Application of artificial neural networks (ANNs) for weight predictions of blue crabs (Callinectes sapidus RATHBUN, 1896) using predictor variables

Abstract

An evaluation of the performance of artificial neural networks (ANNs) to estimate the weights of blue crab (Callinectes sapidus) catches in Yumurtal k Cove (Iskenderun Bay) that uses measured predictor variables is presented, including carapace width (CW), sex (male, female and female with eggs), and sampling month. Blue crabs (n=410) were collected each month between February 1997 and January 1998. Sex, CW, and sampling month were used and specified in the input layer of the network. The weights of the blue crabs were utilized in the output layer of the network. A multi-layer perception architecture model was used and was calibrated with the Levenberg Marguardt (LM) algorithm. Finally, the values were determined by the ANN model using the actual data. The mean square error (MSE) was measured as 3.3, and the best results had a correlation coefficient (R) of 0.93. We compared the predictive capacity of the general linear model (GLM) versus the ANN for the estimation of the weights of blue crabs from independent field data. The results indicated the higher performance capacity of the ANN to predict weights compared to the GLM (R=0.97 vs. R=0.95, raw variable) when evaluated against independent field data.