Stochastic modeling of the PPG signal: a synthesis-by-analysis approach with applications

Diego Martín-Martínez, Pablo Casaseca-de-la-Higuera, Marcos Martín-Fernández, Carlos Alberola-López

Research output: Contribution to journalArticle

Abstract

In this paper, we propose a stochastic model of photoplethysmographic signals that is able to synthesize an arbitrary number of other statistically equivalent signals to the one under analysis. To that end, we first preprocess the pulse signal to normalize and time-align pulses. In a second stage, we design a single-pulse model, which consists of ten parameters. In the third stage, the time evolution of this ten-parameter vector is approximated by means of two autoregressive moving average models, one for the trend and one for the residue; this model is applied after a decorrelation step which let us to process each vector component in parallel. The experiments carried out show that the model we here propose is able to maintain the main features of the original signal; this is accomplished by means of both a linear spectral analysis and also by comparing two measures obtained from a nonlinear analysis. Finally, we explore the capability of the model to: 1) track physical activity; 2) obtain statistics of clinical parameters by model sampling; and 3) recover corrupted or missing signal epochs by synthesis.
Original languageEnglish
Pages (from-to)2432-2441
Number of pages10
JournalIEEE Transactions on Biomedical Engineering
Volume60
Issue number9
DOIs
Publication statusPublished - 12 Apr 2013
Externally publishedYes

Keywords

  • ARMA
  • benchmarking
  • modeling
  • PCA
  • photoplethysmography
  • signal synthesis
  • statistical validation
  • subject simulation

Cite this

Martín-Martínez, Diego ; Casaseca-de-la-Higuera, Pablo ; Martín-Fernández, Marcos ; Alberola-López, Carlos. / Stochastic modeling of the PPG signal : a synthesis-by-analysis approach with applications. In: IEEE Transactions on Biomedical Engineering. 2013 ; Vol. 60, No. 9. pp. 2432-2441.
@article{d7c9607981fc41d890f5aedde199ca33,
title = "Stochastic modeling of the PPG signal: a synthesis-by-analysis approach with applications",
abstract = "In this paper, we propose a stochastic model of photoplethysmographic signals that is able to synthesize an arbitrary number of other statistically equivalent signals to the one under analysis. To that end, we first preprocess the pulse signal to normalize and time-align pulses. In a second stage, we design a single-pulse model, which consists of ten parameters. In the third stage, the time evolution of this ten-parameter vector is approximated by means of two autoregressive moving average models, one for the trend and one for the residue; this model is applied after a decorrelation step which let us to process each vector component in parallel. The experiments carried out show that the model we here propose is able to maintain the main features of the original signal; this is accomplished by means of both a linear spectral analysis and also by comparing two measures obtained from a nonlinear analysis. Finally, we explore the capability of the model to: 1) track physical activity; 2) obtain statistics of clinical parameters by model sampling; and 3) recover corrupted or missing signal epochs by synthesis.",
keywords = "ARMA, benchmarking, modeling, PCA, photoplethysmography, signal synthesis, statistical validation, subject simulation",
author = "Diego Mart{\'i}n-Mart{\'i}nez and Pablo Casaseca-de-la-Higuera and Marcos Mart{\'i}n-Fern{\'a}ndez and Carlos Alberola-L{\'o}pez",
year = "2013",
month = "4",
day = "12",
doi = "10.1109/TBME.2013.2257770",
language = "English",
volume = "60",
pages = "2432--2441",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE",
number = "9",

}

Stochastic modeling of the PPG signal : a synthesis-by-analysis approach with applications. / Martín-Martínez, Diego; Casaseca-de-la-Higuera, Pablo; Martín-Fernández, Marcos; Alberola-López, Carlos.

In: IEEE Transactions on Biomedical Engineering, Vol. 60, No. 9, 12.04.2013, p. 2432-2441.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Stochastic modeling of the PPG signal

T2 - a synthesis-by-analysis approach with applications

AU - Martín-Martínez, Diego

AU - Casaseca-de-la-Higuera, Pablo

AU - Martín-Fernández, Marcos

AU - Alberola-López, Carlos

PY - 2013/4/12

Y1 - 2013/4/12

N2 - In this paper, we propose a stochastic model of photoplethysmographic signals that is able to synthesize an arbitrary number of other statistically equivalent signals to the one under analysis. To that end, we first preprocess the pulse signal to normalize and time-align pulses. In a second stage, we design a single-pulse model, which consists of ten parameters. In the third stage, the time evolution of this ten-parameter vector is approximated by means of two autoregressive moving average models, one for the trend and one for the residue; this model is applied after a decorrelation step which let us to process each vector component in parallel. The experiments carried out show that the model we here propose is able to maintain the main features of the original signal; this is accomplished by means of both a linear spectral analysis and also by comparing two measures obtained from a nonlinear analysis. Finally, we explore the capability of the model to: 1) track physical activity; 2) obtain statistics of clinical parameters by model sampling; and 3) recover corrupted or missing signal epochs by synthesis.

AB - In this paper, we propose a stochastic model of photoplethysmographic signals that is able to synthesize an arbitrary number of other statistically equivalent signals to the one under analysis. To that end, we first preprocess the pulse signal to normalize and time-align pulses. In a second stage, we design a single-pulse model, which consists of ten parameters. In the third stage, the time evolution of this ten-parameter vector is approximated by means of two autoregressive moving average models, one for the trend and one for the residue; this model is applied after a decorrelation step which let us to process each vector component in parallel. The experiments carried out show that the model we here propose is able to maintain the main features of the original signal; this is accomplished by means of both a linear spectral analysis and also by comparing two measures obtained from a nonlinear analysis. Finally, we explore the capability of the model to: 1) track physical activity; 2) obtain statistics of clinical parameters by model sampling; and 3) recover corrupted or missing signal epochs by synthesis.

KW - ARMA

KW - benchmarking

KW - modeling

KW - PCA

KW - photoplethysmography

KW - signal synthesis

KW - statistical validation

KW - subject simulation

U2 - 10.1109/TBME.2013.2257770

DO - 10.1109/TBME.2013.2257770

M3 - Article

VL - 60

SP - 2432

EP - 2441

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 9

ER -