Abstract
Data fusion (integration) techniques are combined with MultiLayer Feedforward (backpropagation) neural networks in order to improve the inversion —extraction of the key describing parameters — of oblique-incidence ionograms (plots of apparent height of reflection versus transmission frequency). Two separate investigations were undertaken: first, the incorporation of vertical ionogram data to improve inversion; and secondly, the fusion of ionogram data gathered from a 2D array of ionosondes (the ground-based radio frequency transmitters). With the former, the average percentage errors obtained by incorporating data fusion dropped by a factor of five when compared with single ionogram inversion. Moreover, gradients of ionospheric parameters (critical frequency, layer height and thickness) were also obtained. In the case of the latter, the error rate dropped by a similar factor, and by even more when vertical ionograms were incorporated. Better results were forthcoming when a hierarchical network was used to invert the ionograms prior to fusion, compared with directly fusing the ionogram array data.
Similar content being viewed by others
References
Ratcliffe J. An Introduction to the Ionosphere and Magnetosphere. Cambridge University Press, 1972.
Lou RC, Kay MG. Data fusion and sensor integration: state-of-the-art 1990s. In MA Abidi and RC Gonzalez (eds.), Data Fusion in Robotics and Machine Intelligence. Academic Press, 1992.
Krishnapuram R, Lee J. Fuzzy-set-based hierarchical networks for information fusion in computer vision. Neural Networks 1992; 5: 335–350.
Huntsberger TL. Data fusion: a neural networks implementation. In MA Abidi and RC Gonzalez (eds.), Data Fusion in Robotics and Machine Intelligence. Academic Press, 1992.
Whittington G, Spracklen T. The application of a neural network model to sensor data fusion. SPIE Applic Artif Neural Networks 1990; 1294: 276–283.
DSTO Department of Administrative Services. IPS Radio and Space Services, User Training Manual, 1995.
Coleman C. Vertical software. High Frequency Radar Division, Defence Science & Technology Organization, Australia, 1995.
Coleman C. Jornoix software. High Frequency Radar Division, Defence Science & Technology Organization, Australia, 1995.
Castelaz PF. Neural networks in defence applications. Proc IEEE Int Conf Neural Networks, 1988: 473–480.
NeuralWare Inc. NeuralWorks Professional II Plus User Guide, 1993.
Zell A. et al. Stuttgart Neural Network Simulator User Manual V 4.1. Institute for Parallel and Distributed High Performance Systems, University of Stuttgart, Germany, 1995. [ftp.informatik.uni-stuttgart.de]
Hagenbuchner M, Fulcher J. Noise removal in ionograms using Artificial Neural Networks. Neural Comput Applic, 1997: 6; 166–172.
Fisher R, Fulcher J, Richards S, Hagenbuchner M, Coleman C. The fusion of oblique-incidence ionograms gathered from multiple collection sites. Proc 1st Australian Data Fusion Symposium — ADFS'96, Adelaide, November 1996, pp. 125–130.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Fisher, R., Fulcher, J. Improving the inversion of ionograms by combining neural network and data fusion techniques. Neural Comput & Applic 7, 3–16 (1998). https://doi.org/10.1007/BF01413705
Issue Date:
DOI: https://doi.org/10.1007/BF01413705