Multilayer neural network in differential diagnosis of balance disorders
Result description
The aim of this study was the differential diagnosis of balance disorders thus a clear distinction between the patient with balance disorders and the patient without balance disorders. The data used in this article was measured under the static conditions on the posturography platform. The patients were split to three groups, peripheral, central and normal based on doctor's diagnosis. These patients were used as input to neural network. Was selected the multilayer network with Backpropagation algorithm.The network was learned the combination of the particular diagnosis thus, the network was learned the combination of normal-peripheral, peripheral-central and central-normal diagnosis. The test set contained 10 normal, 10 peripheral, and 10 central patients, who were evaluated already learned the multilayer neural networks with Backpropagation algorithm. From the results was found out that the proposed multilayer network was able to correctly determine the diagnosis of the particularly
Keywords
posturographyRomberg testBackpropagation algorithmdifferential diagnosisbalance disordersperipheralcentral
The result's identifiers
Result code in IS VaVaI
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Multilayer neural network in differential diagnosis of balance disorders
Original language description
The aim of this study was the differential diagnosis of balance disorders thus a clear distinction between the patient with balance disorders and the patient without balance disorders. The data used in this article was measured under the static conditions on the posturography platform. The patients were split to three groups, peripheral, central and normal based on doctor's diagnosis. These patients were used as input to neural network. Was selected the multilayer network with Backpropagation algorithm.The network was learned the combination of the particular diagnosis thus, the network was learned the combination of normal-peripheral, peripheral-central and central-normal diagnosis. The test set contained 10 normal, 10 peripheral, and 10 central patients, who were evaluated already learned the multilayer neural networks with Backpropagation algorithm. From the results was found out that the proposed multilayer network was able to correctly determine the diagnosis of the particularly
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JC - Computer hardware and software
OECD FORD branch
—
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2012
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 16th WSEAS International Conference on Systems
ISBN
978-1-61804-108-1
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
356-361
Publisher name
WSEAS Press (GR)
Place of publication
Kos
Event location
Kos Island
Event date
Jul 14, 2012
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—
Basic information
Result type
D - Article in proceedings
CEP
JC - Computer hardware and software
Year of implementation
2012