Abstract
This paper introduces the new GRASS GIS add-on module g.infer. The module enables rule-based analysis and workflow management in GRASS GIS, via data-driven inference processes based on the expert system shell CLIPS. The paper discusses the theoretical and developmental background that will help prepare the reader to use the module for Knowledge Engineering applications. In addition, potential application scenarios are sketched out, ranging from the rule-driven formulation of nontrivial GIS-classification tasks and GIS workflows to ontology management and intelligent software agents.
Highlights
Maps are used to represent the world surrounding us
The emerging methodology of describing the application of rule-based systems in enterprise environments for structured, product-generating activities has been named the Business Rules Approach [2][15]. This is of interest for Geographic Information Systems (GIS) application and the related workflow perspective: GRASS GIS modules can be used in a similar fashion to set-up data-processing workflows, while on a higher level, GRASS GIS-based workflows can be fully integrated into greater workflow-chains
The new add-on module g.infer re-introduces generic rule-based data-driven modelling to GRASS GIS for the current versions of GRASS 6.4.x and GRASS 7
Summary
Maps are used to represent the world surrounding us. They are put into use as tools to categorize, classify and judge our environments, to make decisions and act . If a mapping workflow can be formulated by the human GIS operator, but can not be implemented as script or GIS module, there s a problem In this case, the task at hand is basically solveable, but the available software environment lacks the flexibility to accommodate the workflow within acceptable time and effort constraints. The task at hand is basically solveable, but the available software environment lacks the flexibility to accommodate the workflow within acceptable time and effort constraints This situation occurs frequently for classification tasks (remote sensing data or similar fields), resulting in the use of suboptimal classification algorithms: The implemented solution is not Geoinformatics FCE CTU 8, 2012. Problems which have not fully understood or are very complex to solve In such cases, a rule-based approach, as provided by the new GRASS module g.infer becomes advantageous:. The same holds true for the r.binfer module , which uses an inference engine based on Bayesian statistics (making decisions based on past experience) to assist human experts in a field develop computerized expert systems for land use planning and management, basing bases the probable impacts of a future land use action on the conditional probabilities about the impact of similar past actions [1][2]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
