Publication detail

ESTIMATION THE TRANSMISSION BETWEEN ANTENNAS USING ARTIFICIAL NEURAL NETWORKS IN THE UWB BAND

KOTOL, M. PROKEŠ, A. MIKULÁŠEK, T. RAIDA, Z.

Original Title

ESTIMATION THE TRANSMISSION BETWEEN ANTENNAS USING ARTIFICIAL NEURAL NETWORKS IN THE UWB BAND

English Title

ESTIMATION THE TRANSMISSION BETWEEN ANTENNAS USING ARTIFICIAL NEURAL NETWORKS IN THE UWB BAND

Type

conference paper

Language

en

Original Abstract

The characteristics of the transmission channel inside the car are very important for future intra-car communication technologies. These technologies will create the small wireless networks for the distribution of data services such as internet, video, audio, etc. transmission. For these services, it is preferable to use the UWB frequency band from 3 GHz to 11 GHz because of the hardware support availability. An estimation of transmission channel characteristic is time-consuming and computationally demanding process. Presented paper deals with the channel transfer function estimation for different receiving antenna locations determined by the two dimensional grid. Proposed artificial neural network used for the analysis of the transmission channel is based on the feed forward and radial basis function structure. Neural networks have been optimized using measured channel transfer function to achieve better effectiveness, speed and accuracy.

English abstract

The characteristics of the transmission channel inside the car are very important for future intra-car communication technologies. These technologies will create the small wireless networks for the distribution of data services such as internet, video, audio, etc. transmission. For these services, it is preferable to use the UWB frequency band from 3 GHz to 11 GHz because of the hardware support availability. An estimation of transmission channel characteristic is time-consuming and computationally demanding process. Presented paper deals with the channel transfer function estimation for different receiving antenna locations determined by the two dimensional grid. Proposed artificial neural network used for the analysis of the transmission channel is based on the feed forward and radial basis function structure. Neural networks have been optimized using measured channel transfer function to achieve better effectiveness, speed and accuracy.

Keywords

Artificial neural network, feed forward neural networks, radial basis function neural network, car, measurement, channel transmission function

Released

08.08.2016

Publisher

IEEE Xplore

ISBN

978-1-5090-6093-1

Book

2016 Progress in Electromagnetic Research Symposium (PIERS)

Pages from

1465

Pages to

1469

Pages count

4

URL

BibTex


@inproceedings{BUT129207,
  author="Martin {Kotol} and Aleš {Prokeš} and Tomáš {Mikulášek} and Zbyněk {Raida}",
  title="ESTIMATION THE TRANSMISSION BETWEEN ANTENNAS USING ARTIFICIAL NEURAL NETWORKS IN THE UWB BAND",
  annote="The characteristics of the transmission channel inside the car are very important for future intra-car communication technologies. These technologies will create the small wireless networks for the distribution of data services such as internet, video, audio, etc. transmission. For these services, it is preferable to use the UWB frequency band from 3 GHz to 11 GHz because of the hardware support availability. An estimation of transmission channel characteristic is time-consuming and computationally demanding process. Presented paper deals with the channel transfer function estimation for different receiving antenna locations determined by the two dimensional grid.  Proposed artificial neural network used for the analysis of the transmission channel is based on the feed forward and radial basis function structure. Neural networks have been optimized using measured channel transfer function to achieve better effectiveness, speed and accuracy.",
  address="IEEE Xplore",
  booktitle="2016 Progress in Electromagnetic Research Symposium (PIERS)",
  chapter="129207",
  doi="10.1109/PIERS.2016.7734683",
  howpublished="online",
  institution="IEEE Xplore",
  year="2016",
  month="august",
  pages="1465--1469",
  publisher="IEEE Xplore",
  type="conference paper"
}