e
Kaichang Di
techniques are very helpful to improve the traditional Bayes classification method and the proposed approaches of the
implementation of inductive learning in spatial databases are feasible and effective. In inductive learning can resolve the
problem of spectral confusion to a great extent. Combining Bayes method with inductive learning not only improves
classification accuracy greatly, but also extends the classification by subdivide some classes with the discovered
knowledge.
The intelligent integration of GIS and remote sensing is a difficult problem. An encouraging solution to the problem is
mining knowledge from spatial and utilizing the knowledge in image interpretation for spatial data updating. The
implementation of inductive learning in spatial databases and the combination with traditional classification methods
are theoretically and practically valuable. The applications of inductive learning to other image data sources, such as
TM, SAR etc., and the applications of the other data mining methods in remote sensing image classification, are the
future directions of our further study.
REFERENCES
Eklund P.W., Kirkby S.D, A. Salim 1998. Data mining and soil salinity analysis. Int. J. Geographical Information
Sciences, Vol. 12, No 3, pp247-268
Hong Jiarong 1997. Inductive learning — algorithm, theory and application, Science Press, Beijing, Sept.
Huang Xuegiao and John R. Jensen 1997. A Machine-Learning Approach to Automated Knowledge-Base Building for
Remote Sensing Image Analysis with GIS Data. Photogrammetric Engineering & Remote Sensing, Vol.63, No10,
pp1185-1194
Li Deren, Cheng Tao 1994. KDG: Knowledge Discovery from GIS - Propositions on the Use of KDD in an Intelligent
GIS. In Proc. ACTES, The Canadian Conf. on GIS
Li Deren, Di Kaichang, and Li Deyi 1997. A Framework of spatial data mining and knowledge discovery. In Proc. Int.
Workshop on Image Analysis and Information Fusion(IAIF'97), Adelaide, Australia, Nov.
Li Deyi 1992. Inductive learning: knowledge discovery from database. In: Proc. of 10 National Conf. on Database,
Shenyang, China, Sept.
Quinlan J.R 1993. C4.5: programs for machine learning. Morgan Kaufmann, San Mateo, CA
Zhang Jixian et al. 1995. Methods and key techniques of GIS database updating based on remote sensing image source.
In: Proc. 1*' Annual Conf. of China Association on GIS, Beijing
International Archives of Photogrammetry and Remote Sensing. Vol. XXXIII, Part B3. Amsterdam 2000. 245