Architecture of Information Processing System Based on ES-ANN and Visual C#.net Technology

摘要

This paper focused on the development a corn expert system (ES) without undergoing the traditional process of rules formulation. An automated corn ES is based on trained Artificial Neural Networks (ANNs). An error back-propagation ANNs model was used into the corn ES. The ES system provides a dynamic rule base and knowledge base, while the ANNs estimates standard processing based on the truth and experience of domain experts. The ANNs network architecture is designed to a dual, three-layered back-propagation network of continuous value units, fully-interconnected between layers. The trained ANNs were stored in a data base, representing the knowledge base. The network is trained from raw data, avoiding the persistent need for specific knowledge acquisition from domain experts and continuous work from knowledge engineers. This knowledge base was used in the corn ES successfully.