Democritus University of Thrace (DUTH)
Χρήση τεχνικών μηχανικής μάθησης στην ιατρική πληροφορική
Abstract
dc:descriptionIn the present dissertation our research effort concerns the scientific field of Machine Learning in clinical data. More specifically, the contribution of this doctoral dissertationi s that a systematic study and research was carried out in order to design, implement and evaluate an innovative data preprocessing method which transforms the original data set into a new data set with a smaller feature size, improves the classification performance in some classifiers and greatly reduces the classification time since the transformed dataset has fewer variables than the original.The method was tested in five data sets where it was compared with other data preprocessing methods such as Principal Component Analysis and Evolutionary Search.The results of our research showed that the proposed method greatly improves the classification performance compared to the other two data preprocessing methods in all data sets applied.
Degree
thesis:*- Grantor dc:publisher
- Democritus University of Thrace (DUTH)
- Year dc:date
- 2021
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Iliou, Theodoros
- Ηλίου, Θεόδωρος
Subjects
dc:subject × 8Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/49074