Open Collections

UBC Faculty Research and Publications

PPGTempStitch: A MATLAB Toolbox for Augmenting Annotated Photoplethsmogram Signals Tang, Qunfeng; Chen, Zhencheng; Menon, Carlo; Ward, Rabab Kreidieh; Elgendi, Mohamed

Abstract

An annotated photoplethysmogram (PPG) is required when evaluating PPG algorithms that have been developed to detect the onset and systolic peaks of PPG waveforms. However, few publicly accessible PPG datasets exist in which the onset and systolic peaks of the waveforms are annotated. Therefore, this study developed a MATLAB toolbox that stitches predetermined annotated PPGs in a random manner to generate a long, annotated PPG signal. With this toolbox, any combination of four annotated PPG templates that represent regular, irregular, fast rhythm, and noisy PPG waveforms can be stitched together to generate a long, annotated PPG. Furthermore, this toolbox can simulate real-life PPG signals by introducing different noise levels and PPG waveforms. The toolbox can implement two stitching methods: one based on the systolic peak and the other on the onset. Additionally, cubic spline interpolation is used to smooth the waveform around the stitching point, and a skewness index is used as a signal quality index to select the final signal output based on the stitching method used. The developed toolbox is free and open-source software, and a graphical user interface is provided. The method of synthesizing by stitching introduced in this paper is a data augmentation strategy that can help researchers significantly increase the size and diversity of annotated PPG signals available for training and testing different feature extraction algorithms.

Item Metadata

Title
PPGTempStitch: A MATLAB Toolbox for Augmenting Annotated Photoplethsmogram Signals
Creator
Tang, Qunfeng; Chen, Zhencheng; Menon, Carlo; Ward, Rabab Kreidieh; Elgendi, Mohamed
Publisher
Multidisciplinary Digital Publishing Institute
Date Issued
2021-06-10
Description
An annotated photoplethysmogram (PPG) is required when evaluating PPG algorithms that have been developed to detect the onset and systolic peaks of PPG waveforms. However, few publicly accessible PPG datasets exist in which the onset and systolic peaks of the waveforms are annotated. Therefore, this study developed a MATLAB toolbox that stitches predetermined annotated PPGs in a random manner to generate a long, annotated PPG signal. With this toolbox, any combination of four annotated PPG templates that represent regular, irregular, fast rhythm, and noisy PPG waveforms can be stitched together to generate a long, annotated PPG. Furthermore, this toolbox can simulate real-life PPG signals by introducing different noise levels and PPG waveforms. The toolbox can implement two stitching methods: one based on the systolic peak and the other on the onset. Additionally, cubic spline interpolation is used to smooth the waveform around the stitching point, and a skewness index is used as a signal quality index to select the final signal output based on the stitching method used. The developed toolbox is free and open-source software, and a graphical user interface is provided. The method of synthesizing by stitching introduced in this paper is a data augmentation strategy that can help researchers significantly increase the size and diversity of annotated PPG signals available for training and testing different feature extraction algorithms.
Subject
PPG synthesis; pleth augmentation; PPG generators; imbalanced PPG; PPG augmentation; enlarging time-series health data; PPG in low-resource clinical settings; PPG lengthening; PPG signal extension; upsizing existing PPG databases
Genre
Article
Type
Text
Language
eng
Date Available
2021-07-21
Provider
Vancouver : University of British Columbia Library
Rights
CC BY 4.0
DOI
10.14288/1.0400586
URI
http://hdl.handle.net/2429/79062
Affiliation
Applied Science, Faculty of; Non UBC; Electrical and Computer Engineering, Department of
Citation
Sensors 21 (12): 4007 (2021)
Publisher DOI
10.3390/s21124007
Peer Review Status
Reviewed
Scholarly Level
Faculty
Rights URI
https://creativecommons.org/licenses/by/4.0/
Aggregated Source Repository
DSpace

Item Media

Item Citations and Data

Rights

CC BY 4.0