|
Activity Number:
|
524
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 2, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Business and Economics Statistics Section
|
| Abstract - #307943 |
|
Title:
|
Discrimination of Nonstationary Signals Using Localized Higher-Order Spectra
|
|
Author(s):
|
Hernando C. Ombao*+
|
|
Companies:
|
University of Illinois
|
|
Address:
|
725 S. Wright St., Champaign, IL, 61820,
|
|
Keywords:
|
Non-linear ; Non-stationary ; Localized transforms ; Discrimination ; Classification ; Brain Signals
|
|
Abstract:
|
We consider a data set that consists of MEG (magnetoencephalogram) signals recorded from healthy controls and schizophrenic patients. Our neuroscientist collaborators are interested in identifying features that can separate the two groups with the hope that these physiological measures may be used in conjunction with behavioral measures for patient diagnosis. In this talk, we will develop an automatic procedure for time-frequency spectral feature selection via localized transforms. Moreover, given the high degree of complexity of brain signals, we will consider the time-evolutionary spectrum of non-linear transforms as potential features for classification and discrimination.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2007 program |
