首页|Study Findings on Machine Learning Reported by Researchers at Federal University Lavras (Use of machine learning approaches for body weight prediction in Peruvi an Corriedale Sheep)
Study Findings on Machine Learning Reported by Researchers at Federal University Lavras (Use of machine learning approaches for body weight prediction in Peruvi an Corriedale Sheep)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on artificial intelligenc e is the subject of a new report. According to news originating from Federal Uni versity Lavras by NewsRx correspondents, research stated, “The goal of this stud y was to predict the body weight of Corriedale ewes using machine learning (ML) algorithms. Fourteen body measurements (BM) and six different machine learning m odels were used.” The news reporters obtained a quote from the research from Federal University La vras: “Body weight (BW) and BM: wither height (WH), rump height (RH), thoracic p erimeter (TP), abdominal perimeter (AP), foreshank length (FSL), fore-shank widt h (FSW), fore-shank perimeter (FSP), tail width (TW), tail perimeter (TPe), hip width (HW), loin width (LWi), shoulder width (SW), forelimb length (FL), and bod y length (BL), were collected from 100 Corriedale ewes between 1.5 and 2 years o ld from the Illpa Experimental Centre of the National University of Altiplano in Peru. The machine learning algorithms used to estimate body weight were Support Vector Machines for Regression (SVMR), Classification and Regression Trees (CAR T), Random Forest (RF), Model Average Neural Networks (MANN), Multivariate Adapt ive Regression Splines (MARS) and eXtreme Gradient Boosting (XGBoost). The perfo rmance of the models was evaluated by the coefficient of determination (R2), roo t mean square error (RMSE), mean absolute error (MAE), and mean absolute percent age error (MAPE). Highly correlated predictors (r 075) were removed from the dat aset. The remaining predictors were then subjected to variable selection procedu res using the Boruta algorithm. Boruta results confirmed the importance of TP, L Wi, BL, FSL, SW and HW as predictors of ewe weight. The ML models were then trai ned on those selected predictors.”
Federal University LavrasCyborgsEmer ging TechnologiesMachine Learning
NETL
NSTL
