Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Big Data Mining and ...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Big Data Mining and Analytics
Article . 2023 . Peer-reviewed
Data sources: Crossref
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Big Data Mining and Analytics
Article . 2023
Data sources: DOAJ
https://dx.doi.org/10.60692/c9...
Other literature type . 2023
Data sources: Datacite
https://dx.doi.org/10.60692/pw...
Other literature type . 2023
Data sources: Datacite
versions View all 4 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Extraction of Fetal Electrocardiogram by Combining Deep Learning and SVD-ICA-NMF Methods

استخراج مخطط كهربية القلب للجنين من خلال الجمع بين التعلم العميق وطرق SVD - ICA - NMF
Authors: Said Ziani; Yousef Farhaoui; Mohammed Moutaib;

Extraction of Fetal Electrocardiogram by Combining Deep Learning and SVD-ICA-NMF Methods

Abstract

Cet article traite de la détection des signaux FECG de l'électrocardiogramme fœtal à partir de la dérivation abdominale à canal unique. Il est basé sur le réseau neuronal convolutionnel (CNN) combiné à des méthodes mathématiques avancées, telles que l'analyse en composantes indépendantes (ICA), la décomposition en valeurs singulières (SVD) et une technique de réduction des dimensions comme la factorisation matricielle non négative (NMF). En raison de la fréquence très disproportionnée de la fréquence cardiaque du fœtus par rapport à celle de la mère, la représentation de l'échelle de temps distingue clairement l'activité électrique fœtale en termes d'énergie. En outre, nous pouvons démêler les différentes composantes de l'ECG fœtal, qui servent d'entrées au modèle CNN pour optimiser le signal FECG réel, désigné par FECGr, qui est récupéré en utilisant le processus SVD-ICA. Les résultats démontrent l'efficacité de cette approche innovante, qui peut être déployée en temps réel.

Este artículo trata sobre la detección de señales de electrocardiograma fetal FECG a partir de derivaciones abdominales de un solo canal. Se basa en la Red Neural Convolucional (CNN) combinada con métodos matemáticos avanzados, como el Análisis de Componentes Independientes (ICA), la Descomposición de Valores Singulares (SVD) y una técnica de reducción de dimensiones como la Factorización de Matrices No Negativas (NMF). Debido a la frecuencia altamente desproporcionada de la frecuencia cardíaca del feto en comparación con la de la madre, la representación de la escala de tiempo distingue claramente la actividad eléctrica fetal en términos de energía. Además, podemos desenredar los diversos componentes del ECG fetal, que sirven como entradas al modelo CNN para optimizar la señal FECG real, denotada por FECGr, que se recupera utilizando el proceso SVD-ICA. Los hallazgos demuestran la eficiencia de este enfoque innovador, que puede implementarse en tiempo real.

This paper deals with detecting fetal electrocardiogram FECG signals from single-channel abdominal lead.It is based on the Convolutional Neural Network (CNN) combined with advanced mathematical methods, such as Independent Component Analysis (ICA), Singular Value Decomposition (SVD), and a dimension-reduction technique like Nonnegative Matrix Factorization (NMF).Due to the highly disproportionate frequency of the fetus's heart rate compared to the mother's, the time-scale representation clearly distinguishes the fetal electrical activity in terms of energy.Furthermore, we can disentangle the various components of fetal ECG, which serve as inputs to the CNN model to optimize the actual FECG signal, denoted by FECGr, which is recovered using the SVD-ICA process.The findings demonstrate the efficiency of this innovative approach, which may be deployed in real-time.

تتناول هذه الورقة الكشف عن إشارات مخطط كهربية القلب للجنين من الرصاص البطني أحادي القناة. وهي تستند إلى الشبكة العصبية الالتفافية (CNN) جنبًا إلى جنب مع الأساليب الرياضية المتقدمة، مثل تحليل المكونات المستقلة (ICA)، وتحلل القيمة المفردة (SVD)، وتقنية تقليل الأبعاد مثل عامل المصفوفة غير السلبي (NMF). نظرًا للتردد غير المتناسب للغاية لمعدل ضربات قلب الجنين مقارنةً بمعدل ضربات قلب الأم، فإن تمثيل المقياس الزمني يميز بوضوح النشاط الكهربائي للجنين من حيث الطاقة. علاوة على ذلك، يمكننا فصل المكونات المختلفة لمخطط كهربية القلب للجنين، والتي تعمل كمدخلات لنموذج CNN لتحسين إشارة FECG الفعلية، المشار إليها بواسطة FECGr، والتي يتم استردادها باستخدام عملية SVD - ICA. توضح النتائج كفاءة هذا النهج المبتكر، والتي يمكن نشرها في الوقت الفعلي.

Keywords

Blind Source Separation and Independent Component Analysis, Artificial intelligence, Cognitive Neuroscience, Convolutional neural network, Independent component analysis, Speech recognition, Pattern recognition (psychology), Quantum mechanics, convolutional neural network (cnn), Epilepsy Detection, Matrix decomposition, deep learning (dl), Health Sciences, Arrhythmia Detection, FOS: Mathematics, Deep Learning for EEG, Eigenvalues and eigenvectors, fetal electrocardiogram, feature extraction, Physics, Singular value decomposition, Pure mathematics, Life Sciences, Non-negative matrix factorization, QA75.5-76.95, Analysis of Electrocardiogram Signals, Brain-Computer Interfaces in Neuroscience and Medicine, ECG Signal, Independent Component Analysis, Computer science, Dimensionality reduction, Dimension (graph theory), Electronic computers. Computer science, Signal Processing, Computer Science, Physical Sciences, Medicine, Feature extraction, Cardiology and Cardiovascular Medicine, Mathematics, Neuroscience

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    19
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Top 10%
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Top 10%
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Top 10%
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
19
Top 10%
Top 10%
Top 10%
gold
Related to Research communities