Combining PCA and multiset CCA for dimension reduction when group ICA is applied to decompose naturalistic fMRI data
Tsatsishvili, V., Cong, F., Toiviainen, P., & Ristaniemi, T. (2015). Combining PCA and multiset CCA for dimension reduction when group ICA is applied to decompose naturalistic fMRI data. In IJCNN 2015 : International Conference on Neural Networks. Institute of Electrical and Electronic Engineers. Proceedings of International Joint Conference on Neural Networks. https://doi.org/10.1109/IJCNN.2015.7280722
© 2015 IEEE. This is an authors' post-print version of an article whose final and definitive form has been published in the conference proceeding by IEEE.
An extension of group independent component analysis (GICA) is introduced, where multi-set canonical correlation analysis (MCCA) is combined with principal component analysis (PCA) for three-stage dimension reduction. The method is applied on naturalistic functional MRI (fMRI) images acquired during task-free continuous music listening experiment, and the results are compared with the outcome of the conventional GICA. The extended GICA resulted slightly faster ICA convergence and, more interestingly, extracted more stimulus-related components than its conventional counterpart. Therefore, we think the extension is beneficial enhancement for GICA, especially when applied to challenging fMRI data.
PublisherInstitute of Electrical and Electronic Engineers
Parent publication ISBN978-1-4799-1959-8
ConferenceInternational joint conference on neural networks
Is part of publicationIJCNN 2015 : International Conference on Neural Networks
Publication in research information system
MetadataShow full item record
Showing items with similar title or keywords.
Key issues in decomposing fMRI during naturalistic and continuous music experience with independent component analysis Cong, Fengyu; Puoliväli, Tuomas; Alluri, Vinoo; Sipola, Tuomo; Burunat, Iballa; Toiviainen, Petri; Nandi, Asoke; Brattico, Elvira; Ristaniemi, Tapani (Elsevier, 2014)Background Independent component analysis (ICA) has been often used to decompose fMRI data mostly for the resting-state, block and event-related designs due to its outstanding advantage. For fMRI data during free-listening ...
The potential of temporal analysis : Combining log data and lag sequential analysis to investigate temporal differences between scaffolded and non-scaffolded group inquiry-based learning processes Lämsä, Joni; Hämäläinen, Raija; Koskinen, Pekka; Viiri, Jouni; Mannonen, Joonas (Elsevier, 2020)This paper contributes to the ongoing discussion about analysing the temporal aspects of learning processes in the educational technology research field. Our main aim was to advance methods for analysing temporal aspects ...
Nordhausen, Klaus; Matilainen, Markus; Miettinen, Jari; Virta, Joni; Taskinen, Sara (Foundation for Open Access Statistic, 2021)Multivariate time series observations are increasingly common in multiple fields of science but the complex dependencies of such data often translate into intractable models with large number of parameters. An alternative ...
The struggle over risk : the spatial, temporal, and cultural dimensions of protest against nuclear technology Litmanen, Tapio (2001)This thesis examines the social struggle over nuclear risks. The birth and subsequent development of anti-nuclear protest are closely interwoven with the creation of nuclear risks, the public perception of risks, and the ...
Atomistic Insights into Nitrogen-Cycle Electrochemistry : A Combined DFT and Kinetic Monte Carlo Analysis of NO Electrochemical Reduction on Pt(100) Chun, Hee-Joon; Apaja, Vesa; Clayborne, Andre; Honkala, Karoliina; Greeley, Jeffrey (American Chemical Society, 2017)Electrocatalytic denitrification is a promising technology for the removal of NOx species in groundwater. However, a lack of understanding of the molecular pathways that control the overpotential and product distribution ...