Title :
Neural network prediction of HF ionospheric propagation loss
Author :
Chu, A.M. ; Conn, D.R.
Author_Institution :
Dept. of Electr. & Comput. Eng., McMaster Univ., Hamilton, Ont., Canada
fDate :
9/30/1999 12:00:00 AM
Abstract :
A generalised regression neural network is used to predict losses inherent in ionospheric radiowave propagation. Network inputs consist of sun declination, time of day, radio flux, geomagnetic A-index and X-ray flux. Simulations for a 400 km path demonstrate a 2.5 dB error between network predictions and actual measured values, representing a 46% reduction in errors compared to the linear regression method
Keywords :
HF radio propagation; ionospheric electromagnetic wave propagation; losses; neural nets; telecommunication computing; 400 km; HF ionospheric propagation loss; X-ray flux; generalised regression neural network; geomagnetic A-index; ionospheric radiowave propagation; neural network prediction; radio flux; sun declination; time of day;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19991206
