STRESS DETECTION IN BROILER CHICKENS THROUGH SOUND ANALYSIS
DOI:
https://doi.org/10.24867/06BE36MaljkovicKeywords:
broiler chickens, stress detection, sound analysis, SVMAbstract
This paper presents a system for stress detection in broiler chickens through analysis of their sounds. The feature set used in the system is composed of energy, power, root mean square, jitter, shimmer, average pitch, harmonic-noise ratio, outputs of mel filter bank and mel-frequency cepstral coefficients. Support vector machine is used as a classifier. System accuracy on the 50 ms long frame level varies from 61 to 88 %, depending on how old broilers are and selected features.
References
[1] D. Berckmans, “Automatic on-line monitoring of animals by precision livestock farming”, International Society for Animal Hygiene, Saint Malo, 2004.
[2] D. Berckmans et al., “Animal Sound… Talks! Real-time Sound Analysis for Health Monitoring in Livestock”, International Symposium on Animal Environment and Welfare, Chongqing, China, October 2015.
[3] M. Rizwan et al., "Identifying rale sounds in chickens using audio signals for early disease detection in poultry", 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Washington, DC, pp. 55-59, December 2016.
[4] J. Lee et al., “Stress Detection and Classification of Laying Hens by Sound Analysis”, Asian-Australasian Journal of Animal Sciences, Vol. 28, No. 4, pp. 592-598, April 2015.
[5] https://respeaker.io/4_mic_array/ (pristupljeno u septembru 2019.)
[6] I. Fontana et al., “Sound analysis to model weight of broiler chickens”, Poultry Science, September 2017.
[7] F. Eyben, “Real-time Speech and Music Classification by Large Audio Feature Space Extraction”, Springer Theses, DOI 10.1007/978-3-319-27299-3.
[8] M. Lin, S. Zhong, L. Lin, “Chicken Sound Recognition using Anti-noise Mel Frequency Cepstral Coefficients”, 2015 Third International Conference on Robot, Vision and Signal Processing, Kaohsiung, Taiwan, pp. 224-227, November 2015.
[9] J. Cai et al., “Sensor Network for the Monitoring of Ecosystem: Bird Species Recognition”, ISSNIP 2007 3rd International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Melbourne, Australia, pp. 293-298, December 2007.
[10] F. Briggs, X. Fern, R. Raich, “Technical Report (Not Peer Reviewed): Acoustic Classification of Bird Species from Syllables: an Empirical Study”, 2011.
[11] V. Delić, PPT prezentacije i materijali sa predavanja za predmet Govorne tehnologije, Potral katedre za telekomunikacije i obradu signala (www.ktios.net), Fakultet tehničkih nauka, Univerzitet u Novom Sadu, 2018.
[12] M. Sečujski, PPT prezentacije i materijali sa predavanja za predmet Prepoznavanje oblika, Potral katedre za telekomunikacije i obradu signala (www.ktios.net), Fakultet tehničkih nauka, Univerzitet u Novom Sadu, 2017.
[13] B. McFee et al., “librosa: Audio and Music Signal Analysis in Python”, 14th Python in Science Conference (SciPy 2015), Austin, Texas, pp. 18-24, July 2015.
[14] F. Pedregosa et al., “Scikit-learn: Machine Learning in Python”, Journal of Machine Learning Research, Vol. 12, pp. 2825-2830, October 2011.
[2] D. Berckmans et al., “Animal Sound… Talks! Real-time Sound Analysis for Health Monitoring in Livestock”, International Symposium on Animal Environment and Welfare, Chongqing, China, October 2015.
[3] M. Rizwan et al., "Identifying rale sounds in chickens using audio signals for early disease detection in poultry", 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Washington, DC, pp. 55-59, December 2016.
[4] J. Lee et al., “Stress Detection and Classification of Laying Hens by Sound Analysis”, Asian-Australasian Journal of Animal Sciences, Vol. 28, No. 4, pp. 592-598, April 2015.
[5] https://respeaker.io/4_mic_array/ (pristupljeno u septembru 2019.)
[6] I. Fontana et al., “Sound analysis to model weight of broiler chickens”, Poultry Science, September 2017.
[7] F. Eyben, “Real-time Speech and Music Classification by Large Audio Feature Space Extraction”, Springer Theses, DOI 10.1007/978-3-319-27299-3.
[8] M. Lin, S. Zhong, L. Lin, “Chicken Sound Recognition using Anti-noise Mel Frequency Cepstral Coefficients”, 2015 Third International Conference on Robot, Vision and Signal Processing, Kaohsiung, Taiwan, pp. 224-227, November 2015.
[9] J. Cai et al., “Sensor Network for the Monitoring of Ecosystem: Bird Species Recognition”, ISSNIP 2007 3rd International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Melbourne, Australia, pp. 293-298, December 2007.
[10] F. Briggs, X. Fern, R. Raich, “Technical Report (Not Peer Reviewed): Acoustic Classification of Bird Species from Syllables: an Empirical Study”, 2011.
[11] V. Delić, PPT prezentacije i materijali sa predavanja za predmet Govorne tehnologije, Potral katedre za telekomunikacije i obradu signala (www.ktios.net), Fakultet tehničkih nauka, Univerzitet u Novom Sadu, 2018.
[12] M. Sečujski, PPT prezentacije i materijali sa predavanja za predmet Prepoznavanje oblika, Potral katedre za telekomunikacije i obradu signala (www.ktios.net), Fakultet tehničkih nauka, Univerzitet u Novom Sadu, 2017.
[13] B. McFee et al., “librosa: Audio and Music Signal Analysis in Python”, 14th Python in Science Conference (SciPy 2015), Austin, Texas, pp. 18-24, July 2015.
[14] F. Pedregosa et al., “Scikit-learn: Machine Learning in Python”, Journal of Machine Learning Research, Vol. 12, pp. 2825-2830, October 2011.
Downloads
Published
2019-12-30
Issue
Section
Electrotechnical and Computer Engineering
