Research On Mobile Expert System Based On Intelligent Computing

This paper analyses the current states of research on expert systems, especially those of aquaculture domain.To resolve the problems in the field, we did farther user's requirement analysis and studied the old fish disease diagnosis expert systems further, and some documents correlative with them are lucubrated. On the basis of the above works, we put forward the idea and solution, i.e. to build mobile fish disease expert system based on intelligent computing.According to the features of user's requirement and the function required by the mobile fish disease expert system, the knowledge acquisition and reasoning mechanism of expert system working at sever end is studied and designed, which uses rough sets theory, neural network and ant colony algorithm as the key technologies. It can be described as follows: First, use the attributes reduction algorithm based on rough sets to reduce the redundance attributes in the primary data of fish disease cases, which comes from domain experts and the cases in the data are vast and had been diagnosed. Second, take the reduced attributes as the input arguments to build neural network. Thus, the structure of neural network can be diminished effectively. Last, use the corresponding data of the cases training the neural network to acquire the diagnostic knowledge of fish disease and then create the neural network knowledge base. The neural network reasoning machine is constructed based on it. Here, ant colony optimization algorithm is used in the neural network training. The neural network knowledge base with low storage consumption and corresponding reasoning machine with low time-complexity are transplanted into intelligent computational hand equipments. It can successfully solve the problems of mobile expert system in function and application demands.Upon the foundation above, a mobile fish disease expert system based on wireless and wired Internet environments is designed and realized with using many technologies, such as C/C ++, J2EE, J2ME, JSP, Servlet, Java-middleware and WAP, etc.