EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning in the Recognition of Activities of Daily Living Using Smartwatch Data

Ariany F Cavalcante iD, Victor H de L Kunst, Thiago de M Chaves, Júlia D T de Souza, Isabela M Ribeiro iD, Jonysberg P Quintino iD, Fabio Q B da Silva, André L M Santos iD, Veronica Teichrieb iD, Alana Elza F da Gama

Sensors · 2023

DOI: 10.3390/s23177493 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Ariany F Cavalcante und 9 weiteren Autor:innen. Beteiligte Einrichtung: Centro de Informática, Universidade Federal de Pernambuco, Recife 50740-560, PE, Brazil. Hauptthemen laut MEDLINE: Activities of Daily Living, Deep Learning. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Samsung (Brazil), Samsung Eletronica da Amazonia Ltda., INES.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The recognition of human activities (HAR) using wearable device data, such as smartwatches, has gained significant attention in the field of computer science due to its potential to provide insights into individuals’ daily activities. This article aims to conduct a comparative study of deep learning techniques for recognizing activities of daily living (ADL). A mapping of HAR techniques was performed, and three techniques were selected for evaluation, along with a dataset. Experiments were conducted using the selected techniques to assess their performance in ADL recognition, employing standardized evaluation metrics, such as accuracy, precision, recall, and F1-score. Among the evaluated techniques, the DeepConvLSTM architecture, consisting of recurrent convolutional layers and a single LSTM layer, achieved the most promising results. These findings suggest that software applications utilizing this architecture can assist smartwatch users in understanding their movement routines more quickly and accurately.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Activities of Daily LivingDeep LearningHumansRecognition, PsychologyBenchmarkingMovement

Stichwörter der Autor:innen

human activity recognitionneural networkssmartwatchwearable sensor data

Autor:innen und Institutionen

  • Centro de Informática, Universidade Federal de Pernambuco, Recife 50740-560, PE, Brazil.
  • Projeto CIn-UFPE Samsung, Centro de Informática, Recife 50740-560, PE, Brazil.
  • Departamento de Engenharia Biomédica, Universidade Federal de Pernambuco, Recife 50740-560, PE, Brazil.

ORCID-Profile: Ariany F Cavalcante, Isabela M Ribeiro, Jonysberg P Quintino, André L M Santos, Veronica Teichrieb

Förderung

  • Samsung (Brazil)
  • Samsung Eletronica da Amazonia Ltda.
  • INES

Zitieren

APA

Cavalcante, A. F., Kunst, V. H. L., Chaves, T. M., de Souza, J. D. T., Ribeiro, I. M., Quintino, J. P., da Silva, F. Q. B., Santos, A. L. M., Teichrieb, V., & da Gama, A. E. F. (2023). Deep Learning in the Recognition of Activities of Daily Living Using Smartwatch Data. Sensors. https://doi.org/10.3390/s23177493

Vancouver

Cavalcante AF, Kunst VHL, Chaves TM, de Souza JDT, Ribeiro IM, Quintino JP, et al. Deep Learning in the Recognition of Activities of Daily Living Using Smartwatch Data. Sensors. 2023. doi:10.3390/s23177493

BibTeX
@article{Cavalcante2023,
  author = {Cavalcante, Ariany F and Kunst, Victor H de L and Chaves, Thiago de M and de Souza, Júlia D T and Ribeiro, Isabela M and Quintino, Jonysberg P and da Silva, Fabio Q B and Santos, André L M and Teichrieb, Veronica and da Gama, Alana Elza F},
  title = {Deep Learning in the Recognition of Activities of Daily Living Using Smartwatch Data},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23177493}
}
Kostenlos starten →