| Peer-Reviewed

Research of Estrus Detection Models in Dairy Cows by Activity

Received: 20 June 2018     Published: 22 June 2018
Views:       Downloads:
Abstract

The detection of estrus in large-scale ranch is an extremely labor-intensive task. Accurate and efficient detection can shorten the tires spacing of cow and increase economic income of ranch.The change in activity is one of the most important external features of dairy cows' estrus.In this paper, the activity of cows was collected remotely using activity collectors, wireless transmission networks and cloud servers, and the data was framed, labeled and preprocessed. The logistic regression, MLPs and SVMs model were trained by differential activity data of current and historical dates within the same hour.The experimental results show that the detection model by cow activity has a higher accuracy in predicting the estrus of cows. The SVMs in the three models have the best prediction effect. The recall and accuracy rate reach 90.12% and 93.74%, respectively.In the actual ranch test, the estrus detection system using the SVM model has more than double the exposure rate than the manual disclosure.

Published in Science Discovery (Volume 6, Issue 2)
DOI 10.11648/j.sd.20180602.15
Page(s) 102-109
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2018. Published by Science Publishing Group

Keywords

Cows Estrus Prediction, Activity, Logistic Regression, Multilayer Perceptions, Support Vector Machine

References
[1] Kiddy C A. Variation in physical activity as an indicator of oestrus in dairy cows[J].Dairy Sci, 1977, 60(4): 235~243.
[2] Schofield S A, Phillips C J C, Owens A R. Variation in milk production activity rate and electrical impedance of cervical mucus over the oestrus period of dairy cows [J]. Anim. Reprod. Sci, 1991, 24(2): 231~248.
[3] Firk R, Stamer E, Junge W et al. Automation of oestrus detection in dairy cows: a review [J]. Livestock Production Science, 2002, 75(3): 219~232.
[4] Homer EM, Derecka K, Webb R et al. Mutations in genes involved in oestrous cycle associated expression of oestrus [J]. Animal Reproduction Science, 2013, 142(3): 106~112.
[5] Audrey C,Stéphanie C, Julie G et al. Comparison of three devices for the automated detection of estrus in dairy cows [J]. Theriogenology, 2014, 82(5): 734~741.
[6] Reith S, Brandt H, Hoy S. Simultaneous analysis of activity and rumination time, based on collar-mounted sensor technology, of dairy cows over the peri-estrus period [J]. Livestock Science, 2014, 170(1): 219~227.
[7] 田富洋,王冉冉,刘莫尘,等.基于神经网络的奶牛发情行为辨识与预测研究[J].农业机械学报,2013,44(z1):277~281。
[8] 尹令,洪添胜,刘迎湖,等.基于无线传感器网络支持向量机奶牛行为特征识别[J].传感技术学报,2011,24(3):458~462。
[9] 尹令,刘财兴,洪添胜,等.基于无线传感器网络的奶牛行为特征监测系统设计[J].农业工程学报,2010,26(3):203~208。
[10] 赵凯旋,何东健,王恩泽.基于视频分析的奶牛呼吸频率与异常检测[J].农业机械学报,2014,45(10):258~263。
[11] 顾静秋,王志海,高荣华,等.基于融合图像与运动量的奶牛行为识别方法[J].农业机械学报,2017,48(6):145-151。
[12] 侯云涛,蔡晓华,吴泽全,等.奶牛行为特征识别方法的研究与实现—基于支持向量机[J].农机化研究, 2018, 40(8):36-41。
[13] 张爽.奶牛个体反刍行为监测技术研究[D].东北农业大学,2017。
[14] Cox D R. The regression analysis of binary sequences [J]. J Roy Stat Soc B, 1958, 20(3): 215~242.
[15] Walker S H, Duncan D B. Estimation of the probability of an event as a function of several independent variables [J]. Biometrika, 1967, 54(1):167~178.
[16] Werbos P J. Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences [D]. Phd thesis, Harvard University,1974.
[17] Cortes C, Vapnik V. Support-vector networks [J]. Machine Learning, 1995, 20(3): 273~275.
[18] Collobert R, Bengio S. Links between Perceptrons, MLPs and SVMs [C]. New York: ICML, 2004:23~30.
Cite This Article
  • APA Style

    Daoerji Fan, Huijuan Wu. (2018). Research of Estrus Detection Models in Dairy Cows by Activity. Science Discovery, 6(2), 102-109. https://doi.org/10.11648/j.sd.20180602.15

    Copy | Download

    ACS Style

    Daoerji Fan; Huijuan Wu. Research of Estrus Detection Models in Dairy Cows by Activity. Sci. Discov. 2018, 6(2), 102-109. doi: 10.11648/j.sd.20180602.15

    Copy | Download

    AMA Style

    Daoerji Fan, Huijuan Wu. Research of Estrus Detection Models in Dairy Cows by Activity. Sci Discov. 2018;6(2):102-109. doi: 10.11648/j.sd.20180602.15

    Copy | Download

  • @article{10.11648/j.sd.20180602.15,
      author = {Daoerji Fan and Huijuan Wu},
      title = {Research of Estrus Detection Models in Dairy Cows by Activity},
      journal = {Science Discovery},
      volume = {6},
      number = {2},
      pages = {102-109},
      doi = {10.11648/j.sd.20180602.15},
      url = {https://doi.org/10.11648/j.sd.20180602.15},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sd.20180602.15},
      abstract = {The detection of estrus in large-scale ranch is an extremely labor-intensive task. Accurate and efficient detection can shorten the tires spacing of cow and increase economic income of ranch.The change in activity is one of the most important external features of dairy cows' estrus.In this paper, the activity of cows was collected remotely using activity collectors, wireless transmission networks and cloud servers, and the data was framed, labeled and preprocessed. The logistic regression, MLPs and SVMs model were trained by differential activity data of current and historical dates within the same hour.The experimental results show that the detection model by cow activity has a higher accuracy in predicting the estrus of cows. The SVMs in the three models have the best prediction effect. The recall and accuracy rate reach 90.12% and 93.74%, respectively.In the actual ranch test, the estrus detection system using the SVM model has more than double the exposure rate than the manual disclosure.},
     year = {2018}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Research of Estrus Detection Models in Dairy Cows by Activity
    AU  - Daoerji Fan
    AU  - Huijuan Wu
    Y1  - 2018/06/22
    PY  - 2018
    N1  - https://doi.org/10.11648/j.sd.20180602.15
    DO  - 10.11648/j.sd.20180602.15
    T2  - Science Discovery
    JF  - Science Discovery
    JO  - Science Discovery
    SP  - 102
    EP  - 109
    PB  - Science Publishing Group
    SN  - 2331-0650
    UR  - https://doi.org/10.11648/j.sd.20180602.15
    AB  - The detection of estrus in large-scale ranch is an extremely labor-intensive task. Accurate and efficient detection can shorten the tires spacing of cow and increase economic income of ranch.The change in activity is one of the most important external features of dairy cows' estrus.In this paper, the activity of cows was collected remotely using activity collectors, wireless transmission networks and cloud servers, and the data was framed, labeled and preprocessed. The logistic regression, MLPs and SVMs model were trained by differential activity data of current and historical dates within the same hour.The experimental results show that the detection model by cow activity has a higher accuracy in predicting the estrus of cows. The SVMs in the three models have the best prediction effect. The recall and accuracy rate reach 90.12% and 93.74%, respectively.In the actual ranch test, the estrus detection system using the SVM model has more than double the exposure rate than the manual disclosure.
    VL  - 6
    IS  - 2
    ER  - 

    Copy | Download

Author Information
  • College of Electronic Information Engineering, Inner Mongolia University, Hohhot, China

  • College of Electronic Information Engineering, Inner Mongolia University, Hohhot, China

  • Sections