Design and Development of Semanctic Web based Guava Expert System for Disease Classification

Abstract: Neural net is an artificial representation of the human brain that tries to simulate the learning process. Artificial Neural Networks (ANN) architecture is a Multilayer Perceptron (MLP) network, widely used for solving problems related to data classifications, implemented in computer programs which involve large number of necessary calculations. Expert Systems are used to simulate human expert for solving a variety of engineering problems. Normally acquiring knowledge is a big problem in developing the expert systems. In this paper a three layered artificial neural network is used for identifying the disease of the Guava crop. A critical study is conducted for understanding the semantic web stack and applied to design and develop a �Semantic Web Based Guava Expert System". The Guava expert system has two modules namely, information system and expert advisor system. The Guava crop Information system provides some semantic information about Guava varieties, nutrient management, pest and disease management, weed management and post harvesting techniques, whereas advisory system takes inputs from the farmer and processes it using back propagation algorithm to identify the disease.

Keywords: URIs, Resource Description Framework, RDF schema, Ontology, Artificial Neural Networks, Back Propagation Algorithm.