Özlem Öztürk

Learn More
Although potentially harmful effects of heavy metals are well known, limited numbers of studies exist regarding their relationship with autism. The aim of this study was to investigate urine levels of some heavy metals such as of chromium (Cr), cadmium (Cd), and lead (Pb) in children with autism and healthy subjects. Urine levels of Cr, Cd, and Pb were(More)
In this paper, we address the lexicon design problem in Turkish large vocabulary speech recognition. Although we focus only on Turkish, the methods described here are general enough that they can be considered for other agglutinative languages like Finnish, Korean etc. In an agglutinative language, several words can be created from a single root word using(More)
Considering the increasing importance of adaptive approaches in CALL systems, this study implemented a machine learning based student modeling middleware with Bayesian networks. The profiling approach of the student modeling system is based on Felder and Silverman’s Learning Styles Model and Felder and Soloman’s Index of Learning Styles Questionnaire. The(More)
Naturalness of synthetic speech highly depends on appropriate modeling of prosodic aspects. Mostly, three prosody components are modeled: segmental duration, pitch contour and intensity. In this study, we present our work on modeling segmental duration in Turkish using machinelearning algorithms, especially Classification and Regression Trees (CART). The(More)
The main objective of this research is to examine child cancer cases in Zonguldak/Turkey descriptively in epidemiological aspect with the help of GIS. Universe of the study is composed of 60 children between 1 and 19 years old who were treated in Children Oncology Clinic with a diagnosis of cancer. Whole universe was reached without selecting a sample in(More)
Naturalness of synthetic speech depends on appropriate modeling of prosodic aspects. Mostly, three prosody components are modeled: segmental duration, pitch contour and intensity. In this study, we present our work on modeling segmental duration in Turkish by using machine-learning algorithms. The models predict phone durations based on attributes such as(More)
This study was performed to determine the effects of a stress management training program that was administered to adolescents in prison. This was a semi-experimental study that used pretests and posttests in controlled groups; it was performed between June 2012 and March 2013 in a closed prison for children and adolescents. The study was completed with the(More)
  • 1