Comparison of two exploratory data analysis methods for fMRI unsupervised clustering versus independent component analysis.

Comparison of two exploratory data analysis methods for fMRI unsupervised clustering versus independent component analysis.

Exploratory data-driven methods such as unsupervised clustering and independent component analysis (ICA) are considered to be hypothesis-generating procedures, and are complementary to the hypothesis-led statistical inferential methods in functional magnetic resonance imaging (fMRI). In this paper,...

Descrición completa

Detalles Bibliográficos
Publicado en:IEEE Transactions on information technology in biomedicine 8, 3 (2004).
Autor Principal: Meyer-Baese, A.
Formato: Artigo
Idioma:English
Subjects:
FastICA.
Infomax.
Data analysis method.
fMRI.
Feature extraction.
Functional magnetic resonance imaging.
Fuzzy clustering.
Hypothesis generating procedure.
Independent component analysis.
Minimal free energy vector quantization.
Neural gas network.
Principal component analysis.
Receiver operating characteristic analysis.
Self-organizing map.
Task-related activation map.
Topographic ICA.
Unsupervised clustering.