The following information was submitted:
Transactions: INTERNATIONAL JOURNAL of MATHEMATICAL MODELS AND METHODS IN APPLIED SCIENCES
Transactions ID Number: 17-163
Full Name: Pavel Vaøacha
Position: Assistant
Age: ON
Sex: Male
Address: Faculty of Applied Informatics, Nad Stránìmi 4511, 760 05 Zlín
Country: CZECH REPUBLIC
Tel: 777567135
Tel prefix: 00420
Fax:
E-mail address: varacha@fai.utb.cz
Other E-mails:
Title of the Paper: Neural network evolution for an agglomeration heating power consumption approximation
Authors as they appear in the Paper: Pavel Vaøacha, Erik Král, Roman Jašek
Email addresses of all the authors: varacha@fai.utb.cz
Number of paper pages: 8
Abstract: This article deals with Analytic Programming (AP) which was proven to be highly effective tool of Artificial Neural Network (ANN) synthesis and optimization. AP is successfully applied here to evolve such ANN which is able to approximate heating power consumption of an agglomeration, in dependence on time and atmospherics temperature, more accurately than standard methods. An experiment described in the paper was realized on real life data from Most agglomeration and heating plant situated in Komoøany, Czech Republic. Resulted ANN brings 19% increase of approximation accuracy.
Keywords: neural network, approximation, heating plant, analytic programming, soma, optimization
EXTENSION of the file: .pdf
Special (Invited) Session: ANN Synthesis for an Agglomeration Heating Power Consumption
Organizer of the Session: 655-232
How Did you learn about congress: Tomas Horak tomas.horak@gmail.com Marie Drinkova mariedrinkova@seznam.cz
IP ADDRESS: 195.178.89.182
