Godwin M. A. Houdji

Mr. Godwin M. A. Houdji

Université d'Abomey-Calavi, Abomey-Calavi, Benin
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 November 2022 in Electronics
Verified
Journal Article
Open access
PDF file
TJThierry Rock JOSSOU
Thierry Rock JOSSOU
TZtahori zakaria
tahori zakaria
GHGodwin M. A. Houdji
Godwin M. A. Houdji
DMDaton Medenou
Daton Medenou
ALAbdelali Lasfar
Abdelali Lasfar
AEAziz ETTAHIR
Aziz ETTAHIR
The early prediction of onset labour is critical for avoiding the risk of death due to pregnancy delay. Low-income countries often struggle to deliver timely service to pregnant women due to a lack of infrastructure and healthcare facilities, resulting in pregnancy complications and, eventually, death. In this regard, several artificial-intelligence-based methods have been proposed based on the detection of contractions using electrohysterogram (EHG) signals. However, the forecasting of pregnancy contractions based on real-time EHG signals is a challenging task. This study proposes a novel model based on neural basis expansion analysis for interpretable time series (N-BEATS) which predicts labour based on EHG forecasting and contraction classification over a given time horizon. The publicly available TPEHG database of Physiobank was exploited in order to train and test the model, where signals from full-term pregnant women and signals recorded after 26 weeks of gestation were collected. For these signals, the 30 most commonly used classification parameters in the literature were calculated, and principal component analysis (PCA) was utilized to select the 15 most representative parameters (all the domains combined). The results show that neural basis expansion analysis for interpretable time series (N-BEATS) forecasting can forecast EHG signals through training after few iterations. Similarly, the forecasting signal’s duration is determined by the length of the recordings. We then deployed XG-Boost, which achieved the classification accuracy of 99 percent, outperforming the state-of-the-art approaches using a number of classification features greater than or equal to 15.
1

20 July 2022
Verified
Conference Paper
Closed access
TJThierry Rock JOSSOU
Thierry Rock JOSSOU
ZTZakaria Tahori
Zakaria Tahori
GHGodwin M. A. Houdji
Godwin M. A. Houdji
ALAbdelali Lasfar
Abdelali Lasfar
MHMetowanou Heribert
Metowanou Heribert
AEAziz ETTAHIR
Aziz ETTAHIR
As ElectroHyteroGram is recognized as one of the best signatures of uterine contractions during gestation, several parameters can be used to characterize it as well as the contractions. However, not all of these parameters are necessarily useful in distinguishing between labour and physiological contractions. In this work, the principal component analyzis method was used to extract the fifteen best parameters among the thirty most used in the literature. The data used were taken from the publicly available Physiobank database. Samples from both weeks of gestation above and below twenty-six weeks for women who gave birth at full term were considered. The fifteen best parameters were obtained in a random order of appearance, probably depending on other criteria varying from one patient to another. However, with the exception of the Root Mean Square which appears as the parameter representing the very first principal component whatever the patient. And the frequency (peak frequency, mean frequency, median frequency) and nonlinear (sample entropy) parameters most commonly used in the literature are found in our results as main components. Nevertheless, this is within the limits of the available data, which is thirty-five weeks gestation on the Physiobank database.