Assessment of dairy cow feed intake based on BP neural network with polynomial decay learning rate

To overcome the shortcomings of traditional dairy cow feed intake assessment model andBP neural network, this paper proposes a method of optimizing BP neural network usingpolynomial decay learning rate, taking the cow’s body weight, lying duration, lying times,walking steps, foraging duration and concentrate-roughage ratio as input variables andtaking the actual feed intake is the output variable to establish a dairy cow feed intakeassessment model, and the model is trained and verified by experimental data collectedon site. For the sake of comparative study, feed intake is simultaneously assessed by SVRmodel, KNN logistic regression model, traditional BP neural network model, and multilayerBP neural network model. The results show that the established BP model using the polynomial decay learning rate has the highest assessment accuracy, the MSPE, RMSE, MAE,MAPE and R2 are 0.043 kg2/d and 0.208 kg/d, 0.173 kg/d, 1.37% and 0.94 respectively. Compared with SVR model and KNN mode, the RMSE value reduced by 43.9% and 26.5%, it isalso found that the model designed in this paper has many advantages in comparison withthe BP model and multilayer BP model in terms of precision and generalization. Therefore,this method is ready to be applied for accurately evaluating the dairy cow feed intake, andit can provide theoretical guidance and technical support for the precise-feeding and canalso be of high significance in the improvement of dairy precise-breeding.

Remote monitoring system for livestock environmental information based on LoRa wireless ad hoc network technology

The environmental quality of livestock houses is key to livestock breeding and directly affects the growth and health of animals.To target the characteristics of long application cycles and large coverage areas for environmental monitoring in large-scale livestock breeding,the current study designed a remote monitoring system to provide livestock environmental information based on LoRa wireless ad hoc network technology.The system consisted of collection terminals,control terminals,LoRa gateways,and Alibaba Elastic Compute Service.It realized real-time collection,wireless transmission,storage of multi-sensor node data,and remote control.The system was not limited by the selected time or region,because data interaction was achieved by accessing cloud servers using GPRS technology.Users could browse and obtain data from computers and a WeChat mini program from any location with network coverage.Additionally,the system used the improved receiver-based auto rate(RBAR)rate-adaptive algorithm in the LoRa wireless communication component.After application on a dairy farm,the results showed that the whole system collected 6140 sets of environmental data from four dairy houses.The packet loss rate was less than 1%within a communication distance of 604 m,and the communication success rate was greater than 99%.The control instructions were real-time and accurate,and the response time was less than 10 s,which met the remote control needs of large farms.The system provided powerful data and technical support for precision animal production.