Classification with the matrix-variate-$t$ distribution

Abstract

Matrix-variate distributions can intuitively model the dependence structure of matrix-valued observations that arise in applications with multivariate time series, spatio-temporal or repeated measures. This paper develops an Expectation-Maximization algorithm for discriminant analysis and classification with matrix-variate $t$-distributions. The methodology shows promise on simulated datasets or when applied to the forensic matching of fractured surfaces or the classification of functional Magnetic Resonance, satellite or hand gestures images.

arXiv comment12 pages, 7 figures

References in corpus (4)

• A Re-defined and Generalized Percent-Overlap-of-Activation Measure for Studies of fMRI Reproducibility and its Use in Identifying Outlier Activation Maps
• Covariance pattern mixture models for the analysis of multivariate heterogeneous longitudinal data
• Assessing Certainty of Activation or Inactivation in Test-Retest fMRI Studies
• FAST Adaptive Smoothing and Thresholding for Improved Activation Detection in Low-Signal fMRI

Cited by in corpus (8)

• Reduced-Rank Tensor-on-Tensor Regression and Tensor-variate Analysis of Variance
• Robust factored principal component analysis for matrix-valued outlier accommodation and detection
• Fracture Mechanics-Based Quantitative Matching of Forensic Evidence Fragments
• Quantitative Matching of Forensic Evidence Fragments Utilizing 3D Microscopy Analysis of Fracture Surface Replicas
• Robust covariance estimation and explainable outlier detection for matrix-valued data
• Exact Multivariate Amplitude Distributions for Non-Stationary Gaussian or Algebraic Fluctuations of Covariances or Correlations
• Gibbs Sampler for Matrix Generalized Inverse Gaussian Distributions
• Matrix Moments in a Real, Doubly Correlated Algebraic Generalization of the Wishart Model