Cohen, Y., Environmental Information Laboratory, Department of Geography, Bar-Ilan University, Ramat-Gan 52900, Israel Shoshany, M., Environmental Information Laboratory, Department of Geography, Bar-Ilan University, Ramat-Gan 52900, Israel
A regional-oriented concept of spatial knowledge acquisition and representation is presented and discussed. The representation of real-world complex relationships is achieved by the utilization of both factual knowledge base composed of simple indications and evidential inference mechanism capabilities. Following the regional-oriented strategy, an evidential KBS for crop types recognition in Israel is constructed. The spatial information base is mainly composed of simple indications. Most indications are related to multi-temporal imagery information, representing the most updated, primary and informative source for crop types recognition. The evidential inference engine, which is based on the Gordon-Shortliffe Algorithm (GSA), successfully resolves the complex relationships actually existing between the diverse environmental variables.
Conceptualization and implementation of knowledge based system for crop recognition in heterogeneous Mediterranean environments
6
Cohen, Y., Environmental Information Laboratory, Department of Geography, Bar-Ilan University, Ramat-Gan 52900, Israel Shoshany, M., Environmental Information Laboratory, Department of Geography, Bar-Ilan University, Ramat-Gan 52900, Israel
Conceptualization and implementation of knowledge based system for crop recognition in heterogeneous Mediterranean environments
A regional-oriented concept of spatial knowledge acquisition and representation is presented and discussed. The representation of real-world complex relationships is achieved by the utilization of both factual knowledge base composed of simple indications and evidential inference mechanism capabilities. Following the regional-oriented strategy, an evidential KBS for crop types recognition in Israel is constructed. The spatial information base is mainly composed of simple indications. Most indications are related to multi-temporal imagery information, representing the most updated, primary and informative source for crop types recognition. The evidential inference engine, which is based on the Gordon-Shortliffe Algorithm (GSA), successfully resolves the complex relationships actually existing between the diverse environmental variables.