parkinson’s disease can result in a loss of physical performance, which is classified as a movement disorder by clinicians. Parkinson’s disease is currently diagnosed primarily through clinical symptoms, which are highly dependent on clinician experience. As a result, there is a need for effective early detection methods. Traditional machine learning algorithms filter out many inherently relevant features in the process of dimensionality reduction and feature classification, lowering the classification model’s performance. To solve this problem and ensure high correlation between features while reducing dimensionality to achieve the goal of improving classification performance, this paper proposes a recurrent neural network classification model based on self attention and motion perception. Using a combination of self-attention mechanism and recurrent neural network, as well as wearable inertial sensors, the model classifies and trains the five brain area features extracted from MRI and DTI images (cerebral gray matter, white matter, cerebrospinal fluid density, and so on). Clinical and exercise data can be combined to produce characteristic parameters that can be used to describe movement sluggishness. The experimental results show that the model proposed in this paper improves the recognition performance of Parkinson’s disease, which is better than the compared methods by 2.45% to 12.07%.Baojuan MaFengyan ZhangBaoling MaHindawi LimitedarticleMedicine (General)R5-920Medical technologyR855-855.5ENJournal of Healthcare Engineering, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine (General) R5-920 Medical technology R855-855.5
spellingShingle	Medicine (General) R5-920 Medical technology R855-855.5 Baojuan Ma Fengyan Zhang Baoling Ma Self-Attention-Guided Recurrent Neural Network and Motion Perception for Intelligent Prediction of Chronic Diseases
description	Parkinson’s disease is a common chronic disease that affects a large number of people. In the real world, however, Parkinson’s disease can result in a loss of physical performance, which is classified as a movement disorder by clinicians. Parkinson’s disease is currently diagnosed primarily through clinical symptoms, which are highly dependent on clinician experience. As a result, there is a need for effective early detection methods. Traditional machine learning algorithms filter out many inherently relevant features in the process of dimensionality reduction and feature classification, lowering the classification model’s performance. To solve this problem and ensure high correlation between features while reducing dimensionality to achieve the goal of improving classification performance, this paper proposes a recurrent neural network classification model based on self attention and motion perception. Using a combination of self-attention mechanism and recurrent neural network, as well as wearable inertial sensors, the model classifies and trains the five brain area features extracted from MRI and DTI images (cerebral gray matter, white matter, cerebrospinal fluid density, and so on). Clinical and exercise data can be combined to produce characteristic parameters that can be used to describe movement sluggishness. The experimental results show that the model proposed in this paper improves the recognition performance of Parkinson’s disease, which is better than the compared methods by 2.45% to 12.07%.
format	article
author	Baojuan Ma Fengyan Zhang Baoling Ma
author_facet	Baojuan Ma Fengyan Zhang Baoling Ma
author_sort	Baojuan Ma
title	Self-Attention-Guided Recurrent Neural Network and Motion Perception for Intelligent Prediction of Chronic Diseases
title_short	Self-Attention-Guided Recurrent Neural Network and Motion Perception for Intelligent Prediction of Chronic Diseases
title_full	Self-Attention-Guided Recurrent Neural Network and Motion Perception for Intelligent Prediction of Chronic Diseases
title_fullStr	Self-Attention-Guided Recurrent Neural Network and Motion Perception for Intelligent Prediction of Chronic Diseases
title_full_unstemmed	Self-Attention-Guided Recurrent Neural Network and Motion Perception for Intelligent Prediction of Chronic Diseases
title_sort	self-attention-guided recurrent neural network and motion perception for intelligent prediction of chronic diseases
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/622cf7f75664481dbb2a9b1d8b00483f
work_keys_str_mv	AT baojuanma selfattentionguidedrecurrentneuralnetworkandmotionperceptionforintelligentpredictionofchronicdiseases AT fengyanzhang selfattentionguidedrecurrentneuralnetworkandmotionperceptionforintelligentpredictionofchronicdiseases AT baolingma selfattentionguidedrecurrentneuralnetworkandmotionperceptionforintelligentpredictionofchronicdiseases
_version_	1718443100413624320

Self-Attention-Guided Recurrent Neural Network and Motion Perception for Intelligent Prediction of Chronic Diseases

Ejemplares similares