Data Stream Mining

Stream mining is discovering knowledge or patterns from continuous data streams. Unlike traditional data sets, data streams consist of sequences of data instances that flow in and out of a system continuously and with varying update rates. They are temporally ordered, fast-changing, massive, and potentially infinite. In order to cope with data stream characteristics, specific algorithms should be designed. We combine fuzzy clustering and stream mining to create models that classify stream data while capturing hidden structures. We have applied our algorithms to several domains, such as medical, and educational.