Multi-level clustering and reasoning about its clusters using region connection calculus

Authors:
Ickjai Lee;Mary-Anne Williams
Affiliations:
Innovation and Technology Research Laboratory, Faculty of Information Technology, University of Technology Sydney, NSW, Australia;Innovation and Technology Research Laboratory, Faculty of Information Technology, University of Technology Sydney, NSW, Australia
Venue:
PAKDD'03 Proceedings of the 7th Pacific-Asia conference on Advances in knowledge discovery and data mining
Year:
2003

Citing 9
Cited 4

Comments on 'Parallel Algorithms for Hierarchical Clustering and Cluster Validity'

IEEE Transactions on Pattern Analysis and Machine Intelligence
BIRCH: an efficient data clustering method for very large databases

SIGMOD '96 Proceedings of the 1996 ACM SIGMOD international conference on Management of data
CURE: an efficient clustering algorithm for large databases

SIGMOD '98 Proceedings of the 1998 ACM SIGMOD international conference on Management of data
Qualitative Spatial Representation and Reasoning with the Region Connection Calculus

Geoinformatica
Finding Boundary Shape Matching Relationships in Spatial Data

SSD '97 Proceedings of the 5th International Symposium on Advances in Spatial Databases
STING: A Statistical Information Grid Approach to Spatial Data Mining

VLDB '97 Proceedings of the 23rd International Conference on Very Large Data Bases
A progressive refinement approach to spatial data mining

A progressive refinement approach to spatial data mining
Geographic Data Mining and Knowledge Discovery

Geographic Data Mining and Knowledge Discovery
Reasoning about categories in conceptual spaces

IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 1

Fast qualitative reasoning about categories in conceptual spaces

Design and application of hybrid intelligent systems
AN ORDER-k VORONOI APPROACH TO GEOSPATIAL CONCEPT MANAGEMENT WITHIN CONCEPTUAL SPACES

Applied Artificial Intelligence
Data mining coupled conceptual spaces for intelligent agents in data-rich environments

KES'05 Proceedings of the 9th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part IV
Mining positive associations of urban criminal activities using hierarchical crime hot spots

WISI'06 Proceedings of the 2006 international conference on Intelligence and Security Informatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Spatial clustering provides answers for "where?" and "when?" and evokes "why?" for further explorations. In this paper, we propose a divisive multi-level clustering method that requires O(n log n) time. It reveals a cluster hierarchy for the "where?" and "when?" queries. Experimental results demonstrate that it identifies quality multi-level clusters. In addition, we present a solid framework for reasoning about multi-level clusters using Region Connection Calculus for the "why?" query. In this framework, we can derive their possible causes and positive associations between them with ease.