DESIGN AND IMPLEMENTATION OF PIG INTELLIGENT CLASSIFICATION MONITORING SYSTEM BASED ON CONVOLUTION NEURAL NETWORK (CNN)

Abstract

With the development of agricultural information technology, the intelligent monitoring system applied in pigsty can alert people when domestic pigs and wild boars jump into each other's pigsty, and bring convenience to breeding staff. The system uses convolution neural network as the core algorithm to realize the function of real-time monitoring and reminding users. Using Spring MVC framework technology, a pig intelligent classification monitoring system based on C/S architecture is developed. Three layer architecture model of presentation layer, business layer and persistence layer is used. Neural network algorithm is embedded in the image processing module, and Netty framework is used to maintain the connection between each module. Field experiments show that the recognition accuracy of the system can reach 97.08%. This system can be used as a reference for the design of pig intelligent classification monitoring system, and provide a reference for the design of related systems.