Predicting shrimp growth: Artificial neural network versus nonlinear regression models

摘要: Abstract This study evaluated the potential of artificial neural networks (ANN) as an alternative to traditional statistical regression techniques for purpose predicting shrimp growth in a commercial setting. Empirical data collected from farm Hawaii was used this evaluation. Eight functional forms (i.e., linear, polynomial, log reciprocal, von Bertalanffy, Gompertz, logistic and exponential) were employed counterparts ANN. The specific models first estimated dataset consisting 459 records then applied 249 validate their predictive performance. Performance assessed by four measures root mean square error (RMSE), R 2 , percentage wrong turning points predicted values that are within 5% tolerance corresponding actual values). results indicated ANN outperformed complex set conditions typical production environment. generated slightly better descriptive curve than best ones nonlinear made most accurate prediction. Hence, we conclude represents valuable tool variable typifying farms.