Home > Research > Publications & Outputs > New self-adaptive probabilistic neural networks...
View graph of relations

New self-adaptive probabilistic neural networks in bioinformatic and medical tasks

Research output: Contribution to Journal/MagazineJournal articlepeer-review

  • Vassilis L. Georgiou
  • Nicos Pavlidis
  • Kostantinos E. Parsopoulos
  • Philipos D. Alevizos
  • Michael N. Vrahatis
<mark>Journal publication date</mark>06/2006
<mark>Journal</mark>International Journal on Artificial Intelligence Tools
Issue number3
Number of pages26
Pages (from-to)371-396
Publication StatusPublished
<mark>Original language</mark>English


We propose a self–adaptive probabilistic neural network model, which incorporates optimization algorithms to determine its spread parameters. The performance of the proposed model is investigated on two protein localization problems, as well as on two medical diagnostic tasks. Experimental results are compared with that of feedforward neural networks and support vector machines. Different sampling techniques are used and statistical tests are conducted to calculate the statistical significance of the results.