Publication:
BERT for Activity Recognition Using Sequences of Skeleton Features and Data Augmentation with GAN

Simple item page
dc.affiliation.dptoUC3M. Departamento de Informáticaes
dc.affiliation.grupoinvUC3M. Grupo de InvestigaciĂłn: Grupo de Inteligencia Artificial Aplicada (GIAA)es
dc.contributor.authorRamirez, Heilym
dc.contributor.authorVelastin Carroza, Sergio Alejandro
dc.contributor.authorCuéllar, Sara
dc.contributor.authorFabregas, Ernesto
dc.contributor.authorFarias, Gonzalo
dc.contributor.funderMinisterio de Ciencia e Innovación (España)es
dc.date.accessioned2023-06-08T09:53:42Z
dc.date.available2023-06-08T09:53:42Z
dc.date.issued2023-02-01
dc.description.abstractRecently, the scientific community has placed great emphasis on the recognition of human activity, especially in the area of health and care for the elderly. There are already practical applications of activity recognition and unusual conditions that use body sensors such as wrist-worn devices or neck pendants. These relatively simple devices may be prone to errors, might be uncomfortable to wear, might be forgotten or not worn, and are unable to detect more subtle conditions such as incorrect postures. Therefore, other proposed methods are based on the use of images and videos to carry out human activity recognition, even in open spaces and with multiple people. However, the resulting increase in the size and complexity involved when using image data requires the use of the most recent advanced machine learning and deep learning techniques. This paper presents an approach based on deep learning with attention to the recognition of activities from multiple frames. Feature extraction is performed by estimating the pose of the human skeleton, and classification is performed using a neural network based on Bidirectional Encoder Representation of Transformers (BERT). This algorithm was trained with the UP-Fall public dataset, generating more balanced artificial data with a Generative Adversarial Neural network (GAN), and evaluated with real data, outperforming the results of other activity recognition methods using the same dataset.en
dc.description.sponsorshipThis research was supported in part by the Chilean Research and Development Agency (ANID) under Project FONDECYT 1191188, The National University of Distance Education under Projects 2021V/-TAJOV/00 and OPTIVAC 096-034091 2021V/PUNED/008, and the Ministry of Science and Innovation of Spain under Project PID2019-108377RB-C32.en
dc.format.extent15
dc.identifier.bibliographicCitationRamirez, H.; Velastin, S.A.; Cuellar, S.; Fabregas, E.; Farias, G. BERT for Activity Recognition Using Sequences of Skeleton Features and Data Augmentation with GAN. Sensors 2023, 23, 1400. https://doi.org/10.3390/s23031400en
dc.identifier.doihttps://doi.org/10.3390/s23031400
dc.identifier.issn1424-3210
dc.identifier.publicationissue3
dc.identifier.publicationtitleSensorsen
dc.identifier.publicationvolume23
dc.identifier.urihttps://hdl.handle.net/10016/37440
dc.identifier.uxxiAR/0000033063
dc.language.isoeng
dc.publisherMDPIen
dc.relation.projectIDGobierno de España. PID2019-108377RB-C32es
dc.rights© 2023 by the authors
dc.rightsAtribución 3.0 España
dc.rights.accessRightsopen accessen
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/es/
dc.subject.ecienciaInformáticaes
dc.subject.otheractivity recognitionen
dc.subject.otherBERTen
dc.subject.othercomputer visionen
dc.subject.otherhuman skeletonen
dc.subject.otherpose estimationen
dc.titleBERT for Activity Recognition Using Sequences of Skeleton Features and Data Augmentation with GANen
dc.typeresearch article*
dc.type.hasVersionVoR*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
BERT_S_2023.pdf
Size:
2.56 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
DI - GIAA - ArtĂ­culos de Revistas