Sexual dimorphism prediction of Darevskia bithynica (Méhely 1909) from Northwestern Anatolia, Turkey by using artificial neural network

Main Article Content

Çağın Kandemir Çavaş Yusuf Kumlutaş Kamil Candan Çetin Ilgaz

Abstract

The main aim of the manuscript is to predict the gender of Darevskia bithynica by using a feed-forward back-propagation multilayer artificial neural network (ANN). Nine morphological characters were used as an input parameters of the model. The gender type male or female is the output parameter. The total number of data is 115. In order to train, validate and test the ANN model 70%, 15% and 15% of the total data are randomly selected. The regression coefficient (R) values are evaluated as prediction performance. The network with 20 neurons in the hidden is the optimal structure of the ANN that predict the lizard gender with a high R values as 0.98, 0.97 and 0.96 for training, testing and all data, respectively. The lower mean square error (MSE) values for training and testing data are calculated as 0.0145 and 0.0161, respectively. The obtained results satisfactorily confirm the high ability of the ANNs in predicting the gender of Darevskia bithynica.

Article Details

How to Cite
KANDEMIR ÇAVAŞ, Çağın et al. Sexual dimorphism prediction of Darevskia bithynica (Méhely 1909) from Northwestern Anatolia, Turkey by using artificial neural network. Hacettepe Journal of Biology and Chemistry, [S.l.], v. 46, n. 4, p. 473-480, jan. 2019. ISSN 1303-5002. Available at: <http://hjbc.hacettepe.edu.tr/index.php/hjbc/article/view/81>. Date accessed: 14 oct. 2019.
Section
Articles