NORMA eResearch @NCI Library

Abnormal Foetuses Classification Based on Cardiotocography Recordings Using Machine Learning and Deep Learning Algorithms

Tamer, Jassem Alhaj (2020) Abnormal Foetuses Classification Based on Cardiotocography Recordings Using Machine Learning and Deep Learning Algorithms. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[img]
Preview
PDF (Configuration manual)
Download (6MB) | Preview

Abstract

Cardiotocography (CTG), known as Electronic Foetal Monitoring, is typically performed at
third trimester during pregnancy and in labour to primarily monitor the relationship between foetal
heart rate (FHR) and contractions of the uterus (UC). CTG outcomes allow experts to determine
the health of the foetus and to detect any foetal impairments. This research project examined the
CTG recordings overlaid with various well-established machine learning and deep learning
algorithms with the objective of identifying the best performing algorithm capable of classifying
abnormal (suspect or pathologic) foetuses. Accuracy, recall and specificity are considered as
significant performance metrics to identify the best performing model. Machine learning (support
vector machine (SVM), C5.0 decision tree (C5.0), random forest (RF), generalised linear model
(GLM), extreme gradient boosting (XGBoost), k-nearest neighbour (KNN) and naïve Bayes (NB))
and deep leaning models (multilayer perceptron neural networks (MLPNNs)) were applied. SVM
model showed promising performance measures towards the classification of abnormal foetuses
based on CTG recordings at accuracy of 90.65%, recall of 96.32% and specificity of 89.09%.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 18 Jan 2021 13:03
Last Modified: 18 Jan 2021 13:03
URI: http://norma.ncirl.ie/id/eprint/4360

Actions (login required)

View Item View Item