Early warning in egg production curves from commercial hens: A SVM approach
详细信息 查看全文
- 作者：Ivá ; n Ramí ; rez Moralesa ; b ; iramirez@utmachala.edu.ec" class="auth_mail" title="E-mail the corresponding author ; Daniel Rivero Cebriá ; nb ; Enrique Ferná ; ndez Blancob ; Alejandro Pazos Sierrab
- 关键词：Early warning ; Drop in egg production ; Poultry management ; Support vector machines ; Machine learning
- 刊名：Computers and Electronics in Agriculture
- 出版年：2016
- 出版时间：February 2016
- 年：2016
- 卷：121
- 期：Complete
- 页码：169-179
- 全文大小：1954 K
文摘
- •
Support vector machines were used for early detection of problems in egg production.
- •
Farm’s egg production data were collected from 478,919 laying hens grouped in 21 flocks.
- •
Alerts from zero to three days in advance were achieved with data from test set.
- •
An accuracy of 0.9854 was performed for one day in advance alert.
- •
As forecasting interval was increased up to five, good performance metrics were achieved.