Characteristics Analysis Of Prenatal Behavior For Hu Sheep Based On Embedded And Development Of Monitoring System

In recent years,the breeding density of hu sheep gradually increased.But there were fewer means to monitor their amount of daily exercise and growth environment,resulting in dystocia,abortion,the number of diseases increased sharply.Therefore,it was necessary to collect the vital signs of hu sheep in real-time.According to the data,especially the behavioral monitoring information related to exercise,their health status could be identified.It was convenient for breeding staff to intervene in time to improve their production efficiency.According to the above background and current situation,this study developed a monitoring system for vital signs of hu sheep based on embedded,and then regarding the collected three-axis acceleration data as the research object,realizing the classification and recognition of multiple behaviors for prenatal hu sheep.The work of this paper was as follows:1)Aiming at the current time-consuming and manpower-spending problems of prenatal behavior monitoring of hu sheep,a monitoring system based on embedded was designed.Based on the collar’s acquisition node and Zigbee technology,the collected acceleration data was wirelessly transmitted to the embedded base station.The server received the data from the GPRS module in the base station,and then the data was stored in the My SQL database.Finally,the data was displayed on the webpage or mobile phones.2)Aiming at the problems of low accuracy and less recognizable behaviors of hu sheep in labor,a recognition method for prenatal behavior of hu sheep was proposed based on the classification model of the interval threshold and the Genetic Algorithm-Support Vector Machine(GA-SVM).It was able to realize the accurate identification of drinking,eating,ruminating,walking and lying.The experimental results showed that the monitoring system for vital signs of hu sheep based on embedded could collect and transmit the activity information of prenatal hu sheep’ necks simultaneously.Besides,the classification method based on the interval threshold and GA-SVM could effectively distinguish five kinds of prenatal activities,including drinking,eating,ruminating,walking,and lying.The number of identifiable behavioral types increased,and the applicability was greatly improved.The average accuracy of the classification method proposed in this work was 97.88%,which was 31.26%,21.87%,and 21.9% higher than the traditional decision tree algorithm,the K-Nearest Neighbor(KNN)algorithm,and the SVM algorithm,respectively.It was of great significance for establishing the amount of exercise and health assessment models of prenatal hu sheep,improving the efficiency of reproduction,and realizing intelligent management.