Frequency Constrained ShiftCP Modeling of Neuroimaging Data

Morten Mørup; Lars Kai Hansen; Kristoffer H. Madsen

doi:10.1109/ACSSC.2011.6189969

Frequency Constrained ShiftCP Modeling of Neuroimaging Data

Morten Mørup (Invited author), Lars Kai Hansen (Invited author), Kristoffer H. Madsen (Invited author)

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

327 Downloads (Pure)

Abstract

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.

Original language	English
Title of host publication	2011 Conference Record of the Forty Fifth Asilomar Conference on Signals, Systems and Computers (ASILOMAR)
Publisher	IEEE
Publication date	2011
Pages	127-131
ISBN (Print)	978-1-4673-0323-1
DOIs	https://doi.org/10.1109/ACSSC.2011.6189969
Publication status	Published - 2011
Event	Asilomar Conference on Signals, Systems, and Computers - Pacific Grove, CA, United States Duration: 6 Nov 2011 → 9 Nov 2011

Conference

Conference	Asilomar Conference on Signals, Systems, and Computers
Country	United States
City	Pacific Grove, CA
Period	06/11/2011 → 09/11/2011

Bibliographical note

(c) 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.

Access to Document

10.1109/ACSSC.2011.6189969

AsilomarPaperFreqConstrained

http://www.asilomarssc.org/

Fingerprint Dive into the research topics of 'Frequency Constrained ShiftCP Modeling of Neuroimaging Data'. Together they form a unique fingerprint.

Cite this

@inproceedings{5caf8529491447cca36ee73c5bb1ddef,

title = "Frequency Constrained ShiftCP Modeling of Neuroimaging Data",

abstract = "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.",

author = "Morten M{\o}rup and Hansen, {Lars Kai} and Madsen, {Kristoffer H.}",

note = "(c) 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.; Asilomar Conference on Signals, Systems, and Computers, SS&C ; Conference date: 06-11-2011 Through 09-11-2011",

year = "2011",

doi = "10.1109/ACSSC.2011.6189969",

language = "English",

isbn = "978-1-4673-0323-1",

pages = "127--131",

booktitle = "2011 Conference Record of the Forty Fifth Asilomar Conference on Signals, Systems and Computers (ASILOMAR)",

publisher = "IEEE",

address = "United States",

}

Mørup, M , Hansen, LK & Madsen, KH 2011, Frequency Constrained ShiftCP Modeling of Neuroimaging Data. in 2011 Conference Record of the Forty Fifth Asilomar Conference on Signals, Systems and Computers (ASILOMAR). IEEE, pp. 127-131, Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, United States, 06/11/2011. https://doi.org/10.1109/ACSSC.2011.6189969

Frequency Constrained ShiftCP Modeling of Neuroimaging Data. / Mørup, Morten (Invited author); Hansen, Lars Kai (Invited author); Madsen, Kristoffer H. (Invited author).

2011 Conference Record of the Forty Fifth Asilomar Conference on Signals, Systems and Computers (ASILOMAR). IEEE, 2011. p. 127-131.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Frequency Constrained ShiftCP Modeling of Neuroimaging Data

AU - Mørup, Morten

AU - Hansen, Lars Kai

AU - Madsen, Kristoffer H.

N1 - (c) 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.

PY - 2011

Y1 - 2011

N2 - 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.

AB - 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.

U2 - 10.1109/ACSSC.2011.6189969

DO - 10.1109/ACSSC.2011.6189969

M3 - Article in proceedings

SN - 978-1-4673-0323-1

SP - 127

EP - 131

BT - 2011 Conference Record of the Forty Fifth Asilomar Conference on Signals, Systems and Computers (ASILOMAR)

PB - IEEE

T2 - Asilomar Conference on Signals, Systems, and Computers

Y2 - 6 November 2011 through 9 November 2011

ER -