Detection system of dead and sick chickens in large scale farms based on artificial intelligence

With the continuous enrichment of scientific and technological means, the production of most chicken farms has been able to achieve automation, but for the dead and sick chickens in the farm, there is no automatic monitoring step, only through continuous manual inspection and discovery. In the face...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Yiqin Bao, Hongbing Lu, Qiang Zhao, Zhongxue Yang, Wenbin Xu
Formato: article
Lenguaje:EN
Publicado: AIMS Press 2021
Materias:
Acceso en línea:https://doaj.org/article/a71d6f90e155458f9ebb74f458aa4506
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Descripción
Sumario:With the continuous enrichment of scientific and technological means, the production of most chicken farms has been able to achieve automation, but for the dead and sick chickens in the farm, there is no automatic monitoring step, only through continuous manual inspection and discovery. In the face of this problem, there are many solutions to identify dead and sick chickens through sound and image, but they can not achieve the ideal effect. In this paper, a sensor detection method based on artificial intelligence is proposed. This method 1) The maximum displacement of chicken activity is measured by fastening a foot ring on each chicken, and the three-dimensional total variance is designed and calculated to represent the chicken activity intensity. 2) The detection terminal collects the sensing data of foot ring through ZigBee network. 3) The state of chicken (dead chicken and sick chicken) can be identified by machine learning algorithm. This method of artificial intelligence combined with sensor network not only has high recognition rate, but also can reduce the operation cost. The practical results show that the accuracy of the system to identify dead and sick chickens is 95.6%, and the cost of the system running for 4 years can be reduced by 25% compared with manual operation.