Olena Vynokurova

Work place: Control Systems Research Laboratory, Kharkiv National University of Radio Electronics, Kharkiv, 61166, Ukraine

E-mail: olena.vynokurova@nure.ua


Research Interests: Computational Science and Engineering, Computer systems and computational processes, Data Mining, Process Control System, Data Structures and Algorithms


Olena Vynokurova graduated from Kharkiv National University of Radio Electronics in 2002. She got her PhD in 2005. She obtained an academic title of the Senior Researcher in 2007. She got his Dr.habil.sci.ing. in 2012. She obtained an academic title of the Professor in 2014. Prof. Vynokurova has been the Principal Research Scientist of Control Systems Research Laboratory at Kharkiv National University of Radio Electronics and the professor of Information Technology Security Department at Kharkiv National University of Radio Electronics. She has more than 150 scientific publications including 4 monographs. Her research interests are hybrid systems of computational intelligence: dynamical data mining, wavelet-neuro-, neo-fuzzy-, on-line systems that have to do with control, identification, and forecasting, clustering, diagnostics and fault detection.

Author Articles
Hybrid Clustering-Classification Neural Network in the Medical Diagnostics of the Reactive Arthritis

By Yevgeniy V. Bodyanskiy Olena Vynokurova Volodymyr Savvo Tatiana Tverdokhlib Pavlo Mulesa

DOI: https://doi.org/10.5815/ijisa.2016.08.01, Pub. Date: 8 Aug. 2016

In the paper, the hybrid clustering-classification neural network is proposed. This network allows to increase a quality of information processing under the condition of overlapping classes due to the rational choice of learning rate parameter and introducing special procedure of fuzzy reasoning in the clustering-classification process, which occurs both with external learning signal (“supervised”), and without one (“unsupervised”). As similarity measure neighborhood function or membership one, cosine structures are used, which allow to provide a high flexibility due to self-learning-learning process and to provide some new useful properties. Many realized experiments have confirmed the efficiency of proposed hybrid clustering-classification neural network; also, this network was used for solving diagnostics task of reactive arthritis.

[...] Read more.
Other Articles