Investigation of the influence of the metric type on the accuracy of Kohonen neural network’s clustering in the task of medical diagnostics by a blood test

Authors

  • Oleh Konstiantynovych Kolesnytskyi Vinnytsia National Technical University. Vinnitsa
  • Yuliia Oleksandrivna Zhuravska Vinnytsia National Technical University. Vinnitsa

Keywords:

Kohonen neural network, metrics, distance measure, clustering, medical diagnostics

Abstract

In current article the known metrics were analyzed and the influence of the metrics type on the accuracy of the clustering performed by Kohonen neural network was investigated. It was established that by using the weighted Euclidean distance as a metric in comparison with the others, the highest diagnostic accuracy in the task of medical patients’ diagnostics by a blood test using a Kohonen neural network is achieved.


Author Biographies

Oleh Konstiantynovych Kolesnytskyi, Vinnytsia National Technical University. Vinnitsa

assistant professor of computer science

Yuliia Oleksandrivna Zhuravska, Vinnytsia National Technical University. Vinnitsa

student group 1KN-14m

Downloads

Abstract views: 288

How to Cite

[1]
O. K. Kolesnytskyi and Y. O. Zhuravska, “Investigation of the influence of the metric type on the accuracy of Kohonen neural network’s clustering in the task of medical diagnostics by a blood test”, ІТКІ, vol. 31, no. 3, Feb. 2015.

Issue

Vol. 31 No. 3 (2014): Information Technology and Computer Engineering

Section

Biological and medical devices and systems

Metrics

Downloads

Download data is not yet available.