Automatic cattle activity recognition on grazing systems Ramirez Agudelo, John Fredy; Bedoya Mazo, Sebastian; Posada Ochoa, Sandra Lucia ...
Biotecnologia en el sector agropecuario y agroindustrial,
07/2022, Letnik:
20, Številka:
2
Journal Article
Recenzirano
Odprti dostop
The use of collars, pedometers or activity tags is expensive to record cattle's behavior in short periods (e.g. 24h). Under this particular situation, the development of low-cost and easy-to-use ...technologies is relevant. Similar to smartphone apps for human activity recognition, which analyzes data from embedded triaxial accelerometer sensors, we develop an Android app to record activity in cattle. Four main steps were followed: a) data acquisition for model training, b) model training, c) app deploy, and d) app utilization. For data acquisition, we developed a system in which three components were used: two smartphones and a Google Firebase account for data storage. For model training, the generated database was used to train a recurrent neural network. The performance of training was assessed by the confusion matrix. For all actual activities, the trained model provided a high prediction (> 96 %). The trained model was used to deploy an Android app by using the TensorFlow API. Finally, three cell phones (LG gm730) were used to test the app and record the activity of six Holstein cows (3 lactating and 3 non-lactating). Direct and non-systematic observations of the animals were made to contrast the activities recorded by the device. Our results show consistency between the direct observations and the activity recorded by our Android app.
Background: Animal growth modeling is a tool that enables the acquisition of parameters to evaluate animal performance and predict outcomes for decision-making. Objective: To describe the growth of ...male guinea pigs of the Peruvian breed using the non-linear Brody, Gompertz, Logistic, and Von Bertalanffy models. Methodology: Twelve male guinea pigs with an initial weight of 393 ± 55 g were housed in metabolic cages with ad libitum feeding of a complete pellet diet. They were weighed every seven days for 13 weeks until reaching 1197 ± 84 g. Criteria used to assess the model's fitting ability included the Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), coefficient of determination (R2), concordance correlation coefficient (CCC), and mean squared prediction error (CMEP). Results: The Logistic model consistently predicted maturity weight (1421g), initial weight (187g), age (65 days), and weight (711g) at the growth curve inflection point. Gompertz and Von Bertalanffy's models tended to overestimate adult weight (A) and exhibited the lowest maturity index (k). Among Gompertz, Logistic, and Von Bertalanffy models, AIC, BIC, R2, CCC, and CMEP fitting criteria showed no significant differences (p > 0.05). Implications: The Brody model was the only one with biologically inconsistent parameters. Conclusion: Considering the biological significance of parameters and residual analysis, the Logistic model is more suitable for describing the growth curve of male guinea pigs of the Peruvian breed.
Background: Animal growth modeling is a tool that enables the acquisition of parameters to evaluate animal performance and predict outcomes for decision-making. Objective: To describe the growth of ...male guinea pigs of the Peruvian breed using the non-linear Brody, Gompertz, Logistic, and Von Bertalanffy models. Methodology: Twelve male guinea pigs with an initial weight of 393 ± 55 g were housed in metabolic cages with ad libitum feeding of a complete pellet diet. They were weighed every seven days for 13 weeks until reaching 1197 ± 84 g. Criteria used to assess the model's fitting ability included the Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), coefficient of determination (R2), concordance correlation coefficient (CCC), and mean squared prediction error (CMEP). Results: The Logistic model consistently predicted maturity weight (1421g), initial weight (187g), age (65 days), and weight (711g) at the growth curve inflection point. Gompertz and Von Bertalanffy's models tended to overestimate adult weight (A) and exhibited the lowest maturity index (k). Among Gompertz, Logistic, and Von Bertalanffy models, AIC, BIC, R2, CCC, and CMEP fitting criteria showed no significant differences (p > 0.05). Implications: The Brody model was the only one with biologically inconsistent parameters. Conclusion: Considering the biological significance of parameters and residual analysis, the Logistic model is more suitable for describing the growth curve of male guinea pigs of the Peruvian breed.
Successful mitigation efforts entail accurate estimation of on-farm emission and prediction models can be an alternative to current laborious and costly in vivo CH4 measurement techniques. This study ...aimed to: (1) collate a database of individual dairy cattle CH4 emission data from studies conducted in the Latin America and Caribbean (LAC) region; (2) identify key variables for predicting CH4 production (g d−1) and yield g kg−1 of dry matter intake (DMI); (3) develop and cross-validate these newly-developed models; and (4) compare models' predictive ability with equations currently used to support national greenhouse gas (GHG) inventories. A total of 42 studies including 1327 individual dairy cattle records were collated. After removing outliers, the final database retained 34 studies and 610 animal records. Production and yield of CH4 were predicted by fitting mixed-effects models with a random effect of study. Evaluation of developed models and fourteen extant equations was assessed on all-data, confined, and grazing cows subsets. Feed intake was the most important predictor of CH4 production. Our best-developed CH4 production models outperformed Tier 2 equations from the Intergovernmental Panel on Climate Change (IPCC) in the all-data and grazing subsets, whereas they had similar performance for confined animals. Developed CH4 production models that include milk yield can be accurate and useful when feed intake is missing. Some extant equations had similar predictive performance to our best-developed models and can be an option for predicting CH4 production from LAC dairy cows. Extant equations were not accurate in predicting CH4 yield. The use of the newly-developed models rather than extant equations based on energy conversion factors, as applied by the IPCC, can substantially improve the accuracy of GHG inventories in LAC countries.
Display omitted
•Dry matter intake (DMI) was the most important predictor of dairy CH4 production.•Simple regression models including DMI were accurate for predicting CH4 production.•CH4 production can also be predicted using milk yield when DMI is missing.•Developed models outperformed IPCC Tier 2 equations.•These newly-developed models can improve the accuracy GHG inventories from LAC countries.
Abstract
The objective of this meta-analysis was to develop and evaluate models for predicting nitrogen (N) excretion in feces, urine, and manure in beef cattle in South America. The study ...incorporated a total of 1,116 individual observations of N excretion in feces and 939 individual observations of N excretion in feces and in urine (g/d), representing a diverse range of diets, animal genotypes, and management conditions in South America. The dataset also included data on dry matter intake (DMI; kg/d) and nitrogen intake (NI; g/d), concentrations of dietary components, as well as average daily gain (ADG; g/d) and average body weight (BW; kg). Models were derived using linear mixed-effects regression with a random intercept for the study. Fecal N excretion was positively associated with DMI, NI, nonfibrous carbohydrates, average BW, and ADG and negatively associated with EE and CP concentration in the diet. The univariate model predicting fecal N excretion based on DMI (model 1) performed slightly better than the univariate model, which used NI as a predictor variable (model 2) with a root mean square error (RMSE) of 38.0 vs. 39.2%, the RMSE-observations SD ratio (RSR) of 0.81 vs. 0.84, and concordance correlation coefficient (CCC) of 0.53 vs. 0.50, respectively. Models predicting urinary N excretion were less accurate than those derived to predict fecal N excretion, with an average RMSE of 43.7% vs. 37.0%, respectively. Urinary and manure N excretion were positively associated with DMI, NI, CP, average BW, and ADG and negatively associated with neutral detergent fiber concentration in the diet. As opposed to fecal N excretion, the univariate model predicting urinary N excretion using NI (model 10) performed slightly better than the univariate model using DMI (model 9) as predictor variable with an RMSE of 36.0% vs. 39.7%, RSR 0.85 vs. 0.93, and CCC of 0.43 vs. 0.29, respectively. The models developed in this study are applicable for predicting N excretion in beef cattle across a broad spectrum of dietary compositions and animal genotypes in South America. The univariate model using DMI as a predictor is recommended for fecal N prediction, while the univariate model using NI is recommended for predicting urinary and manure N excretion because the use of more complex models resulted in little to no benefits. However, it may be more useful to consider more complex models that incorporate nutrient intakes and diet composition for decision-making when N excretion is a factor to be considered. Three extant equations evaluated in this study have the potential to be used in tropical conditions typical of South America to predict fecal N excretion with good precision and accuracy. However, none of the extant equations are recommended for predicting urine or manure N excretion because of their high RMSE, and low precision and accuracy.
The models developed in this study to predict N excretion in beef cattle can help to improve the environmental and economic sustainability of beef production systems in South America.
Lay Summary
Reductions in nitrogen (N) excretion in beef cattle not only yield environmental advantages but also confer economic benefits associated with reduced purchase of protein feed ingredients. As measuring N excretion under farm conditions is not feasible, models that can accurately predict N excretion using variables that are more easily obtained in beef production systems are needed. A meta-regression analysis was conducted to develop models that can predict N excretion in feces, urine, and manure in beef cattle in South America. The univariate model using dry matter intake as a predictor is recommended for fecal N prediction, while the univariate model using N intake is recommended for predicting urine and manure N excretion because the use of more complex models resulted in little to no benefits. However, more complex models that incorporate nutrient intakes and diet composition might be more useful for decision-making when N excretion is a factor to be considered. Such models enable simulations of N excretion with modifications to diet composition with similar accuracy. The models developed in this study are applicable for predicting N excretion in beef cattle across a broad spectrum of dietary compositions and animal genotypes in South America.
Con el fin de evaluar la respuesta productiva y microeconómica del maní forrajero (Arachis pintoi) como reemplazo parcial de la proteína cruda en cerdos en las etapas de levante y ceba, se realizó ...una investigación con 12 hembras, divididas al azar en cuatro tratamientos: T1. Grupo testigo, alimentado con concentrado comercial; T2, T3 y T4, con 10, 20 y 30%, respectivamente, de reemplazo de la proteína de la dieta a partir de maní. Las variables evaluadas fueron consumo de alimento, peso corporal, ganancia diaria de peso, grasa dorsal, conversión alimenticia y la relación valor del alimento/valor de la ganancia de peso. No se encontró diferencia estadística significativa entre los diferentes tratamientos para todas las variables evaluadas, excepto para el promedio de la ganancia diaria de peso durante la etapa de levante (p < 0.01), la cual reportó los mayores valores para el T1 (1.01 kg) y los menores para T4 (0.78 kg /animal/día ). En el análisis microeconómico se observó que el menor costo asociado con la producción de 1 kg de cerdo en pie se obtuvo para el T3, siendo 45% más bajo con respecto al T1. El comportamiento de la utilidad parcial bruta fue superior para el T3, estando un 46% más alta en relación con el T1, que fue el tratamiento que mejor desempeño presentó en la conversión alimenticia.