Time-varying autoregressive model-based multiple modes particle filtering algorithm for respiratory rate extraction from pulse oximeter

Jinseok Lee; Ki H. Chon

doi:10.1109/TBME.2010.2085437

Time-varying autoregressive model-based multiple modes particle filtering algorithm for respiratory rate extraction from pulse oximeter

Jinseok Lee
, Ki H. Chon

Research output: Contribution to journal › Article › peer-review

37 Citations (Scopus)

Abstract

We present a particle filtering algorithm, which combines both time-invariant (TIV) and time-varying autoregressive (TVAR) models for accurate extraction of breathing frequencies (BFs) that vary either slowly or suddenly. The algorithm sustains its robustness for up to 90 breaths/min (b/m) as well. The proposed algorithm automatically detects stationary and nonstationary breathing dynamics in order to use the appropriate TIV or TVAR algorithm and then uses a particle filter to extract accurate respiratory rates from as low as 6 b/m to as high as 90 b/m. The results were verified on 18 healthy human subjects (16 for metronome and 2 for spontaneous measurements), and the algorithm remained accurate even when the respiratory rate suddenly changed by 24 b/m (either increased or decreased by this amount). Furthermore, simulation examples show that the proposed algorithm remains accurate for SNR ratios as low as -20 dB. We are not aware of any other algorithms that are able to provide accurate TV BF over a wide range of respiratory rates directly from pulse oximeters.

Original language	English
Pages (from-to)	790-794
Number of pages	5
Journal	IEEE Transactions on Biomedical Engineering
Volume	58
Issue number	3 PART 2
DOIs	https://doi.org/10.1109/TBME.2010.2085437
Publication status	Published - Mar 2011

Bibliographical note

Funding Information:
Manuscript received July 8, 2010; accepted September 26, 2010. Date of publication October 11, 2010; date of current version February 18, 2011. This work was supported in part by the Office of Naval Research under work unit N00014-08-1-0244. Asterisk indicates corresponding author. J. Lee is with the Department of Biomedical Engineering, Worcester Polytechnic Institute, Worcester, MA 01609 USA (e-mail: [email protected]). *K. H. Chon is with the Department of Biomedical Engineering, Worcester Polytechnic Institute, Worcester, MA 01609 USA (e-mail: [email protected]). Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org. Digital Object Identifier 10.1109/TBME.2010.2085437

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Autoregressive (AR) model
chronic heart failure (CHF)
chronic obstructive pulmonary disease
optimal parameter search (OPS)
particle filter
pulse oximeters
remote health monitoring
respiratory rate extraction
sleep apnea
sudden infant death syndrome
vital signs

Access to Document

10.1109/TBME.2010.2085437

Cite this

@article{63a155532d22488e9f2214fcf353d3a6,

title = "Time-varying autoregressive model-based multiple modes particle filtering algorithm for respiratory rate extraction from pulse oximeter",

abstract = "We present a particle filtering algorithm, which combines both time-invariant (TIV) and time-varying autoregressive (TVAR) models for accurate extraction of breathing frequencies (BFs) that vary either slowly or suddenly. The algorithm sustains its robustness for up to 90 breaths/min (b/m) as well. The proposed algorithm automatically detects stationary and nonstationary breathing dynamics in order to use the appropriate TIV or TVAR algorithm and then uses a particle filter to extract accurate respiratory rates from as low as 6 b/m to as high as 90 b/m. The results were verified on 18 healthy human subjects (16 for metronome and 2 for spontaneous measurements), and the algorithm remained accurate even when the respiratory rate suddenly changed by 24 b/m (either increased or decreased by this amount). Furthermore, simulation examples show that the proposed algorithm remains accurate for SNR ratios as low as -20 dB. We are not aware of any other algorithms that are able to provide accurate TV BF over a wide range of respiratory rates directly from pulse oximeters.",

keywords = "Autoregressive (AR) model, chronic heart failure (CHF), chronic obstructive pulmonary disease, optimal parameter search (OPS), particle filter, pulse oximeters, remote health monitoring, respiratory rate extraction, sleep apnea, sudden infant death syndrome, vital signs",

author = "Jinseok Lee and Chon, \{Ki H.\}",

note = "Funding Information: Manuscript received July 8, 2010; accepted September 26, 2010. Date of publication October 11, 2010; date of current version February 18, 2011. This work was supported in part by the Office of Naval Research under work unit N00014-08-1-0244. Asterisk indicates corresponding author. J. Lee is with the Department of Biomedical Engineering, Worcester Polytechnic Institute, Worcester, MA 01609 USA (e-mail: [email protected]). *K. H. Chon is with the Department of Biomedical Engineering, Worcester Polytechnic Institute, Worcester, MA 01609 USA (e-mail: [email protected]). Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org. Digital Object Identifier 10.1109/TBME.2010.2085437",

year = "2011",

month = mar,

doi = "10.1109/TBME.2010.2085437",

language = "English",

volume = "58",

pages = "790--794",

journal = "IEEE Transactions on Biomedical Engineering",

issn = "0018-9294",

publisher = "IEEE Computer Society",

number = "3 PART 2",

}

TY - JOUR

T1 - Time-varying autoregressive model-based multiple modes particle filtering algorithm for respiratory rate extraction from pulse oximeter

AU - Lee, Jinseok

AU - Chon, Ki H.

N1 - Funding Information: Manuscript received July 8, 2010; accepted September 26, 2010. Date of publication October 11, 2010; date of current version February 18, 2011. This work was supported in part by the Office of Naval Research under work unit N00014-08-1-0244. Asterisk indicates corresponding author. J. Lee is with the Department of Biomedical Engineering, Worcester Polytechnic Institute, Worcester, MA 01609 USA (e-mail: [email protected]). *K. H. Chon is with the Department of Biomedical Engineering, Worcester Polytechnic Institute, Worcester, MA 01609 USA (e-mail: [email protected]). Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org. Digital Object Identifier 10.1109/TBME.2010.2085437

PY - 2011/3

Y1 - 2011/3

N2 - We present a particle filtering algorithm, which combines both time-invariant (TIV) and time-varying autoregressive (TVAR) models for accurate extraction of breathing frequencies (BFs) that vary either slowly or suddenly. The algorithm sustains its robustness for up to 90 breaths/min (b/m) as well. The proposed algorithm automatically detects stationary and nonstationary breathing dynamics in order to use the appropriate TIV or TVAR algorithm and then uses a particle filter to extract accurate respiratory rates from as low as 6 b/m to as high as 90 b/m. The results were verified on 18 healthy human subjects (16 for metronome and 2 for spontaneous measurements), and the algorithm remained accurate even when the respiratory rate suddenly changed by 24 b/m (either increased or decreased by this amount). Furthermore, simulation examples show that the proposed algorithm remains accurate for SNR ratios as low as -20 dB. We are not aware of any other algorithms that are able to provide accurate TV BF over a wide range of respiratory rates directly from pulse oximeters.

AB - We present a particle filtering algorithm, which combines both time-invariant (TIV) and time-varying autoregressive (TVAR) models for accurate extraction of breathing frequencies (BFs) that vary either slowly or suddenly. The algorithm sustains its robustness for up to 90 breaths/min (b/m) as well. The proposed algorithm automatically detects stationary and nonstationary breathing dynamics in order to use the appropriate TIV or TVAR algorithm and then uses a particle filter to extract accurate respiratory rates from as low as 6 b/m to as high as 90 b/m. The results were verified on 18 healthy human subjects (16 for metronome and 2 for spontaneous measurements), and the algorithm remained accurate even when the respiratory rate suddenly changed by 24 b/m (either increased or decreased by this amount). Furthermore, simulation examples show that the proposed algorithm remains accurate for SNR ratios as low as -20 dB. We are not aware of any other algorithms that are able to provide accurate TV BF over a wide range of respiratory rates directly from pulse oximeters.

KW - Autoregressive (AR) model

KW - chronic heart failure (CHF)

KW - chronic obstructive pulmonary disease

KW - optimal parameter search (OPS)

KW - particle filter

KW - pulse oximeters

KW - remote health monitoring

KW - respiratory rate extraction

KW - sleep apnea

KW - sudden infant death syndrome

KW - vital signs

UR - https://www.scopus.com/pages/publications/79952010477

U2 - 10.1109/TBME.2010.2085437

DO - 10.1109/TBME.2010.2085437

M3 - Article

C2 - 20937577

AN - SCOPUS:79952010477

SN - 0018-9294

VL - 58

SP - 790

EP - 794

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

IS - 3 PART 2

ER -

Time-varying autoregressive model-based multiple modes particle filtering algorithm for respiratory rate extraction from pulse oximeter

Abstract

Bibliographical note

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this