14 May 2023 in Agroforestry Systems
2 March 2020 in IEEE Sensors Journal
Monitoring the ingestive behavior, especially rumination and eating, is important to assess animals’ health, welfare, needs, and to estimate production efficiency. In this paper, the myographic response of masticatory muscles was acquired from cows to directly access ingestive information (grazing and ruminating patterns) with high accuracy and time precision. Myographic signal processing is usually based on the same framework and optimal feature combinations have been extensively researched. However, recognition rates of hand-crafted feature based classifiers may be sensible to data deviation. In order to avoid the aforementioned issues and improve robustness, we propose an approach using sparse representation based classifiers which dismiss the need to select the best feature combination and classifier for the application. Also, we present a novel segmentation protocol to select chew related signal windows on cows. Four state-of-the-art multi-feature sets combined with linear discriminant analysis (LDA) were compared to a sparse representation based classifier called Fisher Discriminant Dictionary Learning (FDDL). Results suggest a significantly better performance of FDDL (p<0.05), achieving an accuracy rate of 90%, even in the presence of noise (0 - 20 dB), having a performance gain of 2.45% (SNR of 0 dB) in relation to the best hand-crafted feature set. When the noise was added just to the test set, all others classifiers remained under 75% (near 50%) for severe noise (0 - 10 dB), while FDDL stayed over 85%.
9 July 2024 in IEEE Sensors Letters
Precision livestock farming (PLF) has motivated the development of sensor technology to monitor animal health and productivity. Feed intake and rumination time are crucial parameters, with surface Electromyography (sEMG) showing promise for differentiating between eating and ruminating chews. This letter investigates if features extracted from fixed-window sEMG segments improve classification accuracy compared to variable-length windows based on chew onset and offset. Data were collected from two Jersey cows using sEMG electrodes placed on the masseter muscle. Eating and rumination activities were visually labeled. The sEMG signal was segmented using a double threshold onset segmentation (DTOS) method based on the onset of muscle activity. Features were extracted from both fixed and variable-length windows defined by the DTOS segmentation. A linear discriminant analysis classifier was used to differentiate between eating and rumination chews. Results showed that features extracted from fixed-window segments achieved a significantly higher classification accuracy (87.85%) compared to variable-length windows. This approach simplifies feature extraction and potentially improves real-time classification for ingestive behavior monitoring in PLF systems.
14 April 2024 in The Journal of Engineering and Exact Sciences
Livestock farming is responsible for producing much of the animal protein that humans consume. Estimates of significant growth in the world population over the years highlight a demand not only for the expansion of animal production but also for an increase in livestock efficiency. To achieve this, one of the essential factors is improving the nutrition process, with the analysis of the ingestive behavior of ruminants being essential. Therefore, this work presents the development of a system for acquiring, storing, and transmitting signals from a pressure sensor for monitoring and evaluating masticatory movements in ruminants. This system employs a pressure sensor to obtain signals relating to chewing movement. A microcontroller acquires these signals at a sampling frequency of 100 Hz, and the resulting data are transmitted to a smartphone via Bluetooth and stored in a memory card for later analysis. Preliminary bench tests were carried out with the system installed on a full-size prototyped bovine head. Compression movements were applied to a silicone tube, causing pressure variations in the sensor. By transmitting the data to a smartphone via Bluetooth, it was possible to check the signal, adjust the gain of the instrumentation amplifier, and achieve the best positioning of the silicone tube in the mouthpiece. By reading the data recorded on a memory card, it was possible to obtain the signal profile, graphically demonstrating that the signal corresponds to the typical profile for this type of sensor.
17 November 2020 in Revista Brasileira de Zootecnia
The objective of this study was to investigate the effects of slaughter body weight (SW) on the performance, carcass characteristics, and meat quality of Jersey bulls in feedlots from weaning to slaughter. Eighteen Jersey bulls (125.7±15.9 kg; 5±0.6 months old) were used in the study. The treatments corresponded to three slaughter-weights: L360 – light weight, SW of 360 kg, M390 – medium weight, SW of 390 kg, and H420 – heavy weight, SW of 420 kg (n = 6/treatment); [...] ABSTRACT The objective of this study was to investigate the effects of slaughter body weight (SW) on the performance, carcass characteristics, and meat quality of Jersey bulls in feedlots from weaning to slaughter. Eighteen Jersey bulls (125.7±15.9 kg; 5±0.6 months old) were used in the study. The treatments corresponded to three slaughter-weights: L360 – light weight, SW of 360 kg, M390 – medium weight, SW of 390 kg, and H420 – heavy weight, SW of 420 kg (n = 6/treatment);
1 January 2019 in Ciência Animal Brasileira
Resumo O objetivo deste estudo foi descrever a estrutura do dossel e o comportamento ingestivo de caprinos em pastos de papuã manejados sob lotação contínua. Os tratamentos corresponderam a quatro alturas de manejo (10, 20, 30 e 40 cm) mantidas através de taxa de lotação variável. As variáveis analisadas foram: composição morfológica, massa e densidade dos componentes; comprimento de lâminas foliares; valor nutritivo por simulação de pastejo; tempos de pastejo, ruminação e atividades complementares. Os dados foram submetidos à análise de variância e teste de contrastes de polinômios ortogonais. Os principais resultados foram: i) com o aumento da altura de manejo, houve um aumento da massa (total e dos componentes morfológicos) e uma inversão na composição morfológica (redução na proporção de lâminas foliares e aumento na de colmos + material morto); ii) o comprimento de lâminas foliares aumentou com a altura de manejo; iii) os animais dedicaram mais tempo ao pastejo com a redução da altura de manejo, embora aparentemente tenham abdicado do pastejo no tratamento 10 cm ao final do experimento. Baseado nos dados de estrutura do dossel e comportamento ingestivo, concluiu-se que pastos de papuã sob lotação contínua devem ser manejados próximos de 40 cm. As razões são discutidas ao longo do artigo.