空间数据挖掘指南

Spatial data mining is the process of discovering interesting and previously unknown, but potentially useful patterns from large spatial datasets. Extracting interesting and useful patterns from spatial datasets is more difficult than extracting the corresponding patterns from traditional numeric and categorical data due to the complexity of spatial data types, spatial relationships, and spatial autocorrelation. This tutorial will introduce spatial data mining in the following categories: location prediction, spatial outlier detection, and co-location mining.

A General Introduction to Spatial Data Mining

Slides: What′s Special About Spatial Data Mining?(PS,PDF) 数据挖掘实验室

Slides: Spatial Data Mining: Accomplishments and Research Needs, GIScience 2004 Keynote Speech(PS,PDF)

数据挖掘论坛

Reference:

数据挖掘工具

[SDM03] Shashi Shekhar, Pusheng Zhang, Yan Huang, and Ranga Raju Vatsavai, "Trends in Spatial Data Mining", as a book chapter to appear in "Data Mining: Next Generation Challenges and Future Directions", Hillol Kargupta and Anupam Joshi(editors), AAAI/MIT Press, 2003 (PS, PDF) 数据挖掘研究院

Location Prediction

Slides: Spatial Autoregressive Models. (PS,PDF)

数据挖掘工具

Slides: Scalable Parallel Formulations of Spatial Auto-Regression (SAR) Models for Mining Regular Grid Geospatial Data (PPT).

数据挖掘论坛

Example of Scalable Parallel Formulations of Spatial Auto-Regression (SAR) Models: 数据挖掘实验室

• Readme
• Codes:
  • Matlab Programs & Data-sets (on IBM SP):

    For small data set (n=16): (ReadMe, Browse programs & Data-sets, Download all in a zipped file)
    For large data set (n=2500): (Readme, Browse programs & Data-sets, Download all in a zipped file) 数据挖掘交友

  • Fortran Programs and Data-sets for 2500 case (on IBM SP):(Readme, Browse programs and code, Download all in a zipped file)
  • Fortran Programs for problem size 10000

Reference:

数据挖掘论坛

[AHP03] Baris Kazar, Shashi Shekhar, and David J. Lilja, "Parallel Formulation of Spatial Auto-Regression", Army High-Performance Computing Research Center (AHPCRC) Technical Report no. 2003-125, August 2003 (PS, PDF) 数据挖掘交友

[IEE02] S. Shekhar, P. Schrater, R. Vatsavai, W. Wu, and S. Chawla, Spatial Contextual Classification and Prediction Models for Mining Geospatial Data , IEEE Transactions on Multimedia (special issue on Multimedia Dataabses) , 2002. (PS, PDF) 数据挖掘论坛

Spatial Outlier Detection

Slides: A Unified Approach to Detecting Spatial Outliers (PS, PDF)

数据挖掘研究院

Example of Spatial Outlier Detection using Matlab:

数据挖掘工具

• Readme
• Matlab Scripts: (Browse files, Download all in a zipped file)

Reference: 数据挖掘研究院

[GEI03] Shashi Shekhar, Chang-Tien Lu, Pusheng Zhang, "A Unified Approach to Detecting Spatial Outliers" volume 7, issue 2, GeoInformatica, Kluwer Academic Publishers, 2003. (PS, PDF) 数据挖掘交友

Co-location Mining

Slides: Mining Co-location Patterns (PS, PDF)

数据挖掘实验室

Example of Mining Co-location Patterns using Matlab:

数据挖掘研究院

• Readme
• Matlab Scripts: (Browse files, Download all in a zipped file)

Reference:

数据挖掘交友

[TKD03] Yan Huang, Shashi Shekhar, and Hui Xiong, Discovering Co-location Patterns from Spatial Datasets: A General Approach, Submitted to IEEE TKDE(under second round review), (PS, PDF)
数据挖掘交友

More publications are available at the Publication Cabinet of Spatial Databases Group

数据挖掘工具