Human activity classification using long short-term memory network

Activities of daily living (ADL) can be used to identify a person’s daily routine which helps health professionals to provide preventive healthcare. Classification of ADLs is therefore very important. In this study, long short-term memory (LSTM) network, which is an extension of recurrent neural net...

Full description

Bibliographic Details
Main Authors: Malshika Welhenge, Anuradhi, Taparugssanagorn, A.
Format: Journal Article
Language:English
Published: SPRINGER LONDON LTD 2019
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/90320
_version_ 1848765370027999232
author Malshika Welhenge, Anuradhi
Taparugssanagorn, A.
author_facet Malshika Welhenge, Anuradhi
Taparugssanagorn, A.
author_sort Malshika Welhenge, Anuradhi
building Curtin Institutional Repository
collection Online Access
description Activities of daily living (ADL) can be used to identify a person’s daily routine which helps health professionals to provide preventive healthcare. Classification of ADLs is therefore very important. In this study, long short-term memory (LSTM) network, which is an extension of recurrent neural networks, is used. Data collected in MobiAct data set are used to train and test the network. An accuracy of 0.90 is achieved using LSTM network.
first_indexed 2025-11-14T11:34:10Z
format Journal Article
id curtin-20.500.11937-90320
institution Curtin University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T11:34:10Z
publishDate 2019
publisher SPRINGER LONDON LTD
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-903202023-02-28T02:23:31Z Human activity classification using long short-term memory network Malshika Welhenge, Anuradhi Taparugssanagorn, A. Science & Technology Technology Engineering, Electrical & Electronic Imaging Science & Photographic Technology Engineering Deep learning ADL LSTM RNN TRIAXIAL ACCELEROMETER FALL DETECTION Activities of daily living (ADL) can be used to identify a person’s daily routine which helps health professionals to provide preventive healthcare. Classification of ADLs is therefore very important. In this study, long short-term memory (LSTM) network, which is an extension of recurrent neural networks, is used. Data collected in MobiAct data set are used to train and test the network. An accuracy of 0.90 is achieved using LSTM network. 2019 Journal Article http://hdl.handle.net/20.500.11937/90320 10.1007/s11760-018-1393-7 English SPRINGER LONDON LTD restricted
spellingShingle Science & Technology
Technology
Engineering, Electrical & Electronic
Imaging Science & Photographic Technology
Engineering
Deep learning
ADL
LSTM
RNN
TRIAXIAL ACCELEROMETER
FALL DETECTION
Malshika Welhenge, Anuradhi
Taparugssanagorn, A.
Human activity classification using long short-term memory network
title Human activity classification using long short-term memory network
title_full Human activity classification using long short-term memory network
title_fullStr Human activity classification using long short-term memory network
title_full_unstemmed Human activity classification using long short-term memory network
title_short Human activity classification using long short-term memory network
title_sort human activity classification using long short-term memory network
topic Science & Technology
Technology
Engineering, Electrical & Electronic
Imaging Science & Photographic Technology
Engineering
Deep learning
ADL
LSTM
RNN
TRIAXIAL ACCELEROMETER
FALL DETECTION
url http://hdl.handle.net/20.500.11937/90320