Using multiple regression, neural networks and support vector machines to predict lamb carcasses composition

• Main Author: Silva, Filipe Samuel
• Publication Date: 2010
• Other Authors: Cortez, Paulo, Cadavez, Vasco
• Language: eng
• Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
• Download full: http://hdl.handle.net/1822/10826
• topic: Carcass; Multiple Regression; Neural Networks; Support Vector Machines; Tissue; Science & Technology

The objective of this work was to use a Data Mining (DM) approach to predict, using as predictors the car- cass measurements taken at slaughter line, the compo- sition of lamb carcasses. One hundred and twenty five lambs of Churra Galega Braganc ̧ana breed were slaugh- tered.During carcasses quartering, a caliper was used to perform subcutaneous fat measurements, over the max- imum depth of longissimus muscle (LM), between the 12th and 13th ribs (C12), and between the 1st and 2nd lumbar vertebrae (C1). The Muscle (MP), Bone (BP), Subcutaneous Fat (SFP), Inter-Muscular Fat (IFP), and Kidney Knob and Channel Fat (KKCF) proportions of lamb carcasses were computed. We used the rminer R library and compared three regression techniques: Mul- tiple Regression (MR), Neural Networks (NN) and Sup- port Vector Machines (SVM). The SVM model provided the lowest relative absolute error for the prediction of BP, SFP and KKCF, while MR presented the best pre- dictions for MP and IFP. Also, a sensitivity analysis procedure revealed the C12 measurement as the most relevant predictor for all five carcass tissues.