Interactive visualization tool for exploring and learning from ensemble of clustering solutions

• Grant number: 15/21560-0
• Support Opportunities: Scholarships abroad - Research
• Start date: March 28, 2016
• End date: March 27, 2017
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Katti Faceli
• Grantee: Katti Faceli
• Host Investigator: Julia Handl
• Host Institution: Centro de Ciências em Gestão e Tecnologia (CCGT). Universidade Federal de São Carlos (UFSCAR). Campus de Sorocaba. Sorocaba , SP, Brazil
• Institution abroad: University of Manchester, England

Abstract

Cluster analysis has been largely employed for knowledge extraction in several fields. Interpretation of clustering results are not straightforward for a domain expert and visual aids are extremely useful in these cases. Techniques for visualization and full exploration of advanced clustering techniques results are still needed. Partitions' Visualizer (PVis) is a visualization tool that provides a static view of a collection of partitions, aiming at facilitating the work of domain experts comparing several clustering results. This research project aims to design/develop a visualization tool suitable for interactively explore collections of clustering solutions. The tool will take into account the capabilities of PVis, mechanisms for interaction, integration with recent clustering resources and integration with other already existing visualization devices. In order to show the effectiveness of the proposed tool, we will perform a case study. It will concern exploring the relations between partitions obtained with multi-objective clustering algorithms in the context of bioinformatics.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

FACELI, KATTI; SAKATA, TIEMI C.; HANDL, JULIA; IEEE. CVis - towards a novel visualization tool to explore the relationship between input and output partitions in multi-objective clustering ensembles. 2017 IEEE CONFERENCE ON COMPUTATIONAL INTELLIGENCE IN BIOINFORMATICS AND COMPUTATIONAL BIOLOGY (CIBCB), v. N/A, p. 6-pg., 2017-01-01. (15/21560-0)

ANTUNES, VANESSA; SAKATA, TIEMI C.; FACELI, KATTI; DE SOUTO, MARCILIO C. P.. Hybrid strategy for selecting compact set of clustering partitions. APPLIED SOFT COMPUTING, v. 87, FEB 2020. (15/21560-0)

ANTUNES, VANESSA; FACELI, KATTI; SAKATA, TIEMI CHRISTINE; IEEE. HSS: Compact set of Partitions via Hybrid Selection. 2017 6TH BRAZILIAN CONFERENCE ON INTELLIGENT SYSTEMS (BRACIS), v. N/A, p. 6-pg., 2017-01-01. (15/21560-0)