Please use this identifier to cite or link to this item: http://openarchive.nure.ua/handle/document/6905
Title: Medical online neuro-fuzzy diagnostics system with active learning
Authors: Bodyanskiy, Ye. V.
Perova, I.
Keywords: Medical Data Mining
active learning
neuro-fuzzy system
medical diagnostics
computational intelligence
learning vector quantization
self-learning procedure
Issue Date: 2017
Publisher: International Journal of Advances in Computer and Electronics Engineering
Citation: Bodyanskiy Ye. Medical online neuro-fuzzy diagnostics system with active learning / Ye. Bodyanskiy, I. Perova // // International Journal of Advances in Computer and Electronics Engineering. -July 2017. -Volume 2. Issue 7. - P. 1–10
Abstract: Situations when in the medical data set some patients have known diagnoses and all other have unknown ones is spread wise problem of present-day medicine. Known systems of computational intelligence show mediocre level of diagnostics in these data sets. In this paper online neuro-fuzzy diagnostics system with active learning is proposed. This system allows to increase a quality of medical diagnostics under the condition of small number of known reference signals due to combination of special learning algorithms – active learning. The proposed online neuro-fuzzy system is based on popular neural networks as Self-Organizing Map (SOM) and Learning Vector Quantization network (LVQ). Active learning procedure permits to tune their synaptic weights using simple recurrent self-learning procedures (SOM) and controlled learning with teacher (LVQ). Neuro-fuzzy diagnostics system with active learningwas used for breast cancer in Wisconsin data set processing and showed higher level of classification-clusterization results comparatively with known systems
URI: http://openarchive.nure.ua/handle/document/6905
Appears in Collections:Кафедра біомедичної інженерії (БМІ)

Files in This Item:
File Description SizeFormat 
18. IJACEE_FPV2I7P1.pdfосновная статья724.29 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.