Doctoral Dissertations
Keywords and Phrases
Cardiotocography; Computational Intelligence; Feature Extraction; Fetal Heart Rate; Machine Learning; Uterine Contractions
Abstract
“Modeling and prediction of complex systems is a challenging problem due to the sub-system interactions and dependencies. This research examines combining various computational intelligence algorithms and modeling techniques to provide insights into these complex processes and allow for better decision making. This hybrid methodology provided additional capabilities to analyze and predict the overall system behavior where a single model cannot be used to understand the complex problem. The systems analyzed here are flooding events and fetal health care. The impact of floods on road infrastructure is investigated using graph theory, agent-based traffic simulation, and Long Short-Term Memory deep learning to predict water level rise from river gauge height. Combined with existing infrastructure models, these techniques provide a 15-minute interval for making closure decisions rather than the current 6-hour interval. The second system explored is fetal monitoring, which is essential to diagnose severe fetal conditions such as acidosis. Support Vector Machine and Random Forest were compared to identify the best model for classification of fetal state. This model provided a more accurate classification than existing research on the CTG. A deep learning forecasting model was developed to predict the future values for fetal heart rate and uterine contractions. The forecasting and classification algorithms are then integrated to evaluate the future condition of the fetus. The final model can predict the fetal state 4 minutes ahead to help the obstetricians to plan necessary interventions for preventing acidosis and asphyxiation. In both cases, time series predictions using hybrid modeling provided superior results to existing methods to predict complex behaviors”--Abstract, page iv.
Advisor(s)
Corns, Steven
Committee Member(s)
Long, Suzanna, 1961-
Qin, Ruwen
Dagli, Cihan H., 1949-
Hu, XianBiao
Department(s)
Engineering Management and Systems Engineering
Degree Name
Ph. D. in Systems Engineering
Publisher
Missouri University of Science and Technology
Publication Date
Summer 2020
Journal article titles appearing in thesis/dissertation
- Agent based modeling for flood inundation mapping and rerouting
- Flood prediction and uncertainty estimation using deep learning
- Evaluation of support vector machines and random forest classifiers in a real-time fetal monitoring system based on cardiotocography data
- Integrated deep learning and supervised machine learning model for fetal heart rate prediction and classification of acidosis
Pagination
xiii, 116 pages
Note about bibliography
Includes bibliographic references.
Rights
© 2020 Vinayaka Nagendra Harikishan Gude Divya Samapth, All rights reserved.
Document Type
Dissertation - Open Access
File Type
text
Language
English
Thesis Number
T 11745
Electronic OCLC #
1198499034
Recommended Citation
Gude, Vinayaka, "Predicting complex system behavior using hybrid modeling and computational intelligence" (2020). Doctoral Dissertations. 2915.
https://scholarsmine.mst.edu/doctoral_dissertations/2915
Comments
This research has been partially funded by the Ozark Biomedical Initiative, in association with the Phelps County Regional Medical Center, Rolla, MO, USA.