Title: Comparison of artificial neural network and K-means for clustering dairy cattle

Authors: Hülya Atıl; Aslı Akıllı

Addresses: Biometry-Genetics Unit, Department of Animal Science, Faculty of Agriculture, Ege University, 35100 Bornova- Izmir, Turkey ' Biometry-Genetics Unit, Department of Animal Science, Faculty of Agriculture, Ahi Evran University, 40100 Kırşehir, Turkey

Abstract: Artificial neural network models (ANN's) are machine-learning systems, a type of artificial intelligence. They have been inspired by and developed along the working principles of the human brain and its nerve cells. ANN's are especially used in the modelling of nonlinear systems. With the information learned through repeated experience, similar to human learning, ANN's can provide classification, pattern recognition, optimisation and the realisation of forward-looking forecasts. Artificial neural network studies have been performed in animal husbandry in recent years. They have been used for the prediction of yield characteristics and classification, animal breeding, quality assessment, and disease diagnosis. In this study, classification of dairy cattle using artificial neural networks and cluster analysis are compared. Artificial neural networks models were determined to be more successful than cluster analysis.

Keywords: cattle classification; artificial neural networks; ANNs; dairy cattle; K-means clustering; animal husbandry; cluster analysis.

DOI: 10.1504/IJSAMI.2016.077266

International Journal of Sustainable Agricultural Management and Informatics, 2016 Vol.2 No.1, pp.40 - 52

Received: 20 Nov 2015
Accepted: 05 Jan 2016
Published online: 25 Jun 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article