Using segment-based features of jaw movements to recognise foraging activities in grazing cattle. (May 2023)

• Record Type: Journal Article
• Authors: Chelotti, José O.; Vanrell, Sebastián R.; Martinez-Rau, Luciano S.; Galli, Julio R.; Utsumi, Santiago A.; Planisich, Alejandra M.; Almirón, Suyai A.; Milone, Diego H.; Giovanini, Leonardo L.; Rufiner, H. Leonardo
• Is Part Of: Biosystems engineering. Volume 229(2023)
• Page Start: 69
• Page End: 84
• Publication Date: 2023-05
• Subjects: Acoustic monitoring -- Ruminant foraging behaviour -- Precision livestock farming -- Pattern recognition -- Feature engineering -- Machine learning; Bioengineering -- Periodicals; Agricultural engineering -- Periodicals; Biological systems -- Periodicals; Génie rural -- Périodiques; Systèmes biologiques -- Périodiques; 631
• DOI: 10.1016/j.biosystemseng.2023.03.014
• Languages: English
• ISSNs: 1537-5110

Abstract

Abstract : Precision livestock farming optimises livestock production through the use of sensor information and communication technologies to support decision making in real-time. Among available technologies to monitor foraging behaviour, the acoustic method has been highly reliable and repeatable, but there is a room for further computational improvements to increase precision and specificity of recognition of foraging activities. In this study, an algorithm called Jaw Movement segment-based Foraging Activity Recogniser (JMFAR) is proposed. The method is based on the computation and analysis of temporal, statistical and spectral features of jaw movement sounds for detection of rumination and grazing bouts. They are called JM-segment features because they are extracted from a sound segment and expect to capture JM information of the whole segment rather than individual JMs. Additionally, two variants of the method are proposed and tested: (i) one considering the temporal and statistical features only (JMFAR-ns); and (ii) another considering a feature selection process (JMFAR-sel). The JMFAR was tested on signals registered in a free grazing environment, achieving an average weighted F1-score of 93%. Then, it was compared with a state-of-the-art algorithm, showing improved performance for estimation of grazing bouts (+19%). The JMFAR-ns variant reduced the computational cost by 25.4%, but achieved a slightly lower performance than the JMFAR. The good performance and low computational cost of JMFAR-ns supports the feasibility of using this algorithm variant for real-time implementation in low-cost embedded systems. The method presented within this publication is protected by a pending patent application: AR P20220100910. Web demo available at: https://sinc.unl.edu.ar/web-demo/jmfar/ Highlights: An acoustic method to recognize foraging activities in grazing cattle is presented. A set of features independent of the identification of jaw-movements is proposed. Two variants of the base method are proposed. The algorithm improves grazing time estimation compared to previous acoustic methods. Its low computational cost allows real-time execution on low-cost embedded platforms.