Ontology-Based Approach to Context Modeling for Late Blight Disease Management in Irish Potato

Abstract

Over the years, various approaches to context modeling and reasoning have been proposed. The approaches have been applied in different domains resulting in significant contributions as well as notable shortcomings. Context refers to the surroundings of an entity that may influence the decision or activity of that entity. Context dimensions include location, time, environment, activity and user preferences. Context information characterizing these dimensions is often dynamic, uncertain and heterogeneous. We propose an ontology-based <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a</sup>pproach to context modeling for late blight disease management in Irish potato. A context ontology was developed to model the domain knowledge of late blight disease while reasoning was achieved using SWRL rules. Our work targets to avail disease management advice that is context-specific thus improving relevance and uptake. The proposed model was evaluated using actual farm data and an accuracy of 88.6 % in disease inference was attained.