EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Novel Framework Based on Deep Learning Architecture for Continuous Human Activity Recognition with Inertial Sensors

Vladimiro Suglia iD, Lucia Palazzo iD, Vitoantonio Bevilacqua iD, Andrea Passantino iD, Gaetano Pagano iD, Giovanni D'Addio iD

Sensors · 29.03.2024 · 24 (7) · 2199

DOI: 10.3390/s24072199 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.03.2024. Verfasst von Vladimiro Suglia und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Information Engineering (DEI), Polytechnic University of Bari, 70126 Bari, Italy. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 46-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Economic Development, BRIEF—Biorobotics Research and Innovation Engineering Facilities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Frameworks for human activity recognition (HAR) can be applied in the clinical environment for monitoring patients’ motor and functional abilities either remotely or within a rehabilitation program. Deep Learning (DL) models can be exploited to perform HAR by means of raw data, thus avoiding time-demanding feature engineering operations. Most works targeting HAR with DL-based architectures have tested the workflow performance on data related to a separate execution of the tasks. Hence, a paucity in the literature has been found with regard to frameworks aimed at recognizing continuously executed motor actions. In this article, the authors present the design, development, and testing of a DL-based workflow targeting continuous human activity recognition (CHAR). The model was trained on the data recorded from ten healthy subjects and tested on eight different subjects. Despite the limited sample size, the authors claim the capability of the proposed framework to accurately classify motor actions within a feasible time, thus making it potentially useful in a clinical scenario.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningHumansHuman ActivitiesActivities of Daily LivingEngineeringHealthy Volunteers

Stichwörter der Autor:innen

activities of daily livingartificial intelligencebioengineeringconvolutional neural networksdata augmentationdeep learninghuman activity recognitioninertial measurement unitsmotion analysisrehabilitationtime-series

Autor:innen und Institutionen

  • Department of Electrical and Information Engineering (DEI), Polytechnic University of Bari, 70126 Bari, Italy.
  • Scientific Clinical Institutes Maugeri SPA SB IRCCS, 70124 Bari, Italy.
  • Apulian Bioengineering S.R.L.,Via delle Violette 14, 70026 Modugno, Italy.

ORCID-Profile: Vladimiro Suglia, Lucia Palazzo, Vitoantonio Bevilacqua, Andrea Passantino, Gaetano Pagano, Giovanni D'Addio

Förderung

  • Ministry of Economic Development
  • BRIEF—Biorobotics Research and Innovation Engineering Facilities

Zitieren

APA

Suglia, V., Palazzo, L., Bevilacqua, V., Passantino, A., Pagano, G., & D'Addio, G. (2024). A Novel Framework Based on Deep Learning Architecture for Continuous Human Activity Recognition with Inertial Sensors. Sensors, 24(7), 2199. https://doi.org/10.3390/s24072199

Vancouver

Suglia V, Palazzo L, Bevilacqua V, Passantino A, Pagano G, D'Addio G. A Novel Framework Based on Deep Learning Architecture for Continuous Human Activity Recognition with Inertial Sensors. Sensors. 2024;24(7):2199. doi:10.3390/s24072199

BibTeX
@article{Suglia2024,
  author = {Suglia, Vladimiro and Palazzo, Lucia and Bevilacqua, Vitoantonio and Passantino, Andrea and Pagano, Gaetano and D'Addio, Giovanni},
  title = {A Novel Framework Based on Deep Learning Architecture for Continuous Human Activity Recognition with Inertial Sensors},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {7},
  pages = {2199},
  doi = {10.3390/s24072199}
}
Kostenlos starten →