Aarhus University Seal / Aarhus Universitets segl

Diffusion map for clustering fMRI spatial maps extracted by Indipendent Component Analysis

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

Standard

Diffusion map for clustering fMRI spatial maps extracted by Indipendent Component Analysis. / Sipola, Tuomo; Cong, Fengyu; Ristaniemi, Tapani; Alluri, Vinoo; Toiviainen, Petri; Brattico, Elvira; Nandi, Asoke K.

In: IEEE International Workshop on Machine Learning for Signal Processing, 2013.

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

Harvard

Sipola, T, Cong, F, Ristaniemi, T, Alluri, V, Toiviainen, P, Brattico, E & Nandi, AK 2013, 'Diffusion map for clustering fMRI spatial maps extracted by Indipendent Component Analysis', IEEE International Workshop on Machine Learning for Signal Processing. https://doi.org/10.1109/MLSP.2013.6661923

APA

Sipola, T., Cong, F., Ristaniemi, T., Alluri, V., Toiviainen, P., Brattico, E., & Nandi, A. K. (2013). Diffusion map for clustering fMRI spatial maps extracted by Indipendent Component Analysis. IEEE International Workshop on Machine Learning for Signal Processing. https://doi.org/10.1109/MLSP.2013.6661923

CBE

Sipola T, Cong F, Ristaniemi T, Alluri V, Toiviainen P, Brattico E, Nandi AK. 2013. Diffusion map for clustering fMRI spatial maps extracted by Indipendent Component Analysis. IEEE International Workshop on Machine Learning for Signal Processing. https://doi.org/10.1109/MLSP.2013.6661923

MLA

Sipola, Tuomo et al. "Diffusion map for clustering fMRI spatial maps extracted by Indipendent Component Analysis". IEEE International Workshop on Machine Learning for Signal Processing. 2013. https://doi.org/10.1109/MLSP.2013.6661923

Vancouver

Sipola T, Cong F, Ristaniemi T, Alluri V, Toiviainen P, Brattico E et al. Diffusion map for clustering fMRI spatial maps extracted by Indipendent Component Analysis. IEEE International Workshop on Machine Learning for Signal Processing. 2013. https://doi.org/10.1109/MLSP.2013.6661923

Author

Sipola, Tuomo ; Cong, Fengyu ; Ristaniemi, Tapani ; Alluri, Vinoo ; Toiviainen, Petri ; Brattico, Elvira ; Nandi, Asoke K. / Diffusion map for clustering fMRI spatial maps extracted by Indipendent Component Analysis. In: IEEE International Workshop on Machine Learning for Signal Processing. 2013.

Bibtex

@inproceedings{c3e42078aec4437a9bcfc614251a9253,
title = "Diffusion map for clustering fMRI spatial maps extracted by Indipendent Component Analysis",
abstract = "Functional magnetic resonance imaging (fMRI) produces data about activity inside the brain, from which spatial maps can be extracted by independent component analysis (ICA). In datasets, there are n spatial maps that contain p voxels. The number of voxels is very high compared to the number of analyzed spatial maps. Clustering of the spatial maps is usually based on correlation matrices. This usually works well, although such a similarity matrix inherently can explain only a certain amount of the total variance contained in the high-dimensional data where n is relatively small but p is large. For high-dimensional space, it is reasonable to perform dimensionality reduction before clustering. In this research, we used the recently developed diffusion map for dimensionality reduction in conjunction with spectral clustering. This research revealed that the diffusion map based clustering worked as well as the more traditional methods, and produced more compact clusters when needed.",
keywords = "clustering, diffusion map, dimensionality reduction, functional magnetic resonance imaging (fMRI), independent component analysis, spatial maps, DYNAMICAL-SYSTEMS",
author = "Tuomo Sipola and Fengyu Cong and Tapani Ristaniemi and Vinoo Alluri and Petri Toiviainen and Elvira Brattico and Nandi, {Asoke K.}",
year = "2013",
doi = "10.1109/MLSP.2013.6661923",
language = "English",
journal = "IEEE International Workshop on Machine Learning for Signal Processing",
issn = "2161-0363",
note = "23rd IEEE International Workshop on Machine Learning for Signal Processing (MLSP) ; Conference date: 22-09-2013 Through 25-09-2013",

}

RIS

TY - GEN

T1 - Diffusion map for clustering fMRI spatial maps extracted by Indipendent Component Analysis

AU - Sipola, Tuomo

AU - Cong, Fengyu

AU - Ristaniemi, Tapani

AU - Alluri, Vinoo

AU - Toiviainen, Petri

AU - Brattico, Elvira

AU - Nandi, Asoke K.

PY - 2013

Y1 - 2013

N2 - Functional magnetic resonance imaging (fMRI) produces data about activity inside the brain, from which spatial maps can be extracted by independent component analysis (ICA). In datasets, there are n spatial maps that contain p voxels. The number of voxels is very high compared to the number of analyzed spatial maps. Clustering of the spatial maps is usually based on correlation matrices. This usually works well, although such a similarity matrix inherently can explain only a certain amount of the total variance contained in the high-dimensional data where n is relatively small but p is large. For high-dimensional space, it is reasonable to perform dimensionality reduction before clustering. In this research, we used the recently developed diffusion map for dimensionality reduction in conjunction with spectral clustering. This research revealed that the diffusion map based clustering worked as well as the more traditional methods, and produced more compact clusters when needed.

AB - Functional magnetic resonance imaging (fMRI) produces data about activity inside the brain, from which spatial maps can be extracted by independent component analysis (ICA). In datasets, there are n spatial maps that contain p voxels. The number of voxels is very high compared to the number of analyzed spatial maps. Clustering of the spatial maps is usually based on correlation matrices. This usually works well, although such a similarity matrix inherently can explain only a certain amount of the total variance contained in the high-dimensional data where n is relatively small but p is large. For high-dimensional space, it is reasonable to perform dimensionality reduction before clustering. In this research, we used the recently developed diffusion map for dimensionality reduction in conjunction with spectral clustering. This research revealed that the diffusion map based clustering worked as well as the more traditional methods, and produced more compact clusters when needed.

KW - clustering

KW - diffusion map

KW - dimensionality reduction

KW - functional magnetic resonance imaging (fMRI)

KW - independent component analysis

KW - spatial maps

KW - DYNAMICAL-SYSTEMS

U2 - 10.1109/MLSP.2013.6661923

DO - 10.1109/MLSP.2013.6661923

M3 - Conference article

JO - IEEE International Workshop on Machine Learning for Signal Processing

JF - IEEE International Workshop on Machine Learning for Signal Processing

SN - 2161-0363

T2 - 23rd IEEE International Workshop on Machine Learning for Signal Processing (MLSP)

Y2 - 22 September 2013 through 25 September 2013

ER -