Linear Discriminant Analysis Achieves High Classification Accuracy for the BOLD fMRI Response to Naturalistic Movie Stimuli

• Published in: Frontiers in human neuroscience Vol. 10; p. 128
• Main Authors: Mandelkow, Hendrik, de Zwart, Jacco A., Duyn, Jeff H.
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 31.03.2016; Frontiers Media S.A
• Subjects: Algorithms; Bayesian analysis; BOLD fMRI; Brain mapping; Brain research; Classification; Cognitive ability; Computational neuroscience; Data analysis; Experiments; Functional magnetic resonance imaging; Hypotheses; LDA; Learning algorithms; movies; multivariate pattern analysis; MVPA; Neuroscience; NMR; Nuclear magnetic resonance; Statistical analysis; Statistics; Visual stimuli; movies; nearest-neighbor; multivariate pattern analysis (MVPA); naturalistic stimuli; linear discriminant analysis (LDA); classification; BOLD fMRI; Gaussian Naïve Bayes (GNB)
• ISSN: 1662-5161; 1662-5161
• DOI: 10.3389/fnhum.2016.00128

Naturalistic stimuli like movies evoke complex perceptual processes, which are of great interest in the study of human cognition by functional MRI (fMRI). However, conventional fMRI analysis based on statistical parametric mapping (SPM) and the general linear model (GLM) is hampered by a lack of acc...