Deep learning based human activity recognition (HAR) using wearable sensor data

Motion or inertial sensors such as gyroscope and accelerometer commonly found in smartwatches and smartphones can measure characteristics such as acceleration and angular velocity of movements in the human body and use them to learn models capable of identifying human activities, that has applicabil...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Saurabh Gupta
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Human Activity Recognition Deep Learning Sensor CNN-GRU InceptionTime AutoML Information technology T58.5-58.64
Acceso en línea:	https://doaj.org/article/4571b9c02fdf4ddc8486b2b5cfd6a5f8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4571b9c02fdf4ddc8486b2b5cfd6a5f8
record_format	dspace
spelling	oai:doaj.org-article:4571b9c02fdf4ddc8486b2b5cfd6a5f82021-11-20T05:16:02ZDeep learning based human activity recognition (HAR) using wearable sensor data2667-096810.1016/j.jjimei.2021.100046https://doaj.org/article/4571b9c02fdf4ddc8486b2b5cfd6a5f82021-11-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2667096821000392https://doaj.org/toc/2667-0968Motion or inertial sensors such as gyroscope and accelerometer commonly found in smartwatches and smartphones can measure characteristics such as acceleration and angular velocity of movements in the human body and use them to learn models capable of identifying human activities, that has applicability in various fields such as biometrics, remote patient health monitoring, etc. Recently deep learning-based methods have become popular for human activity recognition because they use representation learning techniques that can automatically generate optimal features from raw input data generated from sensors without any human intervention and can identify hidden patterns in data. This work proposes a novel hybrid deep neural network model, CNN-GRU that combines convolutional and gated recurrent units for human activity recognition. This model was successfully validated on WISDM dataset and produced accuracy that is suggestively better than other state-of-the-art deep neural network models such as Inception Time and DeepConvLSTM created using AutoML.Saurabh GuptaElsevierarticleHuman Activity RecognitionDeep LearningSensorCNN-GRUInceptionTimeAutoMLInformation technologyT58.5-58.64ENInternational Journal of Information Management Data Insights, Vol 1, Iss 2, Pp 100046- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Human Activity Recognition Deep Learning Sensor CNN-GRU InceptionTime AutoML Information technology T58.5-58.64
spellingShingle	Human Activity Recognition Deep Learning Sensor CNN-GRU InceptionTime AutoML Information technology T58.5-58.64 Saurabh Gupta Deep learning based human activity recognition (HAR) using wearable sensor data
description	Motion or inertial sensors such as gyroscope and accelerometer commonly found in smartwatches and smartphones can measure characteristics such as acceleration and angular velocity of movements in the human body and use them to learn models capable of identifying human activities, that has applicability in various fields such as biometrics, remote patient health monitoring, etc. Recently deep learning-based methods have become popular for human activity recognition because they use representation learning techniques that can automatically generate optimal features from raw input data generated from sensors without any human intervention and can identify hidden patterns in data. This work proposes a novel hybrid deep neural network model, CNN-GRU that combines convolutional and gated recurrent units for human activity recognition. This model was successfully validated on WISDM dataset and produced accuracy that is suggestively better than other state-of-the-art deep neural network models such as Inception Time and DeepConvLSTM created using AutoML.
format	article
author	Saurabh Gupta
author_facet	Saurabh Gupta
author_sort	Saurabh Gupta
title	Deep learning based human activity recognition (HAR) using wearable sensor data
title_short	Deep learning based human activity recognition (HAR) using wearable sensor data
title_full	Deep learning based human activity recognition (HAR) using wearable sensor data
title_fullStr	Deep learning based human activity recognition (HAR) using wearable sensor data
title_full_unstemmed	Deep learning based human activity recognition (HAR) using wearable sensor data
title_sort	deep learning based human activity recognition (har) using wearable sensor data
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/4571b9c02fdf4ddc8486b2b5cfd6a5f8
work_keys_str_mv	AT saurabhgupta deeplearningbasedhumanactivityrecognitionharusingwearablesensordata
_version_	1718419478268608512

Deep learning based human activity recognition (HAR) using wearable sensor data

Ejemplares similares