Live Weight Prediction in Norduz Sheep Using Machine Learning Algorithms

The objective of this study was to compare predictive performances of four machine learning (ML) models: Support Vector Machines with Radial Basis Function Kernel (SVMR), Classification and Regression Trees (CART), Random Forest (RF) and Model Average Neural Networks (MANN) to predict live weight from morphological measurements of Norduz sheep (n=93). Seven morphological measurements; chest girth (CG), chest width (CW), chest depth (CD), height at withers (HW), body length (BL), heigth at rump (HR) and rump width (RW) were used to predict live weigth (LW) of Norduz sheep. All morphological measurements were positively correlated to LW. Live weight had the highest correlation with CG and the lowest correlation with HR. Initially, highly correlated predictors were removed from the data set. The remaining predictors were then subjected to variable selection procedures using the Boruta algorithm. The results of Boruta confirmed the importance of the four predictors HW, BL, CW, and CD. However, HR confirmed to be unimportant was excluded from the dataset. The ML models were trained on selected predictors. The results showed that the prediction performance validated using the test dataset indicated that RF had the lowest values of Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percent Error (MAPE). The permutation-based variable importance scores indicate that CW and CD were the most important variables in predicting LW. The actual LW had the highest significant positive correlations with the values predicted by SVMR and RF, and followed by ANN and CART models respectively. There were no differences between the means of actual and predicted LWs by machine learning models. The fact that the models generalized well on the testing data sets indicates that machine learning algorithms have valid predictive patterns and are effective methods in LW weight of Norduz sheep. Considering runtime of the models, although the CART model had the lowest computational cost, it had the worst performance. The MANN algorithm, on the other hand, required a longer runtime to process the same dataset.

PDF

___

Abd-Allah S, Abd-El Rahman HH, Shoukry MM, Mohamed MI, Salman FM, Abedo AA. 2019. Some body measurements as a management tool for Shami goats raised in subtropical areas in Egypt. Bulletin of the National Research Centre, 43(1). doi: 10.1186/s42269-019-0042-9
Aytekin İ, Eyduran E, Karadas K, Akşahan R, Keskin İ. 2018. Prediction of Fattening Final Live Weight from some Body Measurements and Fattening Period in Young Bulls of Crossbred and Exotic Breeds using MARS Data Mining Algorithm. Pakistan Journal of Zoology, 50(1). doi: 10.17582/journal.pjz/2018.50.1.189.195
Benos L, Tagarakis AC, Dolias G, Berruto R, Kateris D, Bochtis D. 2021. Machine Learning in Agriculture: A Comprehensive Updated Review. Sensors (Basel), 21(11). doi: 10.3390/s21113758
Boehmke B, Greenwell B. 2019. Hands-On Machine Learning with R. CRC Press.
Brown DJ, Savage DB, Hinch GN, Hatcher S. 2015. Monitoring liveweight in sheep is a valuable management strategy: a review of available technologies. Animal Production Science, 55(4). doi: 10.1071/an13274
Burke J, Nuthall P, McKinnon A. 2004. An analysis of the feasibility of using image processing to estimate the live weight of sheep. FHMG research report., Applied Management and Computing Division, Lincoln University. Canterbury, New Zealand.
Celik S, Eyduran E, Karadas K, Tariq MM. 2017. Comparison of predictive performance of data mining algorithms in predicting body weight in Mengali rams of Pakistan. Revista Brasileira de Zootecnia, 46(11):863-872. doi: 10.1590/s1806- 92902017001100005
Chacón E, Macedo F, Velázquez F, Paiva SR, Pineda E, McManus C. 2011. Morphological measurements and body indices for Cuban Creole goats and their crossbreds. Revista Brasileira de Zootecnia, 40(8):1671-1679. doi: 10.1590/s1516-35982011000800007
Cominotte A, Fernandes AFA, Dorea JRR, Rosa GJM, Ladeira MM, van Cleef EHCB, Pereira GL, Baldassini WA, Machado Neto OR. 2020. Automated computer vision system to predict body weight and average daily gain in beef cattle during growing and finishing phases. Livestock Science, 232:103904. doi: 10.1016/j.livsci.2019.103904
Dakhlan A, Saputra A, Hamdani MDI, Sulastri S. 2020. Regression Models and Correlation Analysis for Predicting Body Weight of Female Ettawa Grade Goat using its Body Measurements. Advances in Animal and Veterinary Sciences, 8(11). doi: 10.17582/journal.aavs/2020/8.11.1142.1146
Fernandes AFA, Dorea JRR, Fitzgerald R, Herring W, Rosa GJM. 2019. A novel automated system to acquire biometric and morphological measurements and predict body weight of pigs via 3D computer vision. Journal of Animal Science, 97(1):496-508. doi: 10.1093/jas/sky418
Ferra JdC, Cieslak S, Sartori Filho R, McManus C, Martins CF, Sereno JRB. 2010. Weight and age at puberty and their correlations with morphometric measurements in crossbred breed Suffolk ewe lambs. Revista Brasileira de Zootecnia, 39(1):134-141. doi: 10.1590/s1516-35982010000100018
Gomes RA, Monteiro GR, Assis GJ, Busato KC, Ladeira MM, Chizzotti ML. 2016. Technical note: Estimating body weight and body composition of beef cattle trough digital image analysis. Journal of Animal Science, 94(12):5414-5422. doi: 10.2527/jas2016-0797
Greenwell BM, Boehmke BC. 2020. Variable Importance Plots— An Introduction to the vip Package. The R Journal, 12(1):343. doi: 10.32614/rj-2020-013
Hamner B, Frasco M. 2018. Metrics: Evaluation Metrics for Machine Learning. R package version 0.1.4. https://CRAN.R-project.org/package=Metrics.
Huma ZE, Iqbal F. 2019. Predicting the body weight of Balochi sheep using a machine learning approach. Turkish Journal of Veterinary and Animal Sciences, 43(4):500-506. doi: 10.3906/vet-1812-23
Iqbal F, Raziq A, Huma ZE, Ali M. 2021. An application of least square support vector machine model with parameters optimization for predicting body weight of Harnai sheep breed. Turkish Journal of Veterinary and Animal Sciences, 45(4):716-725. doi: 10.3906/vet-2009-105
Kashiha M, Bahr C, Ott S, Moons CPH, Niewold TA, Ödberg FO, Berckmans D. 2014. Automatic weight estimation of individual pigs using image analysis. Computers and Electronics in Agriculture, 107:38-44. doi: 10.1016/j.compag.2014.06.003
Kuhn M. 2020. caret: Classification and Regression Training. R package version 6.0-86. https://CRAN.R- project.org/package=caret.
Kuhn M, Johnson K. 2013. Applied Predictive Modeling. Springer, New York.
Kuhn M, Johnson K. 2019. Feature Engineering and Selection: A Practical Approach for Predictive Models. CRC Press.
Kursa MB, Rudnicki WR. 2010. Feature Selection with the Boruta Package. Journal of Statistical Software, 36(11). doi: 10.18637/jss.v036.i11
Lee DH, Lee SH, Cho BK, Wakholi C, Seo YW, Cho SH, Kang TH, Lee WH. 2020. Estimation of carcass weight of Hanwoo (Korean native cattle) as a function of body measurements using statistical models and a neural network. Asian- Australasian Journal of Animal Sciences, 33(10):1633-1641. doi: 10.5713/ajas.19.0748
Mavule BS, Muchenje V, Bezuidenhout CC, Kunene NW. 2013. Morphological structure of Zulu sheep based on principal component analysis of body measurements. Small Ruminant Research, 111(1-3):23-30. doi: 10.1016/j.smallrumres. 2012.09.008
Meghelli I, Kaouadji Z, Yilmaz O, Cemal I, Karaca O, Gaouar SBS. 2020. Morphometric characterization and estimating body weight of two Algerian camel breeds using morphometric measurements. Tropical Animal Health and Production, 52(5):2505-2512. doi: 10.1007/s11250-020- 02204-x
Mekparyup J, Saithanu K, Arunkeeree N. 2013. Estimation of body weight of holstein-friesian cattle with multiple regression analysis. International Journal of Applied Mathematics and Statistics, 44(14):1-7.
Menesatti P, Costa C, Antonucci F, Steri R, Pallottino F, Catillo G. 2014. A low-cost stereovision system to estimate size and weight of live sheep. Computers and Electronics in Agriculture, 103:33-38. doi: 10.1016/j.compag.2014.01.018
Miller GA, Hyslop JJ, Barclay D, Edwards A, Thomson W, Duthie C-A. 2019. Using 3D Imaging and Machine Learning to Predict Liveweight and Carcass Characteristics of Live Finishing Beef Cattle. Frontiers in Sustainable Food Systems, 3. doi: 10.3389/fsufs.2019.00030
Morota G, Ventura RV, Silva FF, Koyama M, Fernando SC. 2018. Big Data Analytics and Precision Animal Agriculture Symposium: Machine learning and data mining advance predictive big data analysis in precision animal agriculture. Journal of Animal Science, 96(4):1540-1550. doi: 10.1093/jas/sky014
Negretti P, Bianconi G, Bartocci S, Terramoccia S. 2007. Lateral Trunk Surface as a new parameter to estimate live body weight byVisual Image Analysis. Italian Journal of Animal Science, 6(sup2):1223-1225. doi: 10.4081/ijas.2007.s2.1223
Norouzian MA, Vakili Alavijeh M. 2016. Comparison of artificial neural network and multiple regression analysis for prediction of fat tail weight of sheep. Iranian Journal of Applied Animal Science, 6(4):895-900.
Olaniyi TA, Popoola MA, Olaniyi OA, Faniyi TO, Iniobong U. 2018. Relationship between morphological traits, body indices and body condition score as welfare indicators of Nigerian sheep. Journal of Animal Science and Veterinary Medicine, 3(1):1-5. doi: 10.31248/jasvm2017.078
Pabiou T, Fikse WF, Cromie AR, Keane MG, Näsholm A, Berry DP. 2011. Use of digital images to predict carcass cut yields in cattle. Livestock Science, 137(1-3):130-140. doi: 10.1016/j.livsci.2010.10.012
Patil I. 2021. Visualizations with statistical details: The 'ggstatsplot' approach. Journal of Open Source Software, 6(61):3167. doi: 10.21105/joss.03167
Pogorzelska-Przybyłek P, Nogalski Z, Wielgosz-Groth Z, Winarski R, Sobczuk-Szul M, Łapińska P, Purwin C. 2014. Prediction of the Carcass Value of Young Holstein-Friesian Bulls Based on Live Body Measurements. Annals of Animal Science, 14(2):429-439. doi: 10.2478/aoas-2014-0004
RCoreTeam. 2021. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL https://www.R-project.org/.
Salawu EO, Abdulraheem M, Shoyombo A, Adepeju A, Davies S, Akinsola O, Nwagu B. 2014. Using Artificial Neural Network to Predict Body Weights of Rabbits. Open Journal of Animal Sciences, 04(04):182-186. doi: 10.4236/ojas.2014.44023
Sant’Ana DA, Pache MCB, Martins J, Soares WP, de Melo SLN, Garcia V, de Moares Weber VA, da Silva Heimbach N, Mateus RG, Pistori H. 2021. Weighing live sheep using computer vision techniques and regression machine learning. Machine Learning with Applications, 5:100076. doi: 10.1016/j.mlwa.2021.100076
Shahinfar S, Kelman K, Kahn L. 2019. Prediction of sheep carcass traits from early-life records using machine learning. Computers and Electronics in Agriculture, 156:159-177. doi: 10.1016/j.compag.2018.11.021
Tebug SF, Missohou A, Sourokou Sabi S, Juga J, Poole EJ, Tapio M, Marshall K. 2016. Using body measurements to estimate live weight of dairy cattle in low-input systems in Senegal. Journal of Applied Animal Research, 46(1):87-93. doi: 10.1080/09712119.2016.1262265
Valletta JJ, Torney C, Kings M, Thornton A, Madden J. 2017. Applications of machine learning in animal behaviour studies. Animal Behaviour, 124:203-220. doi: 10.1016/j.anbehav.2016.12.005
Weber VAdM, Weber FdL, Gomes RdC, Oliveira AdS, Menezes GV, Abreu UGPd, Belete NAdS, Pistori H. 2020a. Prediction of Girolando cattle weight by means of body measurements extracted from images. Revista Brasileira de Zootecnia, 49. doi: 10.37496/rbz4920190110
Weber VAM, Weber FdL, Oliveira AdS, Astolfi G, Menezes GV, de Andrade Porto JV, Rezende FPC, Moraes PHd, Matsubara ET, Mateus RG, de Araújo TLAC, da Silva LOC, de Queiroz EQA, de Abreu UGP, da Costa Gomes R, Pistori H. 2020b. Cattle weight estimation using active contour models and regression trees Bagging. Computers and Electronics in Agriculture, 179:105804. doi: 10.1016/j.compag.2020.105804
Wickham H. 2016. ggplot2: Elegant Graphics for Data Analysis. Springer-Verlag, New York.
Zhang ALN, Wu BP, Jiang CXH, Xuan DCZ, Ma EYH, Zhang FYA. 2018. Development and validation of a visual image analysis for monitoring the body size of sheep. Journal of Applied Animal Research, 46(1):1004-1015. doi: 10.1080/09712119.2018.1450257.