Automatic clustering using MOCLONAL for classifying actions of 3D human models

Abstract

Conventional clustering algorithms use a single objective function optimization criterion for classification which may not provide satisfactory results to determine the underlying clusters in many datasets. In such scenario multi-objective algorithms are preferred which improve the clustering performance due to additional knowledge of data properties in the form of objective functions. In this paper we have proposed an automatic multi-objective clustering algorithm based on clonal selection principle of artificial immune system (AIS) and is termed as MOCLONAL. The proposed algorithm is capable of providing a single best solution from the Pareto optimal archive which mostly satisfy the user requirement. Simulation studies on synthetic and real life datasets demonstrate the superior performance of the proposed algorithm compared to benchmark multi-objective clustering algorithm MOCK. An interesting application of the proposed algorithm have been demonstrated to classify the normal and aggressive actions of 3D human models.