A Method for Individual Identification of Dairy Cows Based on Deep Learning

Individual animal identification is an essential part of the large-scale, informatized, and refined development of animal husbandry, because it can trace the milk source and meat products of each cow, and it can also promote the smooth development of beef cattle insurance policies. Deep learning technologies are used to help identify individual livestock. These technologies can help staff avoid too intensive labor and time-consuming, worry-free and accurate identification of animals. This research proposes a robust deep learning method to classify 5 Holstein cows in the same cowshed. In order to prove this concept, the 48-hour activity data of 5 cows collected by a collar equipped with an activity collector were combined to create a data set. After feature extraction of the data, a deep neural network model based on the Keras framework was selected. The best result of the deep neural network reached 93.81% precision, 93.49% recall and 93.45% F1-score. The results show that the method has high precision, recall and F1 score, and can classify and identify different cows.

[1]  G. Fosgate,et al.  Ear-tag retention and identification methods for extensively managed water buffalo (Bubalus bubalis) in Trinidad. , 2006, Preventive veterinary medicine.

[2]  J. Scordino.  Steller sea lions (Eumetopias jubatus) of Oregon and Northern California: seasonal haulout abundance patterns, movements of marked juveniles, and effects of hot-iron branding on apparent survival of pups at Rogue Reef , 2006 .

[3]  Michael Goshey,et al.  Radio Frequency Identification (RFID) , 2008, ACM SIGSPATIAL International Workshop on Advances in Geographic Information Systems.

[4]  Pawel Rotter,et al.  A Framework for Assessing RFID System Security and Privacy Risks , 2008, IEEE Pervasive Computing.

[5]  Francis Butler,et al.  The end of the identity crisis? Advances in biometric markers for animal identification. , 2009 .

[6]  Davide Maltoni,et al.  Advances in fingerprint modeling , 2009, Image Vis. Comput..

[7]  Marta Hernandez-Jover,et al.  Assessment of acute pain experienced by piglets from ear tagging, ear notching and intraperitoneal injectable transponders , 2010 .

[8]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[9]  L. Ruiz-Garcia,et al.  The role of RFID in agriculture: Applications, limitations and challenges , 2011 .

[10]  Anil K. Jain,et al.  Biometric Authentication: System Security and User Privacy , 2012, Computer.

[11]  Aniati Murni Arymurthy,et al.  Beef cattle identification based on muzzle pattern using a matching refinement technique in the SIFT method , 2013 .

[12]  Woo Chaw Seng,et al.  A review of biometric technology along with trends and prospects , 2014, Pattern Recognit..

[13]  Steffen Hoy,et al.  Simultaneous analysis of activity and rumination time, based on collar-mounted sensor technology, of dairy cows over the peri-estrus period , 2014 .

[14]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[15]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[16]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[17]  Václav Snásel,et al.  Biometric cattle identification approach based on Weber's Local Descriptor and AdaBoost classifier , 2016, Comput. Electron. Agric..

[18]  Ali Ismail Awad,et al.  From classical methods to animal biometrics: A review on cattle identification and tracking , 2016, Comput. Electron. Agric..

[19]  Daniel Berckmans,et al.  Appropriate data visualisation is key to Precision Livestock Farming acceptance , 2017, Comput. Electron. Agric..

[20]  C. Arcidiacono,et al.  Development of a threshold-based classifier for real-time recognition of cow feeding and standing behavioural activities from accelerometer data , 2017, Comput. Electron. Agric..

[21]  Aaron Ingham,et al.  Cattle behaviour classification from collar, halter, and ear tag sensors , 2017 .

[22]  Fengshan Bai,et al.  Research on Cow Rumination Monitoring Based on New Activity Sensor , 2019, 2019 9th International Conference on Information Science and Technology (ICIST).

[23]  Yasushi Chida,et al.  Dairy cattle behavior classifications based on decision tree learning using 3-axis neck-mounted accelerometers. , 2019, Animal science journal = Nihon chikusan Gakkaiho.

[24]  Ksh. Nilakanta Singh,et al.  Machine Learning based Decision Support System for Post Mortem Inspection of Pig Health , 2019, 2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS).