An Expert System Tool Based On Artificial Neural Network

Modern agriculture needs the support of information technology .The agricultural Expert Systems(ES) are the kind of intellective information technology of agriculture .The application of agricultural Expert Systems alters the blindness and the subjectivism of the decision-maker in agricultural production, reducing the impolicy, allaying the shortage of agricultural technical staff, and promoting the sustainable development of agriculture. However, the traditional Expert Systems only handle the dominant and superficial knowledge ,they have lots of demerit such as weak reasoning ability , poor intelligence and the difficulty in getting knowledge and so on .Therefore, this paper introduces the technology of the Artificial Neural Network(ANN) to overcome the shortage of Expert Systems ,and tries to solve the problem which has complicated relationship ,fuzzy boundary questionably factor and expresses hard in regulation and mathematical model . The Expert system gets most part of knowledge and ratiocinates by using ANN, changes the result of the output of net into the form which the Expert System can understand, gets the final result from the universal reasoning engine. The tool of Expert System on the basis of ANN provides the expert with the friendly multimedia interface. Experts can train the ANN and input the domain experience and knowledge independently. The universal reasoning engine can link different knowledge database and data file to create different Expert Systems for promoting the speed of building Expert Systems . The Expert System for Heliothis's which build on this tool can forecast the incidence of disease correctly, give user the preventive advice. It proves that the feasibility of the Expert System build on this tool in resolving the bottleneck in getting knowledge , realizes collateral reasoning of ANN, have made an attempt at researching the integrating system of ES and ANN.