*Miner: a spatial and spatiotemporal data mining system

ABSTRACT

Intelligent image information mining for thematic pattern extraction is a complex task. Ever increasing spatial, spectral, and temporal resolution poses several challenges to the geographic knowledge discovery community. Although the improvements in sensor technology and data collection methods may lead to improved geoinformation generation, it also places several constraints on data mining techniques. Moreover thematic classes are spectrally overlapping, that is, many thematic classes can not be separated by spectral features alone. In recent years we have developed several innovative machine learning approaches to address these problems. The resulting software system, called *Miner, was tested on several real world multisource spatiotemporal datasets. Experimental evaluation showed improved accuracy over conventional data mining approaches. In addition, we integrated *Miner with another popular open source machine learning system called Weka. In this demo we show the utility of *Miner for thematic information extraction from multisource spatiotemporal data (remote sensing images and ancillary geospatial databases).

REFERENCES

• 1: B. M. Kazar, S. Shekhar, D. J. Lilja, R. R. Vatsavai, and R. K. Pace. Comparing exact and approximate spatial auto-regression model solutions for spatial data analysis. In GIScience, pages 140--161, 2004.
• 2: S. Shekhar, P. Schrater, R. Vatsavai, W. Wu, and S. Chawla. Spatial contextual classification and prediction models for mining geospatial data. IEEE Transaction on Multimedia, 4(2):174--188, 2002.
• 3: Ranga Raju Vatsavai , Budhendra Bhaduri, A Hybrid Classification Scheme for Mining Multisource Geospatial Data, Proceedings of the Seventh IEEE International Conference on Data Mining Workshops, p.673-678, October 28-31, 2007 [doi>10.1109/ICDMW.2007.5]
• 4: R. R. Vatsavai, T. E. Burk, S. Shekhar, and M. Gini. An efficient hybrid classification system for mining multi-spectral remote sensing imagery guided by spatial databases. In 2nd Pattern Recognition of Remote Sensing Workshop, 2002.
• 5: Ranga Raju Vatsavai , Shashi Shekhar , Thomas E. Burk, A Semi-Supervised Learning Method for Remote Sensing Data Mining, Proceedings of the 17th IEEE International Conference on Tools with Artificial Intelligence, p.207-211, November 14-16, 2005
• 6: Ranga Raju Vatsavai , Shashi Shekhar , Thomas E. Burk, An efficient spatial semi-supervised learning algorithm, International Journal of Parallel, Emergent and Distributed Systems, v.22 n.6, p.427-437, November 2007 [doi>10.1080/17445760701207546]
• 7: Ranga Raju Vatsavai , Shashi Shekhar , Thomas E. Burk , Budhendra Bhaduri, *Miner: A Suit of Classifiers for Spatial, Temporal, Ancillary, and Remote Sensing Data Mining, Proceedings of the Fifth International Conference on Information Technology: New Generations, p.801-806, April 07-09, 2008 [doi>10.1109/ITNG.2008.243]
• 8: Weka. Weka machine learning project. http://www.cs.waikato.ac.nz/ml/index.html.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

Additional Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION

Keywords:
EM, GMM, multisource data, semi-supervised learning