Novel approaches to human activity recognition based on accelerometer data

Página do item simplificado
dc.creatorArtur Jordão
dc.creatorLeonardo Antônio Borges Torres
dc.creatorWilliam Robson Schwartz
dc.date.accessioned2025-04-25T14:41:36Z
dc.date.accessioned2025-09-09T00:54:38Z
dc.date.available2025-04-25T14:41:36Z
dc.date.issued2018
dc.identifier.doihttps://doi.org/10.1007/s11760-018-1293-x
dc.identifier.issn1863-1703
dc.identifier.urihttps://hdl.handle.net/1843/81852
dc.languageeng
dc.publisherUniversidade Federal de Minas Gerais
dc.relation.ispartofSignal, image and video processing
dc.rightsAcesso Restrito
dc.subjectAprendizado do computador
dc.subjectIdentificação de sistemas
dc.subject.otherAnálise de dados sensoriais
dc.subject.otherDados de acelerômetro
dc.subject.otherReconhecimento de Atividades
dc.subject.otherHuman activity recognition, Accelerometer data, Attitude estimation features, Convolutional neural networks
dc.subject.otherIn the past decade, human activity recognition (HAR) hasbeen an active research topic, mostly because of its directapplications in person identification, health care,homeland security and smart environments. For this pur-pose, sensor-based data have been widely explored due totheir easy acquisition and fast processing in dedicated wear-able sensors. Recent technological advances haveallowed the employment of smartphones and smartwatchesto perform HAR, since these devices provide inertial sensorssuch as accelerometers, gyroscopes and barometers.
dc.titleNovel approaches to human activity recognition based on accelerometer data
dc.typeArtigo de periódico
local.citation.epage1394
local.citation.issue7
local.citation.spage1387
local.citation.volume12
local.description.resumoAn increasing number of works have investigated the use of convolutional neural network (ConvNets) approaches to perform human activity recognition (HAR) based on wearable sensor data. These approaches present state-of-the-art results in HAR, outperforming traditional approaches, such as handcrafted methods and 1D convolutions. Motivated by this, in this work we propose a set of methods to enhance ConvNets for HAR. First, we propose a data augmentation which enables the ConvNets to learn more adequately the patterns of the signal. Second, we exploit the attitude estimation of the accelerometer data to devise a set of novel feature descriptors which allow the ConvNets to better discriminate the activities. Finally, we propose a novel ConvNet architecture to explore the patterns among the accelerometer axes throughout the layers that compose the network. We demonstrate that this is a simpler way of improving the activity recognition instead of proposing more complex architectures, serving as direction to future works with the purpose of building ConvNets architectures. The experimental results show that our proposed methods achieve notable improvements and outperform existing state-of-the-art methods.
local.publisher.countryBrasil
local.publisher.departmentENG - DEPARTAMENTO DE ENGENHARIA ELETRÔNICA
local.publisher.departmentICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃO
local.publisher.initialsUFMG
local.url.externahttps://link.springer.com/article/10.1007/s11760-018-1293-x

Arquivos

Licença do pacote

Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
License.txt
Tamanho:
1.99 KB
Formato:
Plain Text
Descrição:
Baixar

Coleções

Artigo de Periódico

Logo UFMG