Sound Signals Processing of Roosters for Sexual Maturity and Puberty Diagnosis

Document Type : Research Article

Authors

• M. Yavari ¹
• A. Banakar ¹
• M. Sharafi ²

¹ Department of Biosystems Engineering, Tarbiat Modares University, Tehran, Iran

² Department of Poultry Science, Faculty of Agriculture, Tarbiat Modares University, Tehran, Iran

https://doi.org/10.22067/jam.v10i2.75264

Abstract

Introduction
Immature birds, like humans and many animals, pass through the puberty period to sexual maturity that is accompanied by sound changes and after the sexual maturity, the sound structure evolves. The puberty period is one of the most important periods in the breeder chicken farms. Because the feeding of roosters at this age can delay or accelerate the time of sexual maturity. On the other hand, the diagnosis of mature roosters to mating with chickens increases egg production in early adulthood. Sexual maturity is a summary of the morphological and physiological changes its peak in the roosters from the age of 16 to 24 weeks. In female birds, the beginning of the first laying is considered to be sexual maturity, while the exact timing of sexual maturity in a male bird cannot be determined. The puberty term means the age at which reproduction is possible for the first time, but reproductive processes have not yet evolved. Therefore, the chance of pregnancy at this age is very low and fertility will not be optimal. Puberty can be likened to teenage years in humans. Bird sounds are generated mainly by the syrinx and humans speak with the stimulation of the vocal cords. The sound produced by the bird is similar to how human speech is produced. Therefore, techniques used to recognize human speech are also likely to be useful for classifying bird sounds.
Material and Methods
Variation in an animal’s vocalizations can provide clues about how the animal uses sound, as well as qualities of the individual that is vocalizing. Bioacoustics research depends heavily on the ability to characterize these variations. The main goal of this study is to diagnosis puberty and the sexual maturity in bred roosters based on sound signals. To do this, the number of roosters with the first ejaculation for puberty and sperm concentration criterion for sexual maturity was divided into three groups of immature males, roosters during the puberty period and adult roosters and the rooster's acoustic signals were recorded by a microphone in a double-sided glass box (50x50x60 cm). The main purpose of using the box is to prevent the effects of noise in the environment on acoustic signals because otherwise, the sound signal of the rooster is unreliable due to the characteristics of the normal sound. Linear predictive coding (LPC) coefficients from the frequency domain were extracted as sound features. The sound features were used to classify k- nearest neighbors (K-NN) inputs for network training.
Results and Discussion
The results of accuracy, recall and precision values are, respectively, 97.7%, 98.3%, and 98.8% for the classification of roosters. Immature roosters had similar sound structures that with start the puberty and Leakage testosterone hormone, the rooster's syrinx, which is part of the secondary sexual feature, also begins to change. After sexual maturity, the syrinx has grown and this evolution also makes the sound structure of the mature rooster very similar. Therefore, according to the similarity of the sound of the mature rooster and immature one, as well as the syrinx continuous changes during the puberty period, the K-NN classifier with the LPC coefficients can show a high degree of accuracy in the classification of roosters. Because a feature of the k-NN algorithm is that it is sensitive to the data local structure.
Conclusion
The main objective of the present study is to detect sexual and puberty of roosters using acoustic signals. The LPC coefficients as K-NN classification inputs show accuracy, recall, and precision values of 98.7%, 98.3%, and 98.8%, respectively. These results indicate high accuracy of K-NN classification to identify and categorize immature roosters, rooster during puberty period, and mature roosters.

Keywords

• Bio-Acoustic signal Processing
• Rooster
• Puberty
• Linear predictive coding (LPC)
• k- nearest neighbors (K-NN)

20.1001.1.22286829.1399.10.2.12.0

Open Access

©2020 The author(s). This article is licensed under Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source.

References

1. Adi, K., M. T. Johnson, and T. S. Osiejuk. 2010. Acoustic censusing using automatic vocalization classification and identity recognition. The Journal of the Acoustical Society of America 127 (2): 874-883.

2. Banakar, A., M. Sadeghi, and A. Shushtari. 2016. An intelligent device for diagnosing avian diseases: Newcastle, infectious bronchitis, avian influenza. Computers and Electronics in Agriculture 127: 744-753.

3. Beani, L., G. Panzica, F. Briganti, P. Persichella, and F. Dessì-Fulgheri. 1995. Testosterone-induced changes of call structure, midbrain and syrinx anatomy in partridges. Physiology & Behavior 58 (6): 1149-1157.

4. Beani, L., F. Briganti, G. Campanella, C. Lupo, and F. Dessi-Fulgheri. 2000. Effect of androgens on structure and rate of crowing in the Japanese quail (Coturnix japonica). Behaviour 137 (4): 417-435.

5. Brackenbury, J. 1978. Respiratory mechanics of sound production in chickens and geese. Journal of Experimental Biology 72: 229-250.

6. Dawson, M. R., I. Charrier, and C. B. Sturdy. 2006. Using an artificial neural network to classify black-capped chickadee (Poecile atricapillus) call note types. The Journal of the Acoustical Society of America 119 (5): 3161-3172.

7. Han, N. C., S. V. Muniandy, and J. Dayou. 2011. Acoustic classification of Australian anurans based on hybrid spectral-entropy approach. 72 (9): 639-645.

8. Huang, C.J., Y.J. Yang, D.X. Yang, and Y. J. Chen. 2009. Frog classification using machine learning techniques. 36 (2): 3737-3743.

9. Jaafar, H., D. A. Ramli, and S. Shahrudin. 2013. MFCC based frog identification system in noisy environment. IEEE International conference on Signal and image processing applications (ICSIPA).

10. Juang, C.-F. and T.-M. Chen. 2007. Birdsong recognition using prediction-based recurrent neural fuzzy networks. Neurocomputing 71: 121-130.

11. Khoshnam, F., S. H. B. Bidgoly, M. Namjoo, and M. Doroozi. 2017. The effect of acoustic system variables on sound signals of Melon varieties. 7 (1): 126-139.

12. Lake, P. 1957. The male reproductive tract of the fowl. Journal of Anatomy 91 (1): 116.

13. Laron, Z., J. Arad, R. Gurewitz, M. Grunebaum, and Z. Dickerman. 1980. Age at first conscious ejaculation: a milestone in male puberty. Helvetica Paediatrica Acta 35: 13-20.

14. Lee, C. H., Y. K. Lee, and R. Z. Huang. 2006. Automatic recognition of bird songs using cepstral coefficients. Journal of Information Technology and Applications 1 (1): 17-23.

15. Lee, J., L. Jin, D. Park, Y. Chung, and H. H. Chang. 2015. Acoustic features for pig wasting disease detection. International Journal of Information Processing and Management 6 (1): 37.

16. Mitrovic, D., M. Zeppelzauer, and C. Breiteneder. 2006. Discrimination and retrieval of animal sounds. 12th International Multi-Media Modelling Conference .

17. National Research Council. 1984. Nutrient requirements of poultry. National Academies.

18. Okanoya, K., and T. Kimura. 1993. Acoustical and perceptual structures of sexually dimorphic distance calls in Bengalese finches (Lonchura striata domestica). Journal of Comparative Psychology 107 (4): 386.

19. Peterson, M. R., T. E. Doom, and M. L. Raymer. 2005. Ga-facilitated knn classifier optimization with varying similarity measures. IEEE Congress on Evolutionary Computation.

20. Rabiner, L. R., and B.-H. Juang. 1993. Fundamentals of speech recognition. PTR Prentice Hall Englewood Cliffs.

21. Sadeghi, M., A. Banakar, and A. J. C. Shushtari. 2017. Diagnosing avian Newcastle, Bronchitis and Influenza Diseases using heart sound signal and Support Vector Machine. Iranian Journal of Biosystems Engineering. 47: 587-601.

22. Sokolova, M., and G. Lapalme. 2009. A systematic analysis of performance measures for classification tasks. Information Processing & Management 45 (4): 427-437.

23. Sturkie, P. D. 2012. Avian physiology. Springer Science & Business Media.

24. Tremain, T. E. 1982. The Government Standard Linear Predictive Coding Algorithm: LPC-10. Speech Technology 40-49.

25. Vandermeulen, J., C. Bahr, D. Johnston, B. Earley, E. Tullo, I. Fontana, M. Guarino, V. Exadaktylos, and D. Berckmans. 2016. Early recognition of bovine respiratory disease in calves using automated continuous monitoring of cough sounds. Computers and Electronics in Agriculture 129: 15-26.

26. Yoneda, T., and K. Okanoya. 1991. Ontogeny of sexually dimorphic distance calls in Bengalese finches (Lonchura domestica). Journal of Ethology 9 (2): 41-46.

27. Zamani, M., M. Aboonajmi, and S. R. Hassan-Beygi. 2016. Design, development and test of the gearbox condition monitoring system using sound signal processing. Journal of Agricultural Machinery 6 (2): 322-335.