Neural network prediction of radio propagation

Lei Qiu; Danchi Jiang; Leif Hanlen

doi:10.1109/AUSCTW.2005.1624263

Neural network prediction of radio propagation

Lei Qiu^*, Danchi Jiang, Leif Hanlen

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

15 Citations (Scopus)

Abstract

Preliminary work for predicting signal distributions in a local area, using a feature-based neural network is presented. The neural network is trained by radio signal measurements at known positions. After appropriately setting the parameters of nodes of the neural network, a corresponding virtual propagation environment is built, which reasonably represents the actual environment. Radio signal strength distribution is predicted by the virtual environment. A new method for radio signal measurement is introduced which mitigates the effect of small scale fading when determining the fingerprint of a position.

Original language	English
Title of host publication	Proceedings 6th Australian Communications Theory Workshop 2005
Pages	272-277
Number of pages	6
DOIs	https://doi.org/10.1109/AUSCTW.2005.1624263
Publication status	Published - 2005
Event	6th Australian Communications Theory Workshop 2005 - Brisbane, Australia Duration: 2 Feb 2005 → 4 Feb 2005

Publication series

Name	Proceedings 6th Australian Communications Theory Workshop 2005
Volume	2005

Conference

Conference	6th Australian Communications Theory Workshop 2005
Country/Territory	Australia
City	Brisbane
Period	2/02/05 → 4/02/05

Access to Document

10.1109/AUSCTW.2005.1624263

Cite this

@inproceedings{88494f012f554e93b171bf5796d2da0c,

title = "Neural network prediction of radio propagation",

abstract = "Preliminary work for predicting signal distributions in a local area, using a feature-based neural network is presented. The neural network is trained by radio signal measurements at known positions. After appropriately setting the parameters of nodes of the neural network, a corresponding virtual propagation environment is built, which reasonably represents the actual environment. Radio signal strength distribution is predicted by the virtual environment. A new method for radio signal measurement is introduced which mitigates the effect of small scale fading when determining the fingerprint of a position.",

keywords = "IEEE 802.11b, Neural networks, Radio measurement, Radio propagation",

author = "Lei Qiu and Danchi Jiang and Leif Hanlen",

year = "2005",

doi = "10.1109/AUSCTW.2005.1624263",

language = "English",

isbn = "0780390075",

series = "Proceedings 6th Australian Communications Theory Workshop 2005",

pages = "272--277",

booktitle = "Proceedings 6th Australian Communications Theory Workshop 2005",

note = "6th Australian Communications Theory Workshop 2005 ; Conference date: 02-02-2005 Through 04-02-2005",

}

Qiu, L, Jiang, D & Hanlen, L 2005, Neural network prediction of radio propagation. in Proceedings 6th Australian Communications Theory Workshop 2005., 1624263, Proceedings 6th Australian Communications Theory Workshop 2005, vol. 2005, pp. 272-277, 6th Australian Communications Theory Workshop 2005, Brisbane, Australia, 2/02/05. https://doi.org/10.1109/AUSCTW.2005.1624263

TY - GEN

T1 - Neural network prediction of radio propagation

AU - Qiu, Lei

AU - Jiang, Danchi

AU - Hanlen, Leif

PY - 2005

Y1 - 2005

N2 - Preliminary work for predicting signal distributions in a local area, using a feature-based neural network is presented. The neural network is trained by radio signal measurements at known positions. After appropriately setting the parameters of nodes of the neural network, a corresponding virtual propagation environment is built, which reasonably represents the actual environment. Radio signal strength distribution is predicted by the virtual environment. A new method for radio signal measurement is introduced which mitigates the effect of small scale fading when determining the fingerprint of a position.

AB - Preliminary work for predicting signal distributions in a local area, using a feature-based neural network is presented. The neural network is trained by radio signal measurements at known positions. After appropriately setting the parameters of nodes of the neural network, a corresponding virtual propagation environment is built, which reasonably represents the actual environment. Radio signal strength distribution is predicted by the virtual environment. A new method for radio signal measurement is introduced which mitigates the effect of small scale fading when determining the fingerprint of a position.

KW - IEEE 802.11b

KW - Neural networks

KW - Radio measurement

KW - Radio propagation

UR - http://www.scopus.com/inward/record.url?scp=33947128265&partnerID=8YFLogxK

U2 - 10.1109/AUSCTW.2005.1624263

DO - 10.1109/AUSCTW.2005.1624263

M3 - Conference contribution

SN - 0780390075

SN - 9780780390072

T3 - Proceedings 6th Australian Communications Theory Workshop 2005

SP - 272

EP - 277

BT - Proceedings 6th Australian Communications Theory Workshop 2005

T2 - 6th Australian Communications Theory Workshop 2005

Y2 - 2 February 2005 through 4 February 2005

ER -

Neural network prediction of radio propagation

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this