There are many active research projects accessing and applying shared ADNI data. Use the search above to find specific research focuses on the active ADNI investigations. This information is requested annually as a requirement for data access.
| Principal Investigator | |
| Principal Investigator's Name: | Nikša Jakovljević |
| Institution: | University of Novi Sad, Faculty of Technical Sciences |
| Department: | Department of Power, Electronic and Telecommunicat |
| Country: | |
| Proposed Analysis: | The aim of our study is exploring possibilities of nonlinear mode decomposition (NMD) in functional magnetic resonance imaging data analysis to investigate changes in Alzheimer's disease. NMD is a method to decompose time series into a set of oscillatory components, by detection of the ridges of the basic modes and of high harmonics of nonlinear, time-varying, oscillatory processes. By decomposing BOLD signal into sub-components oscillating at different frequencies, we want to detect different coherence brain patterns. |
| Additional Investigators | |
| Investigator's Name: | Tatjana Lončar-Turukalo |
| Proposed Analysis: | Upon NMD decomposition she will perform statistical analysis of the identified NMD frequencies in healthy and diseased subjects. Based on the features extracted from NMD analysis, she will perform unsupervised learning to evaluate the performance of clustering algorithms in the separation of healthy and diseased subjects. Depending on its performance, further evaluation of classification algorithms and semi-supervised approaches will be done. The ROI analysis might be as well frequency dependent, i.e. we will investigate correlations among signals where certain frequency component is present in order to identify eventually present/absent networks at different frequency bands. We will compare amplitudes of components as well. |
