Design and Experiment of Cow Calving Prediction Equipment Based on Tail Raising Characteristics

被引：0

作者：

Zhao J. ^{[1
,2
]}

Lu ^{[1
,2
]}

Shi F. ^{[1
,2
]}

Dong Z. ^{[1
,2
]}

Song H. ^{[1
,2
]}

机构：

[1] College of Mechanical and Electronic Engineering, Northwest A&F University, Shaanxi, Yangling

[2] Key Laboratory of Agricultural Internet of Things, Ministry of Agriculture and Rural Affairs, Shaanxi, Yangling

来源：

Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery | 2023年 / 54卷 / 04期

关键词：

calving prediction; Internet of things; machine learning; smart animal husbandry; tail raising characteristics;

D O I：

10.6041/j.issn.1000-1298.2023.04.035

中图分类号：

学科分类号：

摘要：

In order to solve the problem of lack of automatic monitoring and predicting equipment in the process of cow production, a cow calving predicting equipment based on the tail raising characteristics was designed. The equipment included a data acquisition node for recording the tail acceleration of cows to be delivered, a wireless networking for data upload and cloud data storage platform, and a calving prediction algorithm based on machine learning model was developed to realize the automatic prediction of cow calving. The tail data acquisition node used STM32L151CBT6A MCU to control ICM42605 sensor to achieve acceleration data acquisition. After finishing data sorting and local storage, the data was uploaded to the gateway through LoRa network. The gateway transmitted data to Tencent Cloud IoT development platform through WiFi network according to MQTT protocol, and synchronously stored the data in Tencent Cloud database. In the algorithm development experiment, based on the data of 25 cows before calving, a production prediction model was developed based on MK trend test and multi SVM of ensemble learning. After the algorithm performance verification, the model was deployed to the Tencent cloud server. The verification test results showed that the acceleration signal measured by the oxtail node had a good correlation with the output signal set by the vibration sensor calibrator (r = 0. 938, P < 0. 01). The node monitoring module can work continuously for 24 d. The field experiment showed that the maximum packet loss rate of the wireless transmission network was 1. 3%, which met the application requirements. After the equipment was deployed, the monitoring of calving process of 11 cows was completed. The results showed that the equipment successfully predicted nine cows (81. 82%) within 12 h before birth. The calving prediction equipment designed based on the tail raising characteristics can be applied to the monitoring and prediction of the actual cow production process. © 2023 Chinese Society of Agricultural Machinery. All rights reserved.

引用

页码：338 / 346and385

共 27 条

[1] AMICIS I D, VERONESI M C, ROBBE D, Et al., Prevalence, causes, resolution and consequences of bovine dystocia in Italy, Theriogenology, 107, pp. 104-108, (2018)
[2] MEE J F, BEEEY D P, CROMIE A R., Prevalence of, and risk factors associated with, perinatal calf mortality in pasture-based Holstein-Friesian cows, Animal, 2, 4, pp. 613-620, (2008)
[3] WEN Changji, WANG Shengsheng, ZHAO Xin, Et al., Visual dictionary for cows sow behavior recognition [J], Transactions of the Chinese Society for Agricultural Machinery, 45, 1, pp. 266-274, (2014)
[4] ROBICHAUD M V, PASSILLE A M, PEARL D L, Et al., Calving management practices on Canadian dairy farms: prevalence of practices, Journal of Dairy Science, 99, 3, pp. 2391-2404, (2016)
[5] YIN Ling, LIU Caixing, HONG Tiansheng, Et al., Design of system for monitoring dairy cattle's behavioral features based on wireless sensor networks, Transactions of the CSAE, 26, 3, pp. 203-208, (2010)
[6] TITLER M, MAQUIVAR M G, BAS S, Et al., Prediction of parturition in Holstein dairy cattle using electronic data loggers, Journal of Dairy Science, 98, 8, pp. 5304-5312, (2015)
[7] RUTTENC J, KAMPHUIS C, HOGEVEEN H, Et al., Sensor data on cow activity, rumination, and ear temperature improve prediction of the start of calving in dairy cows[J], Computers and Electronics in Agriculture, 132, pp. 108-118, (2017)
[8] HIGAKI S, KOYAMA K, SASAKI Y, Et al., Technical note: calving prediction in dairy cattle based on continuous measurements of ventral tail base skin temperature using supervised machine learning, Journal of Dairy Science, 103, 9, pp. 8535-8540, (2020)
[9] BENAISSA S, TUYTTENS F A M, PLETS D, Et al., Calving and estrus detection in dairy cattle using a combination of indoor localization and accelerometer sensors[J], Computers and Electronics in Agriculture, 168, (2020)
[10] OWENS J L, EDEY T N, BINDON B M, Et al., Parturient behaviour and calf survival in a herd selected for twinning, Applied Animal Behaviour Science, 13, 4, pp. 321-333, (1985)

← 1 2 3 →