Clustering sequential data with OPTICS

Author

Omrani, Amin ; Santhisree, K. ; Damodaram

Author_Institution

Dept. of Comput. Sci., Jawaharlal Nehru Technol. Univ. (JNTUH), Hyderabad, India

fYear

2011

fDate

27-29 May 2011

Firstpage

591

Lastpage

594

Abstract

The Web has enormous, various and knowledgeable data for data mining research. The web is a biggest knowledgeable database with various types of data to mine. One of interesting type of data is user behaviour that mine from server log files. Many algorithms are for clustering and then discover the knowledge from database. In this paper we use OPTICS ("Ordering Points To Identify the Clustering Structure") algorithm to find density based clusters on a social music website data (Last.fm website is a free social platform that share listed music with so different music genres). After pre-processing on music dataset and removing unprofitable data from the dataset was ready to clustering. The clusters are generated by OPTICS algorithm and the average of inter cluster and intra cluster are calculated. Then results are visualized and Euclidean distance measure is used to compare results of intra cluster and inter cluster analyses. Finally showed behavior of clusters that made by OPTICS algorithm on a sequential data.

Keywords

data mining; database management systems; music; pattern clustering; social networking (online); Euclidean distance measure; OPTICS; OPTICS algorithm; data mining research; database; density based clusters; intercluster analyses; intracluster analyses; music dataset; music genres; ordering points to identify the clustering structure algorithm; sequential data clustering; server log files; social music website data; visualized distance measure; Adaptation models; Biology; Biomedical optical imaging; Optics; Clustering algorithm OPTICS; Sequence mining;

fLanguage

English

Publisher

ieee

Conference_Titel

Communication Software and Networks (ICCSN), 2011 IEEE 3rd International Conference on

Conference_Location

Xi´an

Print_ISBN

978-1-61284-485-5

Type

conf

DOI

10.1109/ICCSN.2011.6014339

Filename

6014339