Semi-blind Independent Component Analysis of functional MRI elicited by continuous listening to music

Tuomas Puolivali*, Fengyu Cong, Vinoo Alluri, Qiu-Hua Lin, Petri Toiviainen, Asoke K. Nandi, Elvira Brattico, Tapani Ristaniemi

*Corresponding author for this work

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperConference articleResearchpeer-review

Abstract

This study presents a method to analyze blood-oxygen-level-dependent (BOLD) functional magnetic resonance imaging (tMRI) signals associated with listening to continuous music. Semi-blind independent component analysis (ICA) was applied to decompose the tMRI data to source level activation maps and their respective temporal courses. The unmixing matrix in the source separation process of ICA was constrained by a variety of acoustic features derived from the piece of music used as the stimulus in the experiment. This allowed more stable estimation and extraction of more activation maps of interest compared to conventional ICA methods.

Original languageEnglish
JournalInternational Conference on Acoustics Speech and Signal Processing ICASSP
Pages (from-to)1310-1314
Number of pages5
ISSN1520-6149
Publication statusPublished - 2013
EventIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) - , Canada
Duration: 26 May 201331 May 2013

Conference

ConferenceIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Country/TerritoryCanada
Period26/05/201331/05/2013

Keywords

  • independent component analysis
  • semi-blind
  • acoustic features
  • natural music
  • functional magnetic resonance imaging
  • SPATIAL ICA
  • TIME-SERIES
  • FMRI DATA
  • STIMULATION

Fingerprint

Dive into the research topics of 'Semi-blind Independent Component Analysis of functional MRI elicited by continuous listening to music'. Together they form a unique fingerprint.

Cite this