Robust Clustering Algorithms Employing Fuzzy-Possibilistic Product Partition

One of the main challenges in the field of clustering is creating algorithms that are both accurate and robust. The fuzzy-possibilistic product partition c-means clustering algorithm was introduced with the main goal of producing accurate partitions in the presence of outlier data. This chapter presents several clustering algorithms based on the fuzzy-possibilistic product partition, specialized for the detection of clusters having various shapes including spherical and ellipsoidal shells. The advantages of applying the fuzzy-possibilistic product partition are presented in comparison with previous c-means clustering models. Besides being more robust and accurate than previous probabilistic-possibilistic mixture partitions, the product partition is easier to handle due to its reduced number of parameters.