Pregled bibliografske jedinice broj: 232027
An Approach to Propagation Modeling for Indoor WLAN Applications Using Neural Networks
An Approach to Propagation Modeling for Indoor WLAN Applications Using Neural Networks // Conference Proceedings ICECOM 2005 18th International Conference on Applied Electromagnetics and Communications and joint COST 284 Workshop / Davor Bonefačić (ur.).
Dubrovnik: Hrvatsko društvo za komunikacije, računarstvo, elektroniku, mjerenja I automatiku (KoREMA), 2005. str. 105-108 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 232027 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
An Approach to Propagation Modeling for Indoor WLAN Applications Using Neural Networks
Autori
Vilović, Ivan
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Conference Proceedings ICECOM 2005 18th International Conference on Applied Electromagnetics and Communications and joint COST 284 Workshop
/ Davor Bonefačić - Dubrovnik : Hrvatsko društvo za komunikacije, računarstvo, elektroniku, mjerenja I automatiku (KoREMA), 2005, 105-108
Skup
18th International Conference on Applied Electromagnetics and Communications
Mjesto i datum
Dubrovnik, Hrvatska, 12.10.2005. - 14.10.2005
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
WLAN; ray tracing model; neural network model; signal strength
Sažetak
This paper reports results obtained by propagation modeling for WLAN applications. A multi-ray model is proposed and tested through analytical calculations, neural network simulation, and measurements. As the case used a corridor of university building in Dubrovnik, for which calculation, simulation and measurement of signal strength were obtained. Calculation is based on ray-tracing method with neglecting diffraction and scattering. The results of calculation are compared with measurement. Neural network architecture is proposed with back-propagation training algorithm. The simulation data matches with measurement data rather good.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Računarstvo
POVEZANOST RADA
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb,
Sveučilište u Dubrovniku