Research Article
BibTex RIS Cite

Determination of Estrus in Cattle with Artificial Neural Networks Using Mobility and Environmental Data

Year 2022, Volume: 39 Issue: 1, 40 - 45, 30.04.2022
https://doi.org/10.55507/gopzfd.1116155

Abstract

Detection of estrus with high accuracy directly affects the possibility of cows becoming pregnant and so also milk production. Most milk is obtained in the early lactation period, after calving. Animals in estrus are more active than others. This mobility can be measured by a testing device called "pedometer." Estrus can be estimated using detected movement changes with artificial neural networks (ANN) models. This study aims to create and assess the effectiveness of a neural network model to estimate estrus in cattle by using movement and environmental data. Movement data of 78 cattle, which showed 184 estruses have been captured along with climatic data during a seven-month period at a private agricultural organization. Data such as cow age, lactation number and number of days elapsed from estrus were also taken into account and evaluated. ANN models were compared with accuracy, precision and F-scores. Two-layer classification networks were tested for feed-forward neural network model. Optimal inputs to the neural network model were found to be motion data, motion data of the previous period, the number of days after the previous estrus, temperature and humidity. Two-layer network with 37 for the first layer and 40 neurons in the second layer has been the most successful model with a 0.1775 F - score. The study has shown that the accuracy of estrus prediction is increased by evaluating movement data along with climate data.

References

  • Alpaydın, E. (2010). Introduction to Machine Learning, The MIT Press, Cambridge, Massachusetts.
  • Aungier, S. P. M., Roche, J. F., Sheehy, M., & Crowe, M. A. (2012). Effects of management and health on the use of activity monitoring for estrus detection in dairy cows. J Dairy Sci. 95:2452–66.
  • Beyaz, A., Öztürk, R., & Acar, A. İ. (2012). Süt Sağım Tesislerinde Görüntü Analiz Teknikleri ile Fiziksel Yüklenmenin Belirlenmesi. 18. Ulusal Ergonomi Kongresi, 511-518.
  • Bishop, C. M. (1995). Neural Network for Pattern Recognition. Clarendon, Oxford.
  • Brunassi, L. A., Moura, D. J., Naas, I. A., Vale, M. M., Souza, S. R. L., Lima, K. A. O., Carvalho, T. M. R., & Bueno, L. G. F. (2010). Improving Detection of Dairy Cow Estrus Using Fuzzy Logic. Scientia Agicola, 67(5), 503-509.
  • Chegini, G. R., Khazaei, J., Ghobadian, B., & Goudarzi, A. M. (2008). Prediction of Process and Product Parameters in an Orange Juice Spray Dryer Using Artificial Neural Networks. Journal of Food Engineering, 84(2008), 534-543.
  • Daniel, U. (2006). Sığırcılık. Bilge Kültür Sanat, İstanbul.
  • De Mol, R. M., Keen, A., Krozeze, G. H., & Achten, J. M. F. H. (1999). Description of a Detection Model for Oestrus and Diseases in Dairy Cattle Based on Time Series Analysis Combined with a Kalman Filter. Computer and Electronics in Agriculture, 22(1999), 171-185.
  • Demirci, E. (2007). Evcil Hayvanlarda Reprodüksiyon; Suni Tohumlama ve Androloji Ders Notları, F.Ü. Veterinerlik Fakültesi Ders Teksiri No:57.
  • Dulyala, R., Kuankid, S., Rattanawong, T., & Aurasopon, A. (2014). Classification system for estrus behavior of cow using an Accelerometer. Asia-Pacific Signal and Information Processing Association (APSIPA) Annual Summit and Conference, 9-12 December 2014, FA1-6, Siem Reap, city of Angkor Wat, Cambodia.
  • Firk, R., Stamer, E., Junge, W., & Krieter, J. (2002). Automation of Oestrus Detection in Dairy Cows: A Review. Livestock Produciton Science, 75(2002), 219-232.
  • Galina, C. S., & Orihuela, A. (2007). The detection of estrus in cattle raised under tropical conditions: what we know and what we need to know. Horm Behav, 52:32–8.
  • Garcia, A. (2006). Dealing with Heat Stress in Dairy Cows. http://pubstorage.sdstate.edu/AgBio_Publications/articles/EXEX4024.pdf
  • Hulsen, J. (2012). Sığır Davranışları, Translators: Ayhan Öztürk, Birol Dağ, Uğur Zülkadir. Zutphen, ROODBant Publishers, Hollanda.
  • Krieter, J. S. E. J. W. (2005). Oestrus Detection in Dairy Cows Using Control Charts and Neural Networks. 56th Annual Meeting of the Eurapan Association for Animal Production (EAAP) 5-8 Nisan, Uppsala-Sweden.
  • Madadlou, A., Emam-Djomeh, Z., Mousavi, M. E., Ehsani, M., Javanmard, M., & Sheehan, D. (2009). Response Surface Optimization of an Artificial Neural Network for Predicting the Size of Re-assembled Casein Micelles. Computers and Electronics in Agriculture, 68(2009), 216-221.
  • Mitchell, R. S., Sherlock, R. A., & Simith, L. A. (1996). An Investigation into Use of Machine Learnings for Determining Oestrus in Cows. Computers and Electronics in Agriculture, 15(1996), 195-213.
  • Moller, M. (1993). A Scaled Conjugate Gradiant Algorithm for Fast Supervised Learning. Neural Networks, 6(1993), 525-533.
  • Nadimi, E. S., Jorgensen, R. N., Blanes-Vidal, V., & Christensen, S. (2012). Monitoring and Classifying Animal Behavior Using ZigBee-Based Mabile Ad Hoc Wireless Sensor Networks and Artificial Neural Networks. Computer and Electronics in Agriculture, 2012(82), 44-54.
  • Neethirajan, S. (2020). The Role of Sensors, Big Data and Machine Learning in Modern Animal Farming. Sensing and Bio-Sensing Research, 29 (2020) 100367. https://doi.org/10.1016/j.sbsr.2020.100367.
  • Orman, A. (2011). Temel Sürü Sağlığı Yönetimi, (Editör: Oğan, M.), Anadolu Üniversitesi Yayınları No:2333, Eskişehir.
  • Özgüven, M. M. (2018). Hassas Tarım. Akfon Yayınları, Ankara. ISBN: 978-605-68762-4-0.
  • Peralta, O. A., Pearson, R. E., & Nebel, R. L. (2005). Comparison of three estrus detection systems during summer in a large commercial dairy herd. Anim Reprod Sci. 87(1-2):59-72. doi: 10.1016/j.anireprosci.2004.10.003.
  • Roelofs, J. B., van Eerdenburg, F., Soede, N. M., & Kemp, B. (2005). Pedometer Readings for Estrous Detection and As Predictor for Time Ovulation in Dairy Cattle. Theriogenology, 64, 1690e1703. https://doi.org/10.1016/j.theriogenology.2005.04.004.
  • Sarıbay, M. K., & Erdem, H. (2008). İneklerde Gözlem Yöntemi ile Östrus Tespiti. Veteriner Hekimler Derneği Dergisi, 79(3), 43-50.
  • Senger, P. (1994). The estrus detection problem: new concepts, technologies, and possibilities. J Dairy Sci. 77: 2745e53.
  • Shahriar, Md. S., Smith, D., Rahman, A., Freeman, M., Hills, J., Rawnsley, R., Henry, D. & Bishop-Hurley, G., (2016) Detecting heat events in dairy cows using accelerometers and unsupervised learning. Computers and Electronics in Agriculture. C:(128). 20-26.
  • Sönmez, M., Demirci, E., Türk, G., & Gür, S. (2005). Effect of Season on Some Fertility Parameters of Dairy and Beef Cows in Elazığ Province. Turk J Vet Anim Sci, 29, 821-828.
  • Thanh, L. T., Nishikawa, R., Takemoto, M., Binh, H. T. T., & Nakajo, H. (2018). Cow estrus detection via Discrete Wavelet Transformation and Unsupervised Clustering. SoICT 2018 Proceedings of the Ninth International Symposium on Information and Communication Technology, 305-312. Danang City, Viet Nam — December 06 - 07, 2018.
  • Tömek, B. (2007). Süt Sığırcılığında Sürü Yönetimi Alanında Kullanılan Çağdaş Teknoloji Uygulamaları Üzerine Bir Değerlendirme (Master Thesis). Ege Üniversitesi Fen Bilimleri Enstitüsü, İzmir.
  • Williamson, N., Alawneh, J., Bailey, D., & Butler, K. (2006). Electronic Heat Detection. South Island Dairy Event (SIDE), South Island.
  • Yin, L., Hong, T., & Liu, C. (2013). Estrus Detection in Dairy Cows from Acceleration Data using Self-learning Classification Models. Journal of Computers. 8(10). 2590-2597.

Hareketlilik ve Çevre Verileri Kullanılarak Yapay Sinir Ağları ile Sığırlarda Kızgınlık Tespiti

Year 2022, Volume: 39 Issue: 1, 40 - 45, 30.04.2022
https://doi.org/10.55507/gopzfd.1116155

Abstract

Kızgınlığın yüksek doğrulukla tespiti, ineklerin gebe kalma olasılığını ve dolayısıyla süt üretimini doğrudan etkiler. Sütün çoğu, doğumdan sonra erken laktasyon döneminde elde edilir. Kızgınlık dönemindeki hayvanlar diğerlerinden daha aktiftir. Bu hareketlilik, "pedometre" adı verilen bir test cihazı ile ölçülebilir. Yapay sinir ağları (YSA) modelleri ile tespit edilen hareket değişiklikleri kullanılarak kızgınlık tahmin edilebilir. Bu çalışma, hareket ve çevresel verileri kullanarak sığırlarda kızgınlığı tahmin etmek için bir sinir ağı modelinin etkinliğini oluşturmayı ve değerlendirmeyi amaçlamaktadır. Özel bir tarım kuruluşunda yedi aylık dönemde 184 kızgınlık gösteren 78 büyükbaş hayvanın hareket verisi ve çalışma dönemindeki iklim verisi elde edilmiştir. İnek yaşı, laktasyon sayısı ve kızgınlıktan sonra geçen gün sayısı gibi veriler de dikkate alınmış ve değerlendirilmiştir. YSA modelleri doğruluk, kesinlik ve F-skorları ile karşılaştırılmıştır. İki katmanlı sınıflandırma ağları, ileri beslemeli sinir ağı modeli için test edilmiştir. Sinir ağı modeline en uygun girdilerin hareket verileri, önceki döneme ait hareket verileri, bir önceki kızgınlıktan sonraki gün sayısı, sıcaklık ve nem olduğu anlaşılmıştır. Birinci katmanda 37 ve ikinci katmanda 40 nöron bulunan iki katmanlı ağ, 0,1775 F-skoru ile en başarılı model olmuştur. Çalışma, iklim verileriyle birlikte hareket verilerinin değerlendirerek kızgınlık tahmininin doğruluğunun arttığını göstermiştir.

References

  • Alpaydın, E. (2010). Introduction to Machine Learning, The MIT Press, Cambridge, Massachusetts.
  • Aungier, S. P. M., Roche, J. F., Sheehy, M., & Crowe, M. A. (2012). Effects of management and health on the use of activity monitoring for estrus detection in dairy cows. J Dairy Sci. 95:2452–66.
  • Beyaz, A., Öztürk, R., & Acar, A. İ. (2012). Süt Sağım Tesislerinde Görüntü Analiz Teknikleri ile Fiziksel Yüklenmenin Belirlenmesi. 18. Ulusal Ergonomi Kongresi, 511-518.
  • Bishop, C. M. (1995). Neural Network for Pattern Recognition. Clarendon, Oxford.
  • Brunassi, L. A., Moura, D. J., Naas, I. A., Vale, M. M., Souza, S. R. L., Lima, K. A. O., Carvalho, T. M. R., & Bueno, L. G. F. (2010). Improving Detection of Dairy Cow Estrus Using Fuzzy Logic. Scientia Agicola, 67(5), 503-509.
  • Chegini, G. R., Khazaei, J., Ghobadian, B., & Goudarzi, A. M. (2008). Prediction of Process and Product Parameters in an Orange Juice Spray Dryer Using Artificial Neural Networks. Journal of Food Engineering, 84(2008), 534-543.
  • Daniel, U. (2006). Sığırcılık. Bilge Kültür Sanat, İstanbul.
  • De Mol, R. M., Keen, A., Krozeze, G. H., & Achten, J. M. F. H. (1999). Description of a Detection Model for Oestrus and Diseases in Dairy Cattle Based on Time Series Analysis Combined with a Kalman Filter. Computer and Electronics in Agriculture, 22(1999), 171-185.
  • Demirci, E. (2007). Evcil Hayvanlarda Reprodüksiyon; Suni Tohumlama ve Androloji Ders Notları, F.Ü. Veterinerlik Fakültesi Ders Teksiri No:57.
  • Dulyala, R., Kuankid, S., Rattanawong, T., & Aurasopon, A. (2014). Classification system for estrus behavior of cow using an Accelerometer. Asia-Pacific Signal and Information Processing Association (APSIPA) Annual Summit and Conference, 9-12 December 2014, FA1-6, Siem Reap, city of Angkor Wat, Cambodia.
  • Firk, R., Stamer, E., Junge, W., & Krieter, J. (2002). Automation of Oestrus Detection in Dairy Cows: A Review. Livestock Produciton Science, 75(2002), 219-232.
  • Galina, C. S., & Orihuela, A. (2007). The detection of estrus in cattle raised under tropical conditions: what we know and what we need to know. Horm Behav, 52:32–8.
  • Garcia, A. (2006). Dealing with Heat Stress in Dairy Cows. http://pubstorage.sdstate.edu/AgBio_Publications/articles/EXEX4024.pdf
  • Hulsen, J. (2012). Sığır Davranışları, Translators: Ayhan Öztürk, Birol Dağ, Uğur Zülkadir. Zutphen, ROODBant Publishers, Hollanda.
  • Krieter, J. S. E. J. W. (2005). Oestrus Detection in Dairy Cows Using Control Charts and Neural Networks. 56th Annual Meeting of the Eurapan Association for Animal Production (EAAP) 5-8 Nisan, Uppsala-Sweden.
  • Madadlou, A., Emam-Djomeh, Z., Mousavi, M. E., Ehsani, M., Javanmard, M., & Sheehan, D. (2009). Response Surface Optimization of an Artificial Neural Network for Predicting the Size of Re-assembled Casein Micelles. Computers and Electronics in Agriculture, 68(2009), 216-221.
  • Mitchell, R. S., Sherlock, R. A., & Simith, L. A. (1996). An Investigation into Use of Machine Learnings for Determining Oestrus in Cows. Computers and Electronics in Agriculture, 15(1996), 195-213.
  • Moller, M. (1993). A Scaled Conjugate Gradiant Algorithm for Fast Supervised Learning. Neural Networks, 6(1993), 525-533.
  • Nadimi, E. S., Jorgensen, R. N., Blanes-Vidal, V., & Christensen, S. (2012). Monitoring and Classifying Animal Behavior Using ZigBee-Based Mabile Ad Hoc Wireless Sensor Networks and Artificial Neural Networks. Computer and Electronics in Agriculture, 2012(82), 44-54.
  • Neethirajan, S. (2020). The Role of Sensors, Big Data and Machine Learning in Modern Animal Farming. Sensing and Bio-Sensing Research, 29 (2020) 100367. https://doi.org/10.1016/j.sbsr.2020.100367.
  • Orman, A. (2011). Temel Sürü Sağlığı Yönetimi, (Editör: Oğan, M.), Anadolu Üniversitesi Yayınları No:2333, Eskişehir.
  • Özgüven, M. M. (2018). Hassas Tarım. Akfon Yayınları, Ankara. ISBN: 978-605-68762-4-0.
  • Peralta, O. A., Pearson, R. E., & Nebel, R. L. (2005). Comparison of three estrus detection systems during summer in a large commercial dairy herd. Anim Reprod Sci. 87(1-2):59-72. doi: 10.1016/j.anireprosci.2004.10.003.
  • Roelofs, J. B., van Eerdenburg, F., Soede, N. M., & Kemp, B. (2005). Pedometer Readings for Estrous Detection and As Predictor for Time Ovulation in Dairy Cattle. Theriogenology, 64, 1690e1703. https://doi.org/10.1016/j.theriogenology.2005.04.004.
  • Sarıbay, M. K., & Erdem, H. (2008). İneklerde Gözlem Yöntemi ile Östrus Tespiti. Veteriner Hekimler Derneği Dergisi, 79(3), 43-50.
  • Senger, P. (1994). The estrus detection problem: new concepts, technologies, and possibilities. J Dairy Sci. 77: 2745e53.
  • Shahriar, Md. S., Smith, D., Rahman, A., Freeman, M., Hills, J., Rawnsley, R., Henry, D. & Bishop-Hurley, G., (2016) Detecting heat events in dairy cows using accelerometers and unsupervised learning. Computers and Electronics in Agriculture. C:(128). 20-26.
  • Sönmez, M., Demirci, E., Türk, G., & Gür, S. (2005). Effect of Season on Some Fertility Parameters of Dairy and Beef Cows in Elazığ Province. Turk J Vet Anim Sci, 29, 821-828.
  • Thanh, L. T., Nishikawa, R., Takemoto, M., Binh, H. T. T., & Nakajo, H. (2018). Cow estrus detection via Discrete Wavelet Transformation and Unsupervised Clustering. SoICT 2018 Proceedings of the Ninth International Symposium on Information and Communication Technology, 305-312. Danang City, Viet Nam — December 06 - 07, 2018.
  • Tömek, B. (2007). Süt Sığırcılığında Sürü Yönetimi Alanında Kullanılan Çağdaş Teknoloji Uygulamaları Üzerine Bir Değerlendirme (Master Thesis). Ege Üniversitesi Fen Bilimleri Enstitüsü, İzmir.
  • Williamson, N., Alawneh, J., Bailey, D., & Butler, K. (2006). Electronic Heat Detection. South Island Dairy Event (SIDE), South Island.
  • Yin, L., Hong, T., & Liu, C. (2013). Estrus Detection in Dairy Cows from Acceleration Data using Self-learning Classification Models. Journal of Computers. 8(10). 2590-2597.
There are 32 citations in total.

Details

Primary Language English
Subjects Agricultural, Veterinary and Food Sciences
Journal Section Research Articles
Authors

Adil Koray Yıldız 0000-0002-6472-5276

Mehmet Metin Özgüven This is me 0000-0002-6421-4804

Publication Date April 30, 2022
Published in Issue Year 2022 Volume: 39 Issue: 1

Cite

APA Yıldız, A. K., & Özgüven, M. M. (2022). Determination of Estrus in Cattle with Artificial Neural Networks Using Mobility and Environmental Data. Journal of Agricultural Faculty of Gaziosmanpaşa University (JAFAG), 39(1), 40-45. https://doi.org/10.55507/gopzfd.1116155