Improved model-based clustering using evolutionary optimization
Emad Kebriaei, Kayvan Bijari, Hadi Zare · 2017
As an optimization strategy Maximum Likelihood's definitive goal is to adjust a statistic model with a specific dataset, the method will adjust some variables of a statistical model from a dataset or a known distribution, so the model can “describe” each data sample and estimate the others. Clustering can be based on probability models to cover the missing values. This provides insights into when the data should conform to the model and led to development of new clustering methods such as Expectation Maximization (EM) which is based on the principle of Maximum Likelihood of unobserved variables in finite mixture models. Evolutionary Algorithms are trusted to further improve optimization tactics, in this paper Big-Bang Big-Crunch evolutionary algorithm have been used to boost model-based clustering and experimental results on the real datasets shows its superiority over the typical model-based clustering methods.