Date of Graduation
5-2022
Document Type
Dissertation
Degree Name
Doctor of Philosophy in Engineering (PhD)
Degree Level
Graduate
Department
Industrial Engineering
Advisor/Mentor
Chaovalitwongse, W. Art
Committee Member
Rainwater, Chase E.
Second Committee Member
Nyflot, Matthew
Third Committee Member
Zhang, Shengfan
Keywords
Decision Support System; Information Science; Machine Learning; Predictive Analytics; Representation Learning
Abstract
Machine learning approaches for prediction play an integral role in modern-day decision supports system. An integral part of the process is extracting interest variables or features to describe the input data. Then, the variables are utilized for training machine-learning algorithms to map from the variables to the target output. After the training, the model is validated with either validation or testing data before making predictions with a new dataset. Despite the straightforward workflow, the process relies heavily on good feature representation of data. Engineering suitable representation eases the subsequent actions and copes with many practical issues that potentially prevent the workflow from being effective. Modern approaches alternatively create learning algorithms to derive representing features. The goal is to learn a set of vector components with helpful characteristics. Once obtained, the data are projected to the vectors and utilized as the feature. This dissertation explores the utility of supervised representation learning and addresses critical issues integrating the learning techniques into the workflow to improve prediction performance.
This dissertation aims to address the difficulty of feature engineering using supervised representation learning. This dissertation argues that the method is useful for developing machine learning prediction in the domain where expert knowledge into the gathered data is limited such that expert-define features do not lead to well-perform prediction. In defense of this merit, the dissertation demonstrates the advantages through four developments of the predictions in Neuroscience and Medical research, namely cortical regions mapping, identifying errors in radiotherapy, Sarcoma survival prediction and risk stratification of Sarcoma patients.
Citation
Thammasorn, P. (2022). Supervised Representation Learning for Improving Prediction Performance in Medical Decision Support applications. Graduate Theses and Dissertations Retrieved from https://scholarworks.uark.edu/etd/4478
Included in
Artificial Intelligence and Robotics Commons, Databases and Information Systems Commons, Industrial Engineering Commons, Industrial Technology Commons, Operational Research Commons, Systems Engineering Commons
