Evaluation of a new computer method (ANNs) and traditional methods (LWRS and VBGF) in the calculation of some growth parameters of two cyprinid species

Artificial Neural Networks (ANNs) are a very reliable computer program used in many areas such as growth parameters. The aim of this study to compare the growth estimates of tigris scraper (Capoeta umbla (Heckel, 1843)) and kura barbel (Barbus lacerta (Heckel, 1843) captured from Karasu River (East Anatolia, Turkey) between 2014 and 2016. The age groups were 0-9 for C. umbla and 0-8 for B. lacerta. The estimated parameters of von Bertalanffy growth equations were as L' =51.96 cm, W' 804.16 g, k=0.092 year-1, t0=-1.763 year for C. umbla and L' 32.23 FP, W' 435.87 J, k 0.127\HDU-1, t0-2.489 for B. lacerta. The growth performance index (Y) value was comput-ed as 2.395 for C. umbla and 2.120 for B. lacerta. The length and weight relationships for two fish species were as follows: W=0.0092L3.05 (R²=0.98) and W=0.0095L3.07 (R2=0.98). The growth of these two cyprinid species were isometric growth. A ANNs model is a interdepented system containing many neurons. There are three different layers in a neural network (input, hidden and output layers). Data enters (length/weight, age, sex) at the inputs and passes along the network, by layer, till it reach-es at the outputs (weight/length). MATLAB Ver R2016a (Neural Network Toolbox) was used for ANNs estimatings. MAPE (%) equation was used to compare ANNs and other methods. According to the comparison of the results obtained with MAPE (%), ANNs provide better results than the LWRs and VBGF. The results of this study could give useful insight that ANNs can be evaluated as an alternative for growth prediction.