Short-term feeding behaviour sound classification method for sheep using LSTM networks

Guanghui Duan, Shengfu Zhang, Mingzhou Lu, Cedric Okinda, Mingxia Shen, Tomas Norton

Abstract


A deep learning approach using long-short term memory (LSTM) networks was implemented in this study to classify the sound of short-term feeding behaviour of sheep, including biting, chewing, bolus regurgitation, and rumination chewing. The original acoustic signal was split into sound episodes using an endpoint detection method, where the thresholds of short-term energy and average zero-crossing rate were utilized. A discrete wavelet transform (DWT), Mel-frequency cepstral, and principal-component analysis (PCA) were integrated to extract the dimensionally reduced DWT based Mel-frequency cepstral coefficients (denoted by PW_MFCC) for each sound episode. Then, LSTM networks were employed to train classifiers for sound episode category classification. The performances of the LSTM classifiers with original Mel-frequency cepstral coefficients (MFCC), DWT based MFCC (denoted by W_MFCC), and PW_MFCC as the input feature coefficients were compared. Comparison results demonstrated that the introduction of DWT improved the classifier performance effectively, and PCA reduced the computational overhead without degrading classifier performance. The overall accuracy and comprehensive F1-score of the PW_MFCC based LSTM classifier were 94.97% and 97.41%, respectively. The classifier established in this study provided a foundation for an automatic identification system for sick sheep with abnormal feeding and rumination behaviour pattern.
Keywords: sheep behaviour, short-term feeding behaviour, acoustic analysis, Mel-frequency cepstral coefficients, long-short term memory networks
DOI: 10.25165/j.ijabe.20211402.6081

Citation: Duan G H, Zhang S F, Lu M Z, Okinda C, Shen M X, Norton T. Short-term feeding behaviour sound classification method for sheep using LSTM networks. Int J Agric & Biol Eng, 2021; 14(2): 43–54.

Keywords


sheep behaviour, short-term feeding behaviour, acoustic analysis, Mel-frequency cepstral coefficients, long-short term memory networks

Full Text:

PDF

References


Chelotti J O, Vanrell S R, Milone D H, Utsumi S A, Galli J R, Rufiner H L, et al. A real-time algorithm for acoustic monitoring of ingestive behavior of grazing cattle. Computers and Electronics in Agriculture, 2016; 127: 64–75.

Galli J R, Cangiano C A, Milone D H, Laca E A. Acoustic monitoring of short-term ingestive behavior and intake in grazing sheep. Livest. Sci., 2011; 140(1-3): 32–41.

Oudshoorn F W, Cornou C, Hellwing A L F, Hansen H H, Munksgaard L, Lund P, et al. Estimation of grass intake on pasture for dairy cows using tightly and loosely mounted di- and tri-axial accelerometers combined with bite count. Computers and Electronics in Agriculture, 2013; 99: 227–235.

Leiber F, Holinger M, Zehner N, Dorn K, Probst J K, Neff A S. Intake estimation in dairy cows fed roughage-based diets: An approach based on chewing behaviour measurements. Applied Animal Behaviour Science, 2016; 185: 9–14.

Galli J R, Cangiano C A, Pece M A, Larripa M J, Milone D H, Utsumi S A, et al. Monitoring and assessment of ingestive chewing sounds for prediction of herbage intake rate in grazing cattle. Animal, 2018; 12(5): 973–982.

Campos D P, Abatti P J, Hill A G, Paula A D. Short-term fibre intake estimation in goats using surface electromyography of the masseter muscle. Biosystems Engineering, 2019; 183: 209–220.

Rombach M, Sudekum K H, Munger A, Schori F. Herbage dry matter intake estimation of grazing dairy cows based on animal, behavioral, environmental, and feed variables. Journal of Dairy Science, 2019; 102(4): 2985–2999.

Milone D H, Rufiner H L, Galli J R, Laca E A, Cangiano C A. Computational method for segmentation and classification of ingestive sounds in sheep. Computer and Electronics in Agriculture, 2009; 65(2): 228–237.

Watanabe N, Sakanoue S, Kawamura K, Kozakai T. Development of an automatic classification system for eating, ruminating and resting behavior of cattle using an accelerometer. Grassl. Sci., 2008; 54(4): 231–237.

Buchel S, Sundrum A. Technical note: Evaluation of a new system for measuring feeding behavior of dairy cows. Computers and Electronics in Agriculture, 2014; 108: 12–16.

Sneddon J, Mason A. Automated monitoring of foraging behaviour in free ranging sheep grazing a bio-diverse pasture using audio and video information. In Proceedings of International Conference on Sensing Technology (ICST), Liverpool-UK, 2014; pp.170–173.

Laca E A, Wallisdevries M. Acoustic measurement of intake and grazing behaviour of cattle. Grass Forage Sci., 2000; 55(2): 97–104.

Milone D H, Galli J R, Cangiano C A, Rufiner H L, Laca E A. Automatic recognition of ingestive sounds of cattle based on hidden Markov models. Computers and Electronics in Agriculture, 2012; 87: 51–55.

Navon S, Mizrach A, Hetzroni A, Ungar E D. Automatic recognition of jaw movements in free-ranging cattle, goats and sheep, using acoustic monitoring. Biosystems Engineering, 2013; 114: 474–483.

Deniz N N, Chelotti J O, Galli J R, Planisich A M, Larripa M J, Rufiner H L, et al. Embedded system for real-time monitoring of foraging behavior of grazing cattle using acoustic signals. Computers and Electronics in Agriculture, 2017; 138: 167–174.

Bishop J, Falzon G, Trotter M, Kwan P, Meek P. Sound analysis and detection, and the potential for precision livestock farming - a sheep vocalization case study. In Proceedings of the 1st Asian-Australasian Conference on Precision Pastures and Livestock Farming, Hamilton-New Zealand, 2017; October 1–7.

Chelotti J O, Vanrell S R, Galli J R, Giovanini L L, Rufiner H L. A pattern recognition approach for detecting and classifying jaw movements in grazing cattle. Computers and Electronics in Agriculture, 2018; 145: 83–91.

Galli J R, Milone D H, Cangiano C A, Martínez C E, Laca E A, Chelotti J O, et al. Discriminative power of acoustic features for jaw movement classification in cattle and sheep. Bioacoustics, 2019; 29(5): 1–15.

Hsu W N, Zhang Y, Glass J. A prioritized grid long short-term memory RNN for speech recognition. Proceedings of IEEE Spoken Language Technology Workshop (SLT), San Diego, CA, USA, 2016; pp.467–473.

Qu Z, Haghani P, Weinstein E, Moreno P. Syllable-based acoustic modeling with CTC-SMBR-LSTM. In Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, Piscataway-NJ, 2017; pp.173–177.

Palangi H, Deng L, Shen Y, Gao J, He X, Chen J, et al. Deep sentence embedding using long short-term memory networks: Analysis and application to information retrieval. IEEE/ACM Trans. Audio Speech Lang. Process, 2016; 24: 694–707.

Mallinar N, Rosset C. Deep canonically correlated LSTMs. arXiv:1801.05407, 2018.

Audacity 2.1.2, 2016. Available: https://www.audacityteam.org/.

Ephraim Y, Malah D. Speech enhancement using a minimum mean-square error log-spectral amplitude estimator. IEEE Transactions on Acoustics Speech & Signal Processing, 1985; 33(2): 443–445.

Sheng H, Zhang S F, Zuo L S, Duan G H, Zhang H L, Okinda C, et al. Construction of sheep forage intake estimation models based on sound analysis. Biosystems Engineering, 2020; 192: 144–158.

Davis S, Mermelstein P. Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions on Acoustics, Speech and Signal Processing, 1980; 28: 357–366.

Ganchev T, Fakotakis N, Kokkinakis G. Comparative evaluation of various MFCC implementations on the speaker verification task. In Proceedings of the 10th International Conference on Speech and Computer (SPECOM 2005), Patras-Greece, 2005; 1: 191–194.

Tang C P, Chui K L, Yu Y K, Zeng Z L, Wong K H. Music genre classification using a hierarchical long short term memory (LSTM) model. International Workshop on Pattern Recognition IWPR 2018, Jinan-China, 2018; pp.26–28.

Li M, Chen N. A robust cover song identification system with two-level similarity fusion and post-processing. Applied Sciences, 2018; 8(8): 3383.

Srivastava S, Bhardwaj S, Bhandari A, Gupta K, Bahl H, Gupta J R P. Wavelet packet based mel frequency cepstral features for text independent speaker identification. In: Abraham A, Thampi S (Ed.). Intelligent Informatics. Berlin: Springer, 2013; 182: 237–247.

Patil J M, Desai P K. Word-based LID using HMM and bi-gram modeling. In: Chakravarthi V, Shirur Y, Prasad R (Ed.). Proceedings of International Conference on VLSI, Communication, Advanced Devices, Signals & Systems and Networking (VCASAN-2013). India: Springer, 2013; 258: 373–383.

Jain S, Gupta D. Feature extraction techniques based on human auditory system. In: Bhalla S, Bhateja V, Chandavale A, Hiwale A, Satapathy S (Ed.). Intelligent Computing and Information and Communication. Singapore: Springer, 2018; 673: 667–676.

Sigurdsson S, Petersen K B, Schiler T L. Mel frequency cepstral coefficients: An evaluation of robustness of mp3 encoded music. Conference Proceedings of the Seventh International Conference on Music Information Retrieval (ISMIR), Vicoria-Canada, 2006; pp.286–289.

Chelali F Z, Djeradi A. Text dependant speaker recognition using MFCC, LPC and DWT. International Journal of Speech Technology, 2017; 20(3): 725–740.

Panakkat A, Adeli H. Recurrent neural network for approximate earthquake time and location prediction using multiple seismicity indicators. Comput. Civ. Infrastruct. Eng., 2009; 24(4): 280–292.

Hochreiter S. Long short-term memory. Neural Computation, 1997; 9(8): 1735–1780.

Kingma D P, Adam J B. A method for stochastic optimization. In: Proceedings of the 3rd International Conference for Learning Representations. San Diego: Springer Verlag, 2015; pp.1–15.

Alvarenga F A P, Borges I, Palkovic L, Rodina J, Oddy V H, Dobos R C. Using a three-axis accelerometer to identify and classify sheep behaviour at pasture. Appl. Anim. Behav. Sci., 2016; 181: 91–99.

Vanrell S R, Chelotti J O, Galli J R, Utsumi S A, Giovanini L L, Rufiner H L, et al. A regularity-based algorithm for identifying grazing and rumination bouts from acoustic signals in grazing cattle. Computers and Electronics in Agriculture, 2018; 151: 392–402.

Giovanetti V, Decandia M, Molle G, Acciara M, Mameli M, Cabiddu A, et al. Automatic classification system for grazing, ruminating and resting behaviour of dairy sheep using a tri-axial accelerometer. Livestock Science, 2017; 196: 42–48.

Decandia M, Giovanetti V, Molle G, Acciara M, Mameli M, Cabiddu A, et al. The effect of different time epoch settings on the classification of sheep behaviour using tri-axial accelerometry. Computers and Electronics in Agriculture, 2018; 154: 112–119.

Zehner N, Umstätter C, Niederhauser J J, Schick M. System specification and validation of a noseband pressure sensor for measurement of ruminating and eating behavior in stable-fed cows. Computers and Electronics in Agriculture, 2017; 136: 31–41.

Herskin M S, Munksgaard L, Ladewig J. Effects of acute stressors on nociception, adrenocortical responses and behavior of dairy cows. Physiol. Behav., 2004; 83(3): 411–420.

Bristow D J, Holmes D S. Cortisol levels and anxietyrelated behaviors in cattle. Physiology & Behavior, 2007; 90: 626–628.

Welch J G. Rumination, particle size and passage from the rumen. Journal of animal science, 1982; 54(4): 885–894.

Beauchemin K A, Farr B I, Rode L M. Enhancement of the effective fiber content of barley-based concentrates fed to dairy cows. Journal of Dairy Science, 1991; 74(9): 3128–3139.




Copyright (c) 2021 International Journal of Agricultural and Biological Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

2023-2026 Copyright IJABE Editing and Publishing Office