Towards Association Based Spatio-temporal Reasoning

In this paper, we present an association based approach towards spatio-temporal reasoning on scientific data. This work is built upon our previous work, where we proposed a general framework to discover multiple types of spatial association patterns in spatial data. We extend the framework to accommodate temporal information by generating spatio-temporal episodes. We then develop algorithms to show that such episodes can be used to reason about critical events and make inferences on time-varying interactions. We also present preliminary results on a simulation dataset drawn from Computational Fluid Dynamics (CFD) to validate the proposed algorithms.

[1]  Srinivasan Parthasarathy,et al.  Mining Spatial Object Associations for Scientific Data , 2005, IJCAI.

[2]  Chris Bailey-Kellogg,et al.  Qualitative Spatial Reasoning Extracting and Reasoning with Spatial Aggregates , 2004, AI Mag..

[3]  Srinivasan Parthasarathy,et al.  A generalized framework for mining spatio-temporal patterns in scientific data , 2005, KDD '05.

[4]  Xin Zhang,et al.  Fast mining of spatial collocations , 2004, KDD.

[5]  Jonathan H. Fernyhough.  Event Recognition using Qualitative Reasoning on Automatically Generated Spatio-Temporal Models from , 1997 .

[6]  Yasuhiko Morimoto,et al.  Mining frequent neighboring class sets in spatial databases , 2001, KDD '01.

[7]  Srinivasan Parthasarathy,et al.  Detection and visualization of anomalous structures in molecular dynamics simulation data , 2004, IEEE Visualization 2004.

[8]  Sanjay Chawla,et al.  Complex spatial relationships , 2003, Third IEEE International Conference on Data Mining.

[9]  C. R. Rao,et al.  Statistical analysis of shape of objects based on landmark data. , 1996, Proceedings of the National Academy of Sciences of the United States of America.

[10]  Mikhail J. Atallah,et al.  A Linear Time Algorithm for the Hausdorff Distance Between Convex Polygons , 1983, Inf. Process. Lett..

[11]  Xin Wang,et al.  Volume tracking , 1996, Proceedings of Seventh Annual IEEE Visualization '96.

[12]  J. Christiansen.  Numerical Simulation of Hydrodynamics by the Method of Point Vortices , 1997 .

[13]  Kenneth Yip.  Structural Inferences from Massive Datasets , 1997, IJCAI.

[14]  I. Sadarjoen,et al.  Selective visualization of vortices in hydrodynamic flows , 1998, Proceedings Visualization '98 (Cat. No.98CB36276).

[15]  Anthony G. Cohn,et al.  Qualitative Spatial Representation and Reasoning: An Overview , 2001, Fundam. Informaticae.

[16]  W. Tobler.  A Computer Movie Simulating Urban Growth in the Detroit Region , 1970 .

[17]  Srinivasan Parthasarathy,et al.  Feature Mining Paradigms for Scientific Data , 2003, SDM.

[18]  Chris Henze.  Feature detection in linked derived spaces , 1998, Proceedings Visualization '98 (Cat. No.98CB36276).

[19]  Yi Zhang,et al.  Entropy-based subspace clustering for mining numerical data , 1999, KDD '99.