A Machine-Learning Approach to Automated Knowledge-Base Building for Remote Sensing Image Analysis with GIs Data

A machine learning approach to automated building of knowledge bases for image analysis expert systems incorporating GIS data is presented. The method uses an inductive learning algorithm to generate production rules from training data. With this method, building a knowledge base for a rule-based expert system is easier than using the conventional knowledge acquisition approach. The knowledge base built by this method was used by an expert system to pe$orm a wetland classification of Par Pond on the Savannah River Site, South Carolina using SPOT multispectral imagery and GIs data. To evaluate the peqformance of the resultant knowledge base, the classification result was compared to classifications with two conventional methods. The accuracy assessment and the analysis of the resultant production rules suggest that the knowledge base built by the machine learning method was of good quality for image analysis with GIS data.

[1]  Michael E. Hodgson,et al.  Remote sensing of Wetland habitat: a wood stork example , 1987 .

[2]  T. M. Lillesand,et al.  Rule-based classification models: flexible integration of satellite imagery and thematic spatial data , 1992 .

[3]  Jaime G. Carbonell,et al.  An Overview of Machine Learning , 1983 .

[4]  Tom M. Mitchell,et al.  Generalization as Search , 2002 .

[5]  P. A. WALKER,et al.  SIMPLE An inductive modelling and mapping tool for spatially-oriented data , 1988, Int. J. Geogr. Inf. Sci..

[6]  B. Lees,et al.  A new method for predicting vegetation distributions using decision tree analysis in a geographic information system , 1991 .

[7]  Sunil Narumalani,et al.  Predictive modeling of cattail and waterlily distribution in a South Carolina reservoir using GIS , 1992 .

[8]  Charalambos Kontoes,et al.  An Experimental System for the Integration of GIS Data in Knowledge-Based Image Analysis for Remote Sensing of Agriculture , 1993, Int. J. Geogr. Inf. Sci..

[9]  Richard J. Aspinall,et al.  An inductive modelling procedure based on Bayes' theorem for analysis of pattern in spatial data , 1992, Int. J. Geogr. Inf. Sci..

[10]  Nada Lavrac,et al.  The Multi-Purpose Incremental Learning System AQ15 and Its Testing Application to Three Medical Domains , 1986, AAAI.

[11]  C. Harlow,et al.  Computational image interpretation models : an overview and a perspective , 1990 .

[12]  Thomas G. Dietterich,et al.  A Comparative Review of Selected Methods for Learning from Examples , 1983 .

[13]  Rosamaria Morpurgo,et al.  D‐KAT: a deep knowledge acquisition tool , 1993 .

[14]  Ivan Bratko,et al.  PROLOG Programming for Artificial Intelligence, Second Edition , 1990 .

[15]  L.L.F. Janssen,et al.  Knowledge-based crop classification of a Landsat thematic mapper image , 1992 .

[16]  R T Newkirk,et al.  A Common Knowledge Database for Remote Sensing and Geographic Information in a Change-Detection Expert System , 1990 .

[17]  Peter Jackson,et al.  Introduction to Expert Systems, 2nd Edition , 1990 .

[18]  J. R. Jensen,et al.  Measurement of seasonal and yearly cattail and waterlily changes using multidate SPOT panchromatic data , 1993 .

[19]  Philip J. Stone,et al.  Experiments in induction , 1966 .

[20]  David Mckeown,et al.  The Role of Artificial Intelligence in the Integration of Remotely Sensed Data with Geographic Information Systems , 1987, IEEE Transactions on Geoscience and Remote Sensing.

[21]  John R. Jensen,et al.  Introductory Digital Image Processing: A Remote Sensing Perspective , 1986 .

[22]  Douglas A. Stow,et al.  Category identification of changed land-use polygons in an integrated image processing/geographic information system , 1992 .

[23]  Ryszard S. Michalski,et al.  A Theory and Methodology of Inductive Learning , 1983, Artificial Intelligence.