Acta Univ. Agric. Silvic. Mendelianae Brun. 2013, 61, 377-384
Published online 2013-04-24

Data adjustment for the purposes of self-teaching of the neural network, and its application for the model-reduction of classification of patients suffering from the ischemic heart disease

Vladimír Konečný1, Oldřich Trenz1, Milan Sepši2

1Department of Informatics, Mendel University in Brno, Zemědělská 1, 613 00 Brno, Czech Republic
2Department of Internal Cardiology Medicine – Institutions Shared with the Faculty Hospital in Brno – Institutions of Adult Age Medicine – Faculty of Medicine, Masaryk university in Brno, Jihlavská 20, 625 00 Brno, Czech Republic

Neural networks present a modern, very effective and practical instrument designated for decision-making support. To make use of them, we not only need to select the neural network type and structure, but also a corresponding data adjustment. One consequence of unsuitable data use can be an inexact or absolutely mistaken function of the model.
The need for a certain adjustment of input data comes from the features of the chosen neural network type, from the use of various metrics systems of object attributes, but also from the weight, i.e., the importance of individual attributes, but also from establishing representatives of classifying sets and learning about their characteristics.
For the purposes of the classification itself, we can suffice with a model in which the number of output neurons equals the number of classifying sets. Nonetheless, the model with a greater number of neurons assembled into a matrix can testify more about the problem, and provides clearer visual information.


9 live references