A fast and efficient Modal EM algorithm for Gaussian mixtures

In the modal approach to clustering, clusters are defined as local maxima of underlying probability density function, where latter can be estimated either nonparametrically or using finite mixture models. Thus, closely related certain regions around modes, and every cluster corresponds a bump density. The Modal Expectation-Maximization (MEM) algorithm is an iterative procedure that identify any function. this contribution, we propose fast efficient MEM used when function through Gaussian distributions with parsimonious component-covariance structures. After describing procedure, apply proposed on both simulated real data examples, showing its high flexibility in several contexts.