Time-frequency characterization of tri-axial accelerometer data for fetal movement detection

Mohamed Salah Khlif; Boualem Boashash; Siamak Layeghy; Taoufik Ben-Jabeur; M. Mesbah; C. East; Paul B Colditz

doi:10.1109/ISSPIT.2011.6151607

Time-frequency characterization of tri-axial accelerometer data for fetal movement detection

Mohamed Salah Khlif, Boualem Boashash, Siamak Layeghy, Taoufik Ben-Jabeur, M. Mesbah, C. East, Paul B Colditz

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

6 Citations (Scopus)

Abstract

Monitoring fetal wellbeing is a significant problem in modern obstetrics. Clinicians have become increasingly aware of the link between fetal activity and its well-being. Using data acquired by accelerometry sensors, we use TFDs such as the spectrogram and modified B distribution (MBD) to characterize fetal movements in the time-frequency (TF) domain. This paper reports a fetal activity detection method based on the root-mean-square (RMS) of time series and evaluates its performance against real-time ultrasound imaging, taken as the gold standard. The evaluation showed better performance with the RMS-based detector as compared to maternal perception. The evaluation also showed that the detector performance is age-dependent and that fetal movement is characterized by different TF morphology. Time-frequency distributions (TFDs) with better resolution such as MBD are investigated for TF-based techniques for the detection of fetal movements.

Original language	English
Title of host publication	IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2011
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	466-471
Number of pages	6
ISBN (Print)	9781467307529
DOIs	https://doi.org/10.1109/ISSPIT.2011.6151607
Publication status	Published - 2011
Externally published	Yes
Event	IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) 2011 - University of Deusto-Deusto Tech, Bilbao, Spain Duration: 14 Dec 2011 → 17 Dec 2011 Conference number: 11th https://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=19420

Conference

Conference	IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) 2011
Abbreviated title	ISSPIT 2011
Country	Spain
City	Bilbao
Period	14/12/11 → 17/12/11
Internet address	https://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=19420

Keywords

Accelerometer
detection
fetal movement
modified B distribution
quadratic TFDs
Spectrogram
time-frequency analysis

Access to Document

10.1109/ISSPIT.2011.6151607

Link to publication in Scopus

Cite this

Khlif, M. S., Boashash, B., Layeghy, S., Ben-Jabeur, T., Mesbah, M., East, C., & Colditz, P. B. (2011). Time-frequency characterization of tri-axial accelerometer data for fetal movement detection. In IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2011 (pp. 466-471). [6151607] IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ISSPIT.2011.6151607

Khlif, Mohamed Salah ; Boashash, Boualem ; Layeghy, Siamak ; Ben-Jabeur, Taoufik ; Mesbah, M. ; East, C. ; Colditz, Paul B. / Time-frequency characterization of tri-axial accelerometer data for fetal movement detection. IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2011. IEEE, Institute of Electrical and Electronics Engineers, 2011. pp. 466-471

@inproceedings{e9b88bcbeb604bbd81839a1c1c2b19f3,

title = "Time-frequency characterization of tri-axial accelerometer data for fetal movement detection",

abstract = "Monitoring fetal wellbeing is a significant problem in modern obstetrics. Clinicians have become increasingly aware of the link between fetal activity and its well-being. Using data acquired by accelerometry sensors, we use TFDs such as the spectrogram and modified B distribution (MBD) to characterize fetal movements in the time-frequency (TF) domain. This paper reports a fetal activity detection method based on the root-mean-square (RMS) of time series and evaluates its performance against real-time ultrasound imaging, taken as the gold standard. The evaluation showed better performance with the RMS-based detector as compared to maternal perception. The evaluation also showed that the detector performance is age-dependent and that fetal movement is characterized by different TF morphology. Time-frequency distributions (TFDs) with better resolution such as MBD are investigated for TF-based techniques for the detection of fetal movements.",

keywords = "Accelerometer, detection, fetal movement, modified B distribution, quadratic TFDs, Spectrogram, time-frequency analysis",

author = "Khlif, {Mohamed Salah} and Boualem Boashash and Siamak Layeghy and Taoufik Ben-Jabeur and M. Mesbah and C. East and Colditz, {Paul B}",

year = "2011",

doi = "10.1109/ISSPIT.2011.6151607",

language = "English",

isbn = "9781467307529",

pages = "466--471",

booktitle = "IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2011",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) 2011, ISSPIT 2011 ; Conference date: 14-12-2011 Through 17-12-2011",

url = "https://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=19420",

}

Khlif, MS, Boashash, B, Layeghy, S, Ben-Jabeur, T, Mesbah, M, East, C & Colditz, PB 2011, Time-frequency characterization of tri-axial accelerometer data for fetal movement detection. in IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2011., 6151607, IEEE, Institute of Electrical and Electronics Engineers, pp. 466-471, IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) 2011, Bilbao, Spain, 14/12/11. https://doi.org/10.1109/ISSPIT.2011.6151607

Time-frequency characterization of tri-axial accelerometer data for fetal movement detection. / Khlif, Mohamed Salah; Boashash, Boualem; Layeghy, Siamak; Ben-Jabeur, Taoufik; Mesbah, M.; East, C.; Colditz, Paul B.

IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2011. IEEE, Institute of Electrical and Electronics Engineers, 2011. p. 466-471 6151607.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Time-frequency characterization of tri-axial accelerometer data for fetal movement detection

AU - Khlif, Mohamed Salah

AU - Boashash, Boualem

AU - Layeghy, Siamak

AU - Ben-Jabeur, Taoufik

AU - Mesbah, M.

AU - East, C.

AU - Colditz, Paul B

N1 - Conference code: 11th

PY - 2011

Y1 - 2011

N2 - Monitoring fetal wellbeing is a significant problem in modern obstetrics. Clinicians have become increasingly aware of the link between fetal activity and its well-being. Using data acquired by accelerometry sensors, we use TFDs such as the spectrogram and modified B distribution (MBD) to characterize fetal movements in the time-frequency (TF) domain. This paper reports a fetal activity detection method based on the root-mean-square (RMS) of time series and evaluates its performance against real-time ultrasound imaging, taken as the gold standard. The evaluation showed better performance with the RMS-based detector as compared to maternal perception. The evaluation also showed that the detector performance is age-dependent and that fetal movement is characterized by different TF morphology. Time-frequency distributions (TFDs) with better resolution such as MBD are investigated for TF-based techniques for the detection of fetal movements.

AB - Monitoring fetal wellbeing is a significant problem in modern obstetrics. Clinicians have become increasingly aware of the link between fetal activity and its well-being. Using data acquired by accelerometry sensors, we use TFDs such as the spectrogram and modified B distribution (MBD) to characterize fetal movements in the time-frequency (TF) domain. This paper reports a fetal activity detection method based on the root-mean-square (RMS) of time series and evaluates its performance against real-time ultrasound imaging, taken as the gold standard. The evaluation showed better performance with the RMS-based detector as compared to maternal perception. The evaluation also showed that the detector performance is age-dependent and that fetal movement is characterized by different TF morphology. Time-frequency distributions (TFDs) with better resolution such as MBD are investigated for TF-based techniques for the detection of fetal movements.

KW - Accelerometer

KW - detection

KW - fetal movement

KW - modified B distribution

KW - quadratic TFDs

KW - Spectrogram

KW - time-frequency analysis

UR - http://www.scopus.com/inward/record.url?scp=84857859403&partnerID=8YFLogxK

U2 - 10.1109/ISSPIT.2011.6151607

DO - 10.1109/ISSPIT.2011.6151607

M3 - Conference Paper

AN - SCOPUS:84857859403

SN - 9781467307529

SP - 466

EP - 471

BT - IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2011

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) 2011

Y2 - 14 December 2011 through 17 December 2011

ER -

Khlif MS, Boashash B, Layeghy S, Ben-Jabeur T, Mesbah M, East C et al. Time-frequency characterization of tri-axial accelerometer data for fetal movement detection. In IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2011. IEEE, Institute of Electrical and Electronics Engineers. 2011. p. 466-471. 6151607 https://doi.org/10.1109/ISSPIT.2011.6151607