Hostname: page-component-cc8bf7c57-fxdwj Total loading time: 0 Render date: 2024-12-12T05:22:44.262Z Has data issue: false hasContentIssue false

Recurrent Neural Networks for Narrowband Signal Detection in the Time-Frequency Domain

Published online by Cambridge University Press:  19 September 2017

David Brodrick
Affiliation:
CSIRO Australia Telescope National Facility, Paul Wild Observatory, Locked Bag 194, Narrabri, NSW 2390, Australia, [email protected]
Douglas Taylor
Affiliation:
School of Computer Science and Software Engineering, Queensland University of Technology, GPO Box 2434, Brisbane, QLD 4001, Australia, [email protected]
Joachim Diederich
Affiliation:
School of Information Technology and Electrical Engineering, University of Queensland, St Lucia, QLD 4072, Australia, [email protected]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

A recurrent neural network was trained to detect the time-frequency domain signature of narrowband radio signals against a background of astronomical noise. The objective was to investigate the use of recurrent networks for signal detection in the Search for Extra-Terrestrial Intelligence, though the problem is closely analogous to the detection of some classes of Radio Frequency Interference in radio astronomy.

Type
Search for Extraterrestrial Intelligence (SETI)
Copyright
Copyright © Astronomical Society of the Pacific 2004 

References

Elman, J. 1990, Cognitive Science, 14, 179 Google Scholar
Sullivan, W., Werthimer, D., Bowyer, S., Cobb, D., Gedye, J., & Anderson, D. 1996, in Proceedings of the 5th International Conference on Bioastronomy Google Scholar
Taylor, D., Towsey, M., Finn, G., & Diederich, J. 1999, in Proceedings of the 6th International Conference on Bioastronomy Google Scholar