Sequential Clustering: A Study on Covering Based Rough Set Theory.

Sequential data analysis is one of the vital research area. Several data mining techniques like classification, association, predictions can be applied in sequential data. Clustering is a challenging task in the field of machine learning, pattern recognition and web mining. Clustering is the process of grouping data based on some similarities but applying clustering approach in sequential data should focus on order as well as the content of sequence similarity. Rough set theory is one of the efficient soft computing techniques used in clustering which help researchers to discover overlapping clusters in many applications such as web mining and text mining. The rough set which holds equivalence relation is very rigid as it doesn't support incomplete information system. This leads the theory's application to a certain extent. Hence covering based rough set is introduced where the partitions of a universe are replaced by covers. Different types of covering based rough set theory exist in the literature. In this paper all three types covering rough sets is investigated and produced a comparative study of first type, second type, and third type covering based rough clustering algorithm for sequential data.