Applying fully tensorial ICA to fMRI data
Virta, J., Taskinen, S., & Nordhausen, K. (2016). Applying fully tensorial ICA to fMRI data. In Proceedings of 2016 IEEE Signal Processing in Medicine and Biology Symposium (pp. 1-6). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/SPMB.2016.7846858
© IEEE, 2016. This is a final draft version of an article whose final and definitive form has been published by IEEE. Published in this repository with the kind permission of the publisher.
There are two aspects in functional magnetic resonance imaging (fMRI) data that make them awkward to analyse with traditional multivariate methods - high order and high dimension. The first of these refers to the tensorial nature of observations as array-valued elements instead of vectors. Although this can be circumvented by vectorizing the array, doing so simultaneously loses all the structural information in the original observations. The second aspect refers to the high dimensionality along each dimension making the concept of dimension reduction a valuable tool in the processing of fMRI data. Different methods of tensor dimension reduction are currently gaining popUlarity in literature, and in this paper we apply two recently proposed methods of tensorial independent component analysis to simulated task-based fMRI data. Additionally, as a preprocessing step we introduce a novel extension of PCA for tensors. The simulations show that when extracting a sufficiently large number of principal components, the tensor methods find the task signals very reliably, something the standard temporal independent component analysis (tICA) fails in. ...
PublisherInstitute of Electrical and Electronics Engineers
Parent publication ISBN978-1-5090-6713-8
ConferenceIEEE Signal Processing in Medicine and Biology Symposium
Is part of publicationProceedings of 2016 IEEE Signal Processing in Medicine and Biology Symposium
Publication in research information system
MetadataShow full item record
Showing items with similar title or keywords.
Mansikkamäki, Akseli (2013)The currently available computational methods for the calculation of magnetic coupling constants with density functional theory have been reviewed. These methods include modern approximations to the exchangecorrelation ...
Snowball ICA : A Model Order Free Independent Component Analysis Strategy for Functional Magnetic Resonance Imaging Data Hu, Guoqiang; Waters, Abigail B.; Aslan, Serdar; Frederick, Blaise; Cong, Fengyu; Nickerson, Lisa D. (Frontiers Media, 2020)In independent component analysis (ICA), the selection of model order (i.e., number of components to be extracted) has crucial effects on functional magnetic resonance imaging (fMRI) brain network analysis. Model order ...
Effects of caffeine on neuromuscular function in a non‐fatigued state and during fatiguing exercise Mesquita, Ricardo N. O.; Cronin, Neil J.; Kyröläinen, Heikki; Hintikka, Jukka; Avela, Janna (Cambridge University Press, 2020)Purpose Caffeine enhances exercise performance but its mechanisms of action remain unclear. This study investigated its effects on neuromuscular function in a non‐fatigued state and during fatiguing exercise. Methods Eighteen ...
Guo, Fu-Sheng; Day, Benjamin M.; Chen, Yan-Cong; Tong, Ming-Liang; Mansikkamäki, Akseli; Layfield, Richard A. (Wiley-VCH Verlag, 2017)Abstraction of a chloride ligand from the dysprosium metallocene [(Cpttt)2DyCl] (1Dy Cpttt=1,2,4‐tri(tert‐butyl)cyclopentadienide) by the triethylsilylium cation produces the first base‐free rare‐earth metallocenium cation ...
Structural and functional characterization of the cell wall-targeting domain of lysostaphin with NMR spectroscopy Kauppinen, Linda (2018)Src-homologi 3 (SH3) domeenit ovat solun signaalireiteillä toimivia välttämättömiä, ei-katalyyttisiä domeeneja. Kuten monilla muilla aitotumaisten solujen proteiineilla tai domeeneilla, myös SH3-domeeneilla on homologinen ...