VGU RESEARCH REPOSITORY
Please use this identifier to cite or link to this item:
https://epub.vgu.edu.vn/handle/dlibvgu/1268
Title: | Anomaly detection in cardiotocograph signal using deep neural network | Authors: | Tran Phuong Nam | Keywords: | Long short-term memory;Deep learning;Machine learning;Cardiocotograph;Regression | Issue Date: | 2021 | Abstract: | Cardiotocography (CTG) traces, comprised of the fetal heart rate (FHR) and the uterine contraction (UC), are used and interpreted by gynecologists and obstetricians to visually present, measure, and assess the wellbeing of the foetus during the antenatal period by following the International Federation of Gynaecology and Obstetrics (FIGO) guidelines. The research is an attempt to train a model using the CTG values as input to predict the outcome of umbilical artery pH. This process involves using the built-in Long short-term memory (LSTM) deep learning model of Liquid time-constant networks (LTCs)[1]. Several windowing strategies are applied with 2 types of output: regression prediction of pH value and classification. With best accuracy metrics of MAPE 1.16% for regression and 96.43% for classification. There are also several related works for comparison and reference |
URI(1): | http://epub.vgu.edu.vn/handle/dlibvgu/1268 |
Appears in Collections: | Computer Science (CS) |
Files in This Item:
File | Description | Size | Format | Existing users please Login |
---|---|---|---|---|
Anomaly detection in cardiotocograph signal using deep neural network.pdf | 1.5 MB | Adobe PDF |
Page view(s)
51
checked on Mar 29, 2024
Download(s)
22
checked on Mar 29, 2024
Google ScholarTM
Check
Items are protected by © Copyright of Vietnamese - German University Library