Classification of Spatio-Temporal Data

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F10%3A00171587" target="_blank" >RIV/68407700:21240/10:00171587 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Classification of Spatio-Temporal Data
Original language description
This paper presents a new approach in spatio-temporal data classification. Due to easy transformation of time dimension of spatio-temporal data into the phase of complex number, the presented approach uses complex numbers. The classification is based ona complex-valued neural network with multilayer topology. The paper proposes an extension of complexvalued backpropagation algorithm, which uses activation function applying nonlinearity on the amplitude only (preserving the phase). In order to transformthe input data into complex numbers, a new coding technique is presented. Output coding is developed allowing the classification from complex numbers. It is solved with introduction of one-of-N coding extension into complex numbers, which is used as network's output coding. This approach is verified in application of hand-written character recognition, using the data collected during the writing process. The simulation results of this application are presented in the paper.
Czech name
—
Czech description
—

Publication year
2010
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 7th EUROSIM Congress on Modelling and Simulation, Vol. 2: Full Papers
ISBN
978-80-01-04589-3
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
—
Publisher name
Department of Computer Science and Engineering, FEE, CTU in Prague
Place of publication
Prague
Event location
Praha
Event date
Sep 6, 2010
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)