Conference paper
Frequency Constrained ShiftCP Modeling of Neuroimaging Data
The shift invariant multi-linear model based on the CandeComp/PARAFAC (CP) model denoted ShiftCP has proven useful for the modeling of latency changes in trial based neuroimaging data[17]. In order to facilitate component interpretation we presently extend the shiftCP model such that the extracted components can be constrained to pertain to predefined frequency ranges such as alpha, beta and gamma activity.
To infer the number of components in the model we propose to apply automatic relevance determination by imposing priors that define the range of variation of each component of the shiftCP model and learning the hyper-parameters of these priors during model estimation.
Language: | English |
---|---|
Publisher: | IEEE |
Year: | 2011 |
Pages: | 127-131 |
Proceedings: | Asilomar Conference on Signals, Systems, and Computers |
ISBN: | 1467303216 , 1467303232 , 9781467303217 , 9781467303231 , 1467303224 and 9781467303224 |
ISSN: | 10586393 and 25762303 |
Types: | Conference paper |
DOI: | 10.1109/ACSSC.2011.6189969 |
ORCIDs: | Mørup, Morten and Hansen, Lars Kai |
Analytical models Brain models CandeComp/PARAFAC model Data models Electroencephalography Frequency domain analysis Mathematical model alpha activity automatic relevance determination beta activity component interpretation electroencephalography frequency constrained ShiftCP modeling gamma activity hyper-parameter learning medical signal processing model estimation neurophysiology shift invariant multilinear model trial based neuroimaging data