EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Anomaly Detection in Multi-Wavelength Photoplethysmography Using Lightweight Machine Learning Algorithms

Vlad-Eusebiu Baciu iD, Joan Lambert Cause iD, Ángel Solé Morillo iD, Juan C García-Naranjo iD, Johan Stiens iD, Bruno da Silva iD

Sensors · 04.08.2023 · 23 (15) · 6947

DOI: 10.3390/s23156947 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 04.08.2023. Verfasst von Vlad-Eusebiu Baciu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel (VUB), 1050 Brussels, Belgium. Hauptthemen laut MEDLINE: Photoplethysmography, Algorithms. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Post-doc VUB Global Minds, Vrije Universiteit Brussel (VUB), SRP-Projects M3D2 and LSDS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Over the past few years, there has been increased interest in photoplethysmography (PPG) technology, which has revealed that, in addition to heart rate and oxygen saturation, the pulse shape of the PPG signal contains much more valuable information. Lately, the wearable market has shifted towards a multi-wavelength and multichannel approach to increase signal robustness and facilitate the extraction of other intrinsic information from the signal. This transition presents several challenges related to complexity, accuracy, and reliability of algorithms. To address these challenges, anomaly detection stages can be employed to increase the accuracy and reliability of estimated parameters. Powerful algorithms, such as lightweight machine learning (ML) algorithms, can be used for anomaly detection in multi-wavelength PPG (MW-PPG). The main contributions of this paper are (a) proposing a set of features with high information gain for anomaly detection in MW-PPG signals in the classification context, (b) assessing the impact of window size and evaluating various lightweight ML models to achieve highly accurate anomaly detection, and (c) examining the effectiveness of MW-PPG signals in detecting artifacts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PhotoplethysmographyAlgorithmsReproducibility of ResultsHeart RateMachine LearningArtifactsSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

PPGanomaly detectionartifactmachine learningmulti-wavelength PPGneural networksphotoplethysmographysupervised learningtime seriesunsupervised learning

Autor:innen und Institutionen

  • Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel (VUB), 1050 Brussels, Belgium.
  • Department of Biomedical Engineering, Universidad de Oriente, Santiago de Cuba 90500, Cuba.
  • Centre of Medical Biophysics, Universidad de Oriente, Santiago de Cuba 90500, Cuba.

ORCID-Profile: Vlad-Eusebiu Baciu, Joan Lambert Cause, Ángel Solé Morillo, Juan C García-Naranjo, Johan Stiens, Bruno da Silva

Förderung

  • Post-doc VUB Global Minds
  • Vrije Universiteit Brussel (VUB)
  • SRP-Projects M3D2 and LSDS
  • ETRO-IOF Project
  • FWO-Flanders
  • Belgian Development Cooperation
  • VLIR-UOS (Flemish Interuniversity Council-University Cooperation for Development)
  • Institutional University Cooperation program (IUC 2019 Phase 2 UO) with the Universidad de Oriente (Cuba)

Zitieren

APA

Baciu, V. E., Lambert Cause, J., Solé Morillo, Á., García-Naranjo, J. C., Stiens, J., & da Silva, B. (2023). Anomaly Detection in Multi-Wavelength Photoplethysmography Using Lightweight Machine Learning Algorithms. Sensors, 23(15), 6947. https://doi.org/10.3390/s23156947

Vancouver

Baciu VE, Lambert Cause J, Solé Morillo Á, García-Naranjo JC, Stiens J, da Silva B. Anomaly Detection in Multi-Wavelength Photoplethysmography Using Lightweight Machine Learning Algorithms. Sensors. 2023;23(15):6947. doi:10.3390/s23156947

BibTeX
@article{Baciu2023,
  author = {Baciu, Vlad-Eusebiu and Lambert Cause, Joan and Solé Morillo, Ángel and García-Naranjo, Juan C and Stiens, Johan and da Silva, Bruno},
  title = {Anomaly Detection in Multi-Wavelength Photoplethysmography Using Lightweight Machine Learning Algorithms},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {15},
  pages = {6947},
  doi = {10.3390/s23156947}
}
Kostenlos starten →