Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A Lightweight Hybrid Authentication and Key Agreement Protocol for Decentralized Device-to-Device Communication with Post-Quantum Confidentiality.

Sensors (Basel, Switzerland)·2026
Same author

Agreement between intra-bladder and insufflation pressure readings during laparoscopic surgery.

Journal of clinical monitoring and computing·2026
Same author

Evaluating a Wearable-Based Pain Monitoring System in Palliative Cancer Care: Usability and Feasibility Study.

JMIR formative research·2026
Same author

Exploring Near- and Far-Field Effects in Photoplethysmography Signals Across Different Source-Detector Distances.

Sensors (Basel, Switzerland)·2025
Same author

Nondestructive Monitoring of Textile-Reinforced Cementitious Composites Subjected to Freeze-Thaw Cycles.

Materials (Basel, Switzerland)·2025
Same author

An Introduction to Ventra: A Programmable Abdominal Phantom for Training, Educational, Research, and Development Purposes.

Sensors (Basel, Switzerland)·2024

Related Experiment Video

Updated: Jul 19, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K

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

Vlad-Eusebiu Baciu1, Joan Lambert Cause1,2, Ángel Solé Morillo1

  • 1Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel (VUB), 1050 Brussels, Belgium.

Sensors (Basel, Switzerland)
|August 12, 2023
PubMed
Summary

This study introduces advanced anomaly detection for multi-wavelength photoplethysmography (MW-PPG) signals using lightweight machine learning. Findings show improved accuracy and artifact detection in wearable health monitoring.

Keywords:
PPGanomaly detectionartifactmachine learningmulti-wavelength PPGneural networksphotoplethysmographysupervised learningtime seriesunsupervised learning

More Related Videos

Semi-automated Optical Heartbeat Analysis of Small Hearts
12:10

Semi-automated Optical Heartbeat Analysis of Small Hearts

Published on: September 16, 2009

12.3K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K

Related Experiment Videos

Last Updated: Jul 19, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K
Semi-automated Optical Heartbeat Analysis of Small Hearts
12:10

Semi-automated Optical Heartbeat Analysis of Small Hearts

Published on: September 16, 2009

12.3K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K

Area of Science:

  • Biomedical Engineering
  • Signal Processing
  • Machine Learning

Background:

  • Photoplethysmography (PPG) signals offer more than heart rate and oxygen saturation, with pulse shape containing valuable physiological data.
  • The trend towards multi-wavelength PPG (MW-PPG) in wearables enhances signal robustness but introduces algorithmic complexity and reliability challenges.
  • Anomaly detection is crucial for improving the accuracy and reliability of parameter estimation from complex PPG signals.

Purpose of the Study:

  • To propose high-information-gain features for anomaly detection in MW-PPG signals within a classification framework.
  • To evaluate the influence of window size and compare various lightweight machine learning models for accurate anomaly detection.
  • To investigate the efficacy of MW-PPG signals in identifying and mitigating signal artifacts.

Main Methods:

  • Feature engineering focused on identifying discriminative characteristics for anomaly detection in MW-PPG data.
  • Comparative analysis of different lightweight machine learning algorithms (e.g., SVM, Random Forest, Logistic Regression) for anomaly classification.
  • Systematic evaluation of varying window sizes to optimize feature extraction and model performance.
  • Assessment of MW-PPG signal capabilities in detecting common physiological and motion artifacts.

Main Results:

  • Identification of a specific set of features demonstrating high information gain for MW-PPG anomaly detection.
  • Demonstration that certain lightweight ML models achieve superior accuracy in detecting anomalies within MW-PPG signals.
  • Quantification of the impact of window size on the performance of anomaly detection algorithms.
  • Validation of MW-PPG's effectiveness in distinguishing between clean signals and various types of artifacts.

Conclusions:

  • The proposed features and lightweight ML models provide an effective solution for anomaly detection in MW-PPG signals.
  • Optimizing window size and selecting appropriate ML algorithms are critical for reliable MW-PPG data analysis.
  • MW-PPG technology shows significant promise for robust artifact detection, enhancing the trustworthiness of wearable health monitoring devices.