caa a22 4500 445322241 CHVBK 20180317142707.0 cr unu---uuuuu 170323e20110601xx s 000 0 eng 10.1007/s00530-010-0226-5 doi (NATIONALLICENCE)springer-10.1007/s00530-010-0226-5 Li Hua-Fu Department of Information Management, Kainan University, 338, Taoyuan, Taiwan aut MEMSA: mining emerging melody structures from music query data [Elektronische Daten] [Hua-Fu Li] Effective and efficient mining of music structure patterns from music query data is one of the most interesting issues of multimedia data mining. In this paper, we introduce a new kind of pattern, called emerging melody structure (EMS), for knowledge discovery from music melody streams. EMSs are defined as music data items with melody strings whose support increase significantly from one sliding window to another window from streaming melody sequences. The discovered EMS can be used to predict the future trend of online music style recommendation, to personalize the Web service of music downloading priority, for music composers to compose new music or for service provider to collect more similar music. Therefore, an efficient data mining approach, called MEMSA (Mining Emerging Melody Structure Algorithm), is proposed to discover all EMSs from streaming music query data over sliding windows. In the framework of MEMSA, a prefix tree-based data structure, called EMS-tree (Emerging Melody Structure tree), is constructed for maintaining temporal EMSs effectively. Experimental results show that the proposed method MEMSA is an efficient algorithm for mining all EMSs from streaming melody sequences efficiently. Springer-Verlag, 2011 Data mining nationallicence Multimedia data mining nationallicence Music data mining nationallicence Melody structure mining nationallicence Emerging melody structure mining nationallicence Multimedia Systems Springer-Verlag 17/3(2011-06-01), 237-245 0942-4962 17:3<237 2011 17 530 https://doi.org/10.1007/s00530-010-0226-5 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s00530-010-0226-5 text/html Onlinezugriff via DOI NATIONALLICENCE 100 1- Li Hua-Fu Department of Information Management, Kainan University, 338, Taoyuan, Taiwan aut NATIONALLICENCE 773 0- Multimedia Systems Springer-Verlag 17/3(2011-06-01), 237-245 0942-4962 17:3<237 2011 17 530 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer