Abstract
The research work is presented here in two parts. The one comprises research on the applicability of machine learning techniques for the early identification of chromosomal abnormalities. It is shown in part I that the ANNs achieve better results than other existing methods in terms of diagnostic rate (DR) of chromosomal abnormalities (100% DR of T21) at a lower false positive rate.
The work presented in part II of the thesis has been done under a three-years research project for the analysis of the folk music of Cyprus and the Eastern Mediterranean Countries and it was funded by the Research Promotion Foundation of the Republic of Cyprus. The COSFIRE filters that have been found effective for 2D and 3D signals, had been adapted for 1D music signals and their effectiveness in different applications has been studied and the results are reported.
The ultimate objective of this thesis is the development of machine learning techniques that can be validated in real data in medicine and musicology and that can have practical value.
The work presented in part II of the thesis has been done under a three-years research project for the analysis of the folk music of Cyprus and the Eastern Mediterranean Countries and it was funded by the Research Promotion Foundation of the Republic of Cyprus. The COSFIRE filters that have been found effective for 2D and 3D signals, had been adapted for 1D music signals and their effectiveness in different applications has been studied and the results are reported.
The ultimate objective of this thesis is the development of machine learning techniques that can be validated in real data in medicine and musicology and that can have practical value.
| Original language | English |
|---|---|
| Qualification | Doctor of Philosophy |
| Awarding Institution |
|
| Supervisors/Advisors |
|
| Award date | 13-Dec-2016 |
| Place of Publication | [Groningen] |
| Publisher | |
| Print ISBNs | 978-90-367-9393-3 |
| Electronic ISBNs | 978-90-367-9392-6 |
| Publication status | Published - 2016 |