The impact of refinement strategies on sequential clustering algorithms

Sequential clustering algorithms have been characterized as fast and straightforward methods which produce, as result, a single clustering. They have the drawback of being dependent on the order in which data patterns are input to the algorithm and, generally, produce compact and spherical clusters. The focus of the work is a group of sequential algorithms which includes the Basic Sequential Algorithmic Scheme (BSAS) and two of its variations, the MBSAS and the TTSAS. The paper investigates refinement strategies which aim to improve the performance of the three sequential algorithms based on two processes: merge and reassignment. Results from experiments conducted in various data domains (from UCI and synthetic) are presented and a comparative analysis is given as evidence of the benefits of sequential clustering algorithm coupled with a refinement procedure.