Neural networks applied to the classification of spectral features for automatic modulation recognition
作者： N. Ghani , R. Lamontagne
DOI: 10.1109/MILCOM.1993.408536
关键词:
摘要: The use of back-error propagation neural networks for the automatic modulation recognition (AMR) an intercepted signal is demonstrated. In all, ten types are considered and a variety spectral preprocessors investigated feature extraction. For given training test sets, Welch periodogram found to give best results. classification, experimental results show that match even outdo performance conventional k-nearest neighbor (k-NN) classifier this preprocessor. Moreover, optimization selected demonstrated using optimal brain damage (OBD) pruning technique. >
sci-hub.se 参考文章(7)
W.A. Gardner, Exploitation of spectral redundancy in cyclostationary signals IEEE Signal Processing Magazine. ,vol. 8, pp. 14- 36 ,(1991) , 10.1109/79.81007
P. Welch, The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms IEEE Transactions on Audio and Electroacoustics. ,vol. 15, pp. 70- 73 ,(1967) , 10.1109/TAU.1967.1161901
Yann LeCun, John Denker, Sara Solla, None, Optimal Brain Damage neural information processing systems. ,vol. 2, pp. 598- 605 ,(1989)
M. Raghuveer, C. Nikias, Bispectrum estimation: A parametric approach IEEE Transactions on Acoustics, Speech, and Signal Processing. ,vol. 33, pp. 1213- 1230 ,(1985) , 10.1109/TASSP.1985.1164679
Keinosuke Fukunaga, Introduction to Statistical Pattern Recognition ,(1972)
Eric B. Baum, David Haussler, What Size Net Gives Valid Generalization neural information processing systems. ,vol. 1, pp. 81- 90 ,(1988) , 10.1162/NECO.1989.1.1.151
René Lamontagne, Performance of the Backpropagation Neural Network for Recognition of Radio Signals Using Time-Domain Features ICANN ’93. pp. 986- 989 ,(1993) , 10.1007/978-1-4471-2063-6_289