Sound Analysis to Recognize Cattle Vocalization in a Semi-open Barn

Abstract

In precision livestock, there has been a growing demand for innovative tools that collect and analyze information about individual animals. For this purpose, various variables of precision livestock such as monitoring the general condition of animals, activity and health status, food intake, or estrous activity are measured by using information technology. In recent years, the requirement for sound analysis to be used in these systems has increased. Because collecting sound signals do not require animal intervention. Dairy cattle make different sounds in cases of illness, pregnancy, feeding, etc., and by using sound signals, the diagnosis and status determination of the animal can be made. The aim of this study is to record the vocalization data of a dairy cattle in a semi-open barn and to investigate its differences from other barn sounds. It has been revealed that the frequency ranges of cattle, environment, bird, and machine sounds, which are analyzed by time domain, frequency domain, and spectrogram, are different and these differences can be used in a cattle identification system.

Keywords

• cattle vocalization
• sound analysis
• spectrogram

Yarı-açık bir Ahırda Sığır Vokalizasyonunu Tanımak için Ses Analizi

Abstract

Hassas hayvancılıkta, hayvanlar hakkında bilgi toplayan ve analiz eden yenilikçi araçlara yönelik artan bir talep vardır. Bu amaçla, hayvanların genel durumlarının izlenmesi, aktivite ve sağlık durumu, gıda alımı veya kızgınlık aktivitesi gibi hassas hayvancılığın çeşitli değişkenleri bilgi teknolojileri kullanılarak ölçülür. Son yıllarda bu sistemlerde kullanılacak ses analizlerine olan ihtiyaç artmıştır. Çünkü ses sinyallerini toplamak hayvan müdahalesi gerektirmez. Süt sığırları hastalık, hamilelik, beslenme vb. durumlarda farklı sesler çıkarır ve ses sinyalleri kullanılarak hayvanın teşhis ve durum tespiti yapılabilmektedir. Bu çalışmanın amacı, ahırda bulunan bir süt sığırının vokalizasyon verilerini kayıt altına almak ve diğer ahır seslerinden farkını araştırmaktır. Zaman domeni, frekans domeni ve spektrogram ile analiz edilen sığır, ortam, kuş ve makine seslerinin frekans aralıklarının farklı olduğu ve bu farklılıkların bir sığır tanımlama sisteminde kullanılabileceği ortaya konulmuştur

Keywords

• sığır vokalizasyonu
• ses analizi
• spektrogram

References

1. [1] T. R. Beckham and L. K. Holmstrom, “The Use of Information Technology in Animal Health Management, Disease Reporting, Surveillance, and Emergency Response,” 83rd Gen. Sess. World Assem. World Organ. Anim. Heal., vol. 33, no. 0, pp. 1–15, 2015.
2. [2] E. Tullo, I. Fontana, and M. Guarino, “Precision livestock farming: an overview of image and sound labelling,” in European Conference on Precision Livestock Farming 2013:(PLF) EC-PLF, 2013, pp. 30–38.
3. [3] V. C. Dalcin et al., “Physiological parameters for thermal stress in dairy cattle,” Rev. Bras. Zootec., vol. 45, no. 8, pp. 458–465, Aug. 2016. https://doi.org/10.1590/S1806-92902016000800006.
4. [4] J. Wang, M. Bell, X. Liu, and G. Liu, “Machine-learning techniques can enhance dairy cow estrus detection using location and acceleration data,” Animals, vol. 10, no. 7, pp. 1–17, 2020. https://doi.org/10.3390/ani10071160.
5. [5] S. Stankovski, G. Ostojic, I. Senk, M. Rakic-Skokovic, S. Trivunovic, and D. Kucevic, “Dairy cow monitoring by RFID,” Sci. Agric., vol. 69, no. 1, pp. 75–80, Feb. 2012. https://doi.org/10.1590/S0103-90162012000100011.
6. [6] Y. Chung, J. Lee, S. Oh, D. Park, H. H. Chang, and S. Kim, “Automatic detection of cow’s oestrus in audio surveillance system,” Asian-Australasian J. Anim. Sci., vol. 26, no. 7, pp. 1030–1037, 2013. https://doi.org/10.5713/ajas.2012.12628.
7. [7] V. Röttgen et al., “Automatic recording of individual oestrus vocalisation in group-housed dairy cattle: Development of a cattle call monitor,” Animal, vol. 14, no. 1, pp. 198–205, 2020. https://doi.org/10.1017/S1751731119001733.
8. [8] G. Jahns, W. Kowalczyk, and K. Walter, “Sound Analysis to Recognize Different Animals,” IFAC Proc. Vol., vol. 30, no. 26, pp. 169–173, 1997. https://doi.org/10.1016/s1474-6670(17)41265-1.

9. [9] A. Urrutia, S. Martínez-Byer, P. Szenczi, R. Hudson, and O. Bánszegi, “Stable individual differences in vocalisation and motor activity during acute stress in the domestic cat,” Behav. Processes, vol. 165, pp. 58–65, Aug. 2019. https://doi.org/10.1016/j.beproc.2019.05.022.
10. [10] C. Y. Yeo, S. A. R. Al-Haddad, and C. K. Ng, “Dog voice identification (ID) for detection system,” 2012 2nd Int. Conf. Digit. Inf. Process. Commun. ICDIPC 2012, no. Id, pp. 120–123, 2012. https://doi.org/10.1109/ICDIPC.2012.6257264
11. [11] C. Y. Yeo, S. A. R. Al-Haddad, and C. K. Ng, “Animal voice recognition for identification (ID) detection system,” Proc. - 2011 IEEE 7th Int. Colloq. Signal Process. Its Appl. CSPA 2011, no. Id, pp. 198–201, 2011. https://doi.org/10.1109/CSPA.2011.5759872.
12. [12] A. Urrutia, S. Martínez-Byer, P. Szenczi, R. Hudson, and O. Bánszegi, “Stable individual differences in vocalisation and motor activity during acute stress in the domestic cat,” Behav. Processes, vol. 165, pp. 58–65, Aug. 2019. https://doi.org/10.1016/j.beproc.2019.05.022
13. [13] J. C. Bishop, G. Falzon, M. Trotter, P. Kwan, and P. D. Meek, “Sound Analysis and Detection, and the Potential for Precision Livestock Farming - A Sheep Vocalisation Case Study,” 1st Asian-Australiasian Conf. Precis. Pastures Livest. Farming, no. October, pp. 1–7, 2017.
14. [14] V. Röttgen et al., “Vocalization as an indicator of estrus climax in Holstein heifers during natural estrus and superovulation,” J. Dairy Sci., vol. 101, no. 3, pp. 2383–2394, 2018. https://doi.org/10.3168/jds.2017-13412.
15. [15] J. M. Watts and J. M. Stookey, “Vocal behaviour in cattle: the animal’s commentary on its biological processes and welfare,” Appl. Anim. Behav. Sci., vol. 67, no. 1–2, pp. 15–33, Mar. 2000. https://doi.org/10.1016/S0168-1591(99)00108-2
16. [16] C. Phillips, Ed., Cattle Behaviour & Welfare. Malden, MA, USA: Blackwell Science Ltd, 2002. https://doi.org/10.1002/9780470752418
17. [17] S. Göncü and S. Bozkurt, “Holstein cow vocalization behavior during oestrus periods,” MOJ Ecol. Environ. Sci., vol. 4, no. 6, pp. 276–279, 2019. https://doi.org/10.15406/mojes.2019.04.00165.
18. [18] P. C. Schön, K. Hämel, B. Puppe, A. Tuchscherer, W. Kanitz, and G. Manteuffel, “Altered vocalization rate during the estrous cycle in dairy cattle,” J. Dairy Sci., vol. 90, no. 1, pp. 202–206, 2007.https://doi.org/10.3168/jds.S0022-0302(07)72621-8.
19. [19] J. Lee, S. Zuo, Y. Chung, D. Park, H. H. Chang, and S. Kim, “Formant-based acoustic features for cow’s estrus detection in audio surveillance system,” 11th IEEE Int. Conf. Adv. Video Signal-Based Surveillance, AVSS 2014, pp. 236–240, 2014. https://doi.org/10.1109/AVSS.2014.6918674.
20. [20] N. Ding, X. Cheng, and Z. Cui, “Design of Ruminant Sound Detection for Dairy Cows Based on DWT-MFCC,” 2018 5th Int. Conf. Syst. Informatics, ICSAI 2018, no. Icsai, pp. 856–860, 2019. https://doi.org/10.1109/ICSAI.2018.8599308.
21. [21] D. H. Jung et al., “Deep learning-based cattle vocal classification model and real-time livestock monitoring system with noise filtering,” Animals, vol. 11, no. 2, pp. 1–16, 2021. https://doi.org/10.3390/ani11020357.
22. [22] M. P. Mcloughlin, R. Stewart, and A. G. McElligott, “Automated bioacoustics: methods in ecology and conservation and their potential for animal welfare monitoring,” J. R. Soc. Interface, vol. 16, no. 155, p. 20190225, Jun. 2019. https://doi.org/10.1098/rsif.2019.0225.
23. [23] V. Boddapati, A. Petef, J. Rasmusson, and L. Lundberg, “Classifying environmental sounds using image recognition networks,” Procedia Comput. Sci., vol. 112, pp. 2048–2056, 2017. https://doi.org/10.1016/j.procs.2017.08.250.
24. [24] “Amcrest Smart Player.” LLC, Amcrest Technologies, Houston; Tex, 2020.
25. [25] S. L. Hopp, M. J. Owren, and C. S. Evans, Animal acoustic communication: sound analysis and research methods. Springer Science & Business Media, 2012.
26. [26] J. L. Semmlow, Biosignal and medical image processing. CRC press, 2008.
27. [27] A. Subasi, Practical guide for biomedical signals analysis using machine learning techniques: A MATLAB based approach. Academic Press, 2019.
28. [28] “Audacity Audio Editing Software.” Audacity, 2020