Knowledge Discovery From Massive Data Streams

Abstract

T.S. Eliot once wrote some beautiful poetic lines including one “Where is the knowledge we have lost in information?”. Can't say that T.S. Eliot could have anticipated today's scenario which is emerging from his poetic lines. Data in present scenario is a profuse resource in many circumstances and is piling-up and many technical leaders are finding themselves drowning in data. Through this big stream of data there is a vast flood of information coming out and seemingly crossing manageable boundaries. As Information is a necessary channel for educing and constructing knowledge, one can assume the importance of generating new and comprehensive knowledge discovery tools and techniques for digging this overflowing sea of information to create explicit knowledge. This chapter describes traditional as well as modern research techniques towards knowledge discovery from massive data streams. These techniques have been effectively applied not exclusively to completely structured but also to semi-structured and unstructured data. At the same time Semantic Web technologies in today's perspective require many of them to deal with all sorts of raw data.