Disentangling data dependency using cross-validation strategies to evaluate prediction quality of cattle grazing activities using machine learning algorithms and wearable sensor data.

Wearable sensors have been explored as an alternative for real-time monitoring of cattle feeding behavior in grazing systems. To evaluate the performance of predictive models such as machine learning (ML) techniques, data cross-validation (CV) approaches are often employed. However, due to data dependencies and confounding effects, poorly performed validation strategies may significantly inflate the prediction quality. In this context, our objective was to evaluate the effect of different CV strategies on the prediction of grazing activities in cattle using wearable sensor (accelerometer) data and ML algorithms. Six Nellore bulls (average live weight of 345 ± 21 kg) had their behavior visually classified as grazing or not-grazing for a period of 15 d. Elastic Net Generalized Linear Model (GLM), Random Forest (RF), and Artificial Neural Network (ANN) were employed to predict grazing activity (grazing or not-grazing) using 3-axis accelerometer data. For each analytical method, three CV strategies were evaluated: holdout, leave-one-animal-out (LOAO), and leave-one-day-out (LODO). Algorithms were trained using similar dataset sizes (holdout: n = 57,862; LOAO: n = 56,786; LODO: n = 56,672). Overall, GLM delivered the worst prediction accuracy (53%) compared with the ML techniques (65% for both RF and ANN), and ANN performed slightly better than RF for LOAO (73%) and LODO (64%) across CV strategies. The holdout yielded the highest nominal accuracy values for all three ML approaches (GLM: 59%, RF: 76%, and ANN: 74%), followed by LODO (GLM: 49%, RF: 61%, and ANN: 63%) and LOAO (GLM: 52%, RF: 57%, and ANN: 57%). With a larger dataset (i.e., more animals and grazing management scenarios), it is expected that accuracy could be increased. Most importantly, the greater prediction accuracy observed for holdout CV may simply indicate a lack of data independence and the presence of carry-over effects from animals and grazing management. Our results suggest that generalizing predictive models to unknown (not used for training) animals or grazing management may incur poor prediction quality. The results highlight the need for using management knowledge to define the validation strategy that is closer to the real-life situation, i.e., the intended application of the predictive model.

Image Analysis and Computer Vision Applications in Animal Sciences: An Overview.

Computer Vision, Digital Image Processing, and Digital Image Analysis can be viewed as an amalgam of terms that very often are used to describe similar processes. Most of this confusion arises because these are interconnected fields that emerged with the development of digital image acquisition. Thus, there is a need to understand the connection between these fields, how a digital image is formed, and the differences regarding the many sensors available, each best suited for different applications. From the advent of the charge-coupled devices demarking the birth of digital imaging, the field has advanced quite fast. Sensors have evolved from grayscale to color with increasingly higher resolution and better performance. Also, many other sensors have appeared, such as infrared cameras, stereo imaging, time of flight sensors, satellite, and hyperspectral imaging. There are also images generated by other signals, such as sound (ultrasound scanners and sonars) and radiation (standard x-ray and computed tomography), which are widely used to produce medical images. In animal and veterinary sciences, these sensors have been used in many applications, mostly under experimental conditions and with just some applications yet developed on commercial farms. Such applications can range from the assessment of beef cuts composition to live animal identification, tracking, behavior monitoring, and measurement of phenotypes of interest, such as body weight, condition score, and gait. Computer vision systems (CVS) have the potential to be used in precision livestock farming and high-throughput phenotyping applications. We believe that the constant measurement of traits through CVS can reduce management costs and optimize decision-making in livestock operations, in addition to opening new possibilities in selective breeding. Applications of CSV are currently a growing research area and there are already commercial products available. However, there are still challenges that demand research for the successful development of autonomous solutions capable of delivering critical information. This review intends to present significant developments that have been made in CVS applications in animal and veterinary sciences and to highlight areas in which further research is still needed before full deployment of CVS in breeding programs and commercial farms.

Forecasting beef production and quality using large-scale integrated data from Brazil.

With agriculture rapidly becoming a data-driven field, it is imperative to extract useful information from large data collections to optimize the production systems. We compared the efficacy of regression (linear regression or generalized linear regression [GLR] for continuous or categorical outcomes, respectively), random forests (RF) and multilayer neural networks (NN) to predict beef carcass weight (CW), age when finished (AS), fat deposition (FD), and carcass quality (CQ). The data analyzed contained information on over 4 million beef cattle from 5,204 farms, corresponding to 4.3% of Brazil's national production between 2014 and 2016. Explanatory variables were integrated from different data sources and encompassed animal traits, participation in a technical advising program, nutritional products sold to farms, economic variables related to beef production, month when finished, soil fertility, and climate in the location in which animals were raised. The training set was composed of information collected in 2014 and 2015, while the testing set had information recorded in 2016. After parameter tuning for each algorithm, models were used to predict the testing set. The best model to predict CW and AS was RF (CW: predicted root mean square error = 0.65, R2 = 0.61, and mean absolute error = 0.49; AS: accuracy = 28.7%, Cohen's kappa coefficient [Kappa] = 0.08). While the best approach for FD and CQ was GLR (accuracy = 45.7%, Kappa = 0.05, and accuracy = 58.7%, Kappa = 0.09, respectively). Across all models, there was a tendency for better performance with RF and regression and worse with NN. Animal category, nutritional plan, cattle sales price, participation in a technical advising program, and climate and soil in which animals were raised were deemed important for prediction of meat production and quality with regression and RF. The development of strategies for prediction of livestock production using real-world large-scale data will be core to projecting future trends and optimizing the allocation of resources at all levels of the production chain, rendering animal production more sustainable. Despite beef cattle production being a complex system, this analysis shows that by integrating different sources of data it is possible to forecast meat production and quality at the national level with moderate-high levels of accuracy.