Functional Mixture Discriminant Analysis with hidden process regression for curve classification

TL;DR

This paper introduces a novel mixture model-based discriminant analysis method for functional data, employing hidden process regression to effectively classify complex curves with regime changes, and demonstrates superior performance over existing methods.

Contribution

It proposes a new discriminant analysis approach using hidden process regression for functional data, enhancing classification of complex curves with regime changes.

Findings

Outperforms alternative methods on simulated data

Provides flexible curve modeling for complex-shaped curves

Uses EM algorithm for efficient parameter estimation

Abstract

We present a new mixture model-based discriminant analysis approach for functional data using a specific hidden process regression model. The approach allows for fitting flexible curve-models to each class of complex-shaped curves presenting regime changes. The model parameters are learned by maximizing the observed-data log-likelihood for each class by using a dedicated expectation-maximization (EM) algorithm. Comparisons on simulated data with alternative approaches show that the proposed approach provides better results.