摘要
Current techniques for measuring feed intake in housed cattle are both expensive and time-consuming making them unsuitable for use on commercial farms. Estimates of individual animal intake are required for assessing production efficiency. The aim of this study was to predict individual animal intake using parameters that can be easily obtained on commercial farms including feeding behaviour, liveweight and age. In total, 80 steers were used, and each steer was allocated to one of two diets (40 per diet) which consisted of (g/kg; DM) forage to concentrate ratios of either 494:506 (MIXED) or 80:920 (CONC). Individual daily fresh weight intakes (FWI; kg/day) were recorded for each animal using 32 electronic feeders over a 56-day period, and individual DM intakes (DMI; kg/day) subsequently calculated. Individual feeding behaviour variables were calculated for each day of the measurement period from the electronic feeders and included: total number of visits to the feeder, total time spent at the feeder (TOTFEEDTIME), total time where feed was consumed (TIMEWITHFEED) and average length of time during each visit to the feeder. These feeding behaviour variables were chosen due to ease of obtaining from accelerometers. Four modelling techniques to predict individual animal intake were examined, based on (i) individual animal TOTFEEDTIME relative expressed as a proportion of the dietary group (GRP) and total GRP intake, (ii) multiple linear regression (REG) (iii) random forests (RF) and (iv) support vector regressor (SVR). Each model was used to predict CONC and MIXED diets separately, giving eight prediction models, (i) GRP_CONC, (ii) GRP_MIXED, (iii) REG_CONC, (iv) REG_MIXED, (v) RF_CONC, (vi) RF_MIXED, (vii) SVR_CONC and (viii) SVR_MIXED. Each model was tested on FWI and DMI. Model performance was assessed using repeated measures correlations (R2_RM) to capture the repeated nature of daily intakes compared with standard R2, RMSE and mean absolute error (MAE). REG, RF and SVR models predicted FWI with R2_RM = 0.1–0.36, RMSE = 1.51–2.96 kg and MAE = 1.19–2.49 kg, and DMI with R2_RM = 0.13–0.19, RMSE = 1.15–1.61 kg and MAE = 0.9–1.28 kg. The GRP models predicted FWI with R2_RM = 0.42–0.49, RMSE = 2.76–3.88 kg and MAE = 2.46–3.47 kg, and DMI with R2_RM = 0.32–0.44, RMSE = 0.32–0.44 kg, MAE = 1.55–2.22 kg. Whilst more simplistic GRP models showed higher R2_RM than regression and machine learning techniques, these models had larger errors, likely due to individual feeding patterns not being captured. Although regression and machine learning techniques produced lower errors associated with individual intakes, overall precision of prediction was too low for practical use.
摘要译文
用于测量储存牛进料摄入量的当前技术既昂贵又耗时，使其不适合在商业农场上使用。需要评估生产效率所需的个体动物摄入量。本研究的目的是使用可以在商业农场容易获得的参数预测单独的动物摄入，包括喂养行为，活重和年龄。总共使用80个阉牛，将每个转向分配给两种饮食（每种饮食40的40次），其由（G / kg; DM）饲料组成，以浓缩494：506（混合）或80：920（浓缩）。使用32个电子饲养器在56天的时间内每只动物记录单独的每日新鲜重量摄入量（FWI;千克/天），随后计算单独的DM摄入量（DMI; KG /日）。从电子馈送器的测量期间的每一天计算各个馈送行为变量，包括：对馈线的总访问量，在馈线（TotfeedTime）的总时间，消耗饲料的总时间（TimeWithFeed）和平均长度每次访问喂食器时的时间。由于易于获得加速度计，选择这些饲养行为变量。检查四种建模技术，以预测单个动物摄入量，基于（i）单独的动物Totfeedtime相对表达为膳食组（GRP）和总GRP Intake的比例，（ii）多元线性回归（III）随机森林（rf）和（iv）支持向量regressor（svr）。每个模型用于分别预测浓缩和混合饮食，给出八个预测模型，（i）grp_conc，（ii）grp_mixed，（iiv）reg_mixed，（v）rf_conc，（vi）rf_mixed（vii） svr_conc和（viii）svr_mixed。每个模型都在FWI和DMI上进行了测试。使用重复测量的相关性评估模型性能（R 2 _rm），以捕获与标准R 2 ，RMSE和平均绝对误差（MAE）相比每日摄入量的反复性质。 REG，RF和SVR模型预测FWI，R 2 _RM = 0.1-0.36，RMSE = 1.51-2.96 kg和MAE = 1.19-2.49 kg，以及带有R 2 的DMI _rm = 0.13-0.19，RMSE = 1.15-1.61千克和MAE = 0.9-1.28千克。 GRP模型通过R 2 _RM = 0.42-0.49，RMSE = 2.76-3.88 kg和MAE = 2.46-3.47 kg，以及带有R 2 _RM = 0.32的DMI -0.44，RMSE = 0.32-0.44千克，MAE = 1.55-2.22千克。虽然比回归和机器学习技术更简单地显示出更高的R 2 _rm，但这些模型的错误有更大的误差，可能由于未被捕获的各个馈电模式。虽然回归和机器学习技术产生了与个体摄入量相关的误差，但是预测的整体精度对于实际使用太低了。
C. Davison[a][1];J.M. Bowen[b][1];C. Michie[a];J.A. Rooke[b];N. Jonsson[c];I. Andonovic[a];C. Tachtatzis[a];M. Gilroy[d];C-A. Duthie[b]. Predicting feed intake using modelling based on feeding behaviour in finishing beef steers[J]. animal, 2021,15(7)