Aristotle University Of Thessaloniki (AUTH)
Oscillation features time series and linear - nonlinear dynamic regression models with application in predicting epileptic seizure
Abstract
dc:descriptionThe present PhD thesis combines methods of linear and nonlinear time series analysis and of dynamical systems analysis with statistical methods with aim to study and develop statistical measures computed directly on one time series and on extracted time series of oscillation features. Basic aim of this dissertation is the use of these measures for detecting dynamic changes in the brain activity of epileptic patients, as seizure approaches. In particular, two methods for determining the optimum time series model in the cases of linear and nonlinear modeling were developed, and measures based on model fitting and measures computed on features time series were defined. These measures were used for detecting dynamic change in preictal periods and they performed very well. The comparison of said measures with other, commonly used in practice, ranked them among the best.
Degree
thesis:*- Grantor dc:publisher
- Aristotle University Of Thessaloniki (AUTH)
- Year dc:date
- 2009
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Vlachos, Ioannis
- Βλάχος, Ιωάννης
Subjects
dc:subject × 12Rights
- Language dc:language
- eng
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/21251