2009 | OriginalPaper | Buchkapitel
Mining Spread Patterns of Spatio-temporal Co-occurrences over Zones
verfasst von : Feng Qian, Qinming He, Jiangfeng He
Erschienen in: Computational Science and Its Applications – ICCSA 2009
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
The research tracks the spread of co-occurrence phenomena over the zonal space. Spread patterns of spatio-temporal co-occurrences over zones (SPCOZs) represent the spread structures over the zones for the subsets of features whose events co-locate in space and time. SPCOZs are of great use in many applications, such as tracking the evolutions of infectious diseases and ecological disasters in space and time. However, finding SPCOZs is computationally expensive due to large size of history data sets, exponential number of feature combinations, and complex interest measures. In this paper, we propose a novel Spread Pattern Tree (SP-Tree) to index the spread elements of the SPCOZs which holds the monotonic property with the size of the co-occurrences. We also propose an efficient mining algorithm (SPCOZ-Miner) for mining SPCOZs. The experimental evaluation with both synthetic and real-world data sets shows our algorithm is effective and much more efficient than a straight approach.