Effective lossless condensed representation and discovery of spatial co-location patterns

Lizhen Wang, Xuguang Bao, Hongmei Chen*, Longbing Cao

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

47 Citations (Scopus)

Abstract

A spatial co-location pattern is a set of spatial features frequently co-occuring in nearby geographic spaces. Similar to closed frequent itemset mining, closed co-location pattern (CCP) mining was proposed for losslessly condensing large collections of prevalent co-location patterns. However, the state-of-the-art condensation methods in mining CCP are inspired by closed frequent itemset mining and do not consider the intrinsic characteristics of spatial co-locations, e.g., the participation index and ratio in spatial feature interactions, thus causing serious containment issues in CCP mining. In this paper, we propose a novel lossless condensed representation of prevalent co-location patterns, Super Participation Index-closed (SPI-closed) co-location. An efficient SPI-closed Miner is also proposed to effectively capture the nature of spatial co-location patterns, alongside the development of three additional pruning strategies to make the SPI-closed Miner efficient. This method captures richer feature interactions in spatial co-locations and solves the containment issues in existing CCP methods. A performance evaluation conducted on both synthetic and real-life data sets shows that SPI-closed Miner reduces the number of CCPs by up to 50%, and runs much faster than the baseline CCP mining algorithm described in the literature.

Original languageEnglish
Pages (from-to)197-213
Number of pages17
JournalInformation Sciences
Volume436-437
DOIs
Publication statusPublished - Apr 2018
Externally publishedYes

Keywords

  • Spatial data mining
  • Spatial co-location patterns
  • SPI-closed co-location patterns
  • Lossless condensed representation

Fingerprint

Dive into the research topics of 'Effective lossless condensed representation and discovery of spatial co-location patterns'. Together they form a unique fingerprint.

Cite this