Implementation and evaluation of a parallel clustering algorithm in MOCLE

• Grant number: 11/21236-7
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: February 01, 2012
• End date: January 31, 2013
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Tiemi Christine Sakata
• Grantee: Rafael Mariottini Tomazela
• Host Institution: Centro de Ciências e Tecnologias para a Sustentabilidade (CCTS). Universidade Federal de São Carlos (UFSCAR). Sorocaba , SP, Brazil

Abstract

MOCLE (Multi-Objective Clustering Ensemble) is a framework for exploratory data analysis via clustering in order to facilitate experts to analyze resultants partitions. MOCLE uses a multi-objective ensemble to select and combine the partitions generated by different clustering algorithms. However, MOCLE depends on the several different clustering algorithms, considering various parameters to guarantee the diversity of ensemble's base partitions. The purpose of this project is to study, analyze and include a parallel clustering algorithm in MOCLE. This study is divided in two phases: (i) use a parallel clustering algorithm in high-dimensional data with many objects to verify its efficiency, both in relation to execution time as well as the quality of partitions generated; (ii) expande the number of clustering algorithms of MOCLE including the parallel clustering algorithm chosen.