Mining top- k Hot Melody Structures over online music query streams

Abstract

Online mining of frequent patterns from music data is one of the most important research issues of multimedia data mining. Most previous studies require the specification of a min_ support threshold and aim at mining a complete set of frequent patterns satisfying min_ support. However, in practice, it is difficult for users to provide an appropriate value of min_ support threshold. In this paper, we propose a new problem of multimedia data mining: online mining of top- k melody structures of length no less than min_ l, where k is the desired number of hot melody structures to be mined and min_ l is the minimal length of each melody structure. An efficient single-pass algorithm, called top- k-HMS (top- k Hot Melody Structures), is developed for mining such melody structures without min_ support. In the framework of top- k-HMS algorithm, a new summary data structure, called TKM-list (top- k melody list) is developed to maintain the essential information about the top- k hot melody structures from the current melody sequence streams. Experimental studies show that the proposed top- k-HMS algorithm is an efficient one-pass method for mining the set of top- k Hot Melody Structures over a continuous stream of melody sequences.