Signal Identification using a new high efficient technique

Automatic signal type identification (ASTI) is an important topic for both the civilian and military domains. Most of the proposed identifiers can only recognize a few types of digital signal and usually need high levels of SNRs. This paper presents a new high efficient technique that includes a variety of digital signal types. In this technique, a combination of higher order moments and higher order cumulants (up to eighth) are proposed as the effective features. A hierarchical support vector machine based structure is proposed as the classifier. In order to improve the performance of identifier, a genetic algorithm is used for parameters selection of the classifier. Simulation results show that the proposed technique is able to identify the different types of digital signal (e.g. QAM128, ASK8, and V29) with high accuracy even at low SNRs.

[1]  Elsayed Elsayed Azzouz,et al.  Algorithms for automatic modulation recognition of communication signals , 1998, IEEE Trans. Commun..

[2]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[3]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[4]  R. Mammone,et al.  A new method of modulation classification for digitally modulated signals , 1992, MILCOM 92 Conference Record.

[5]  Elsayed Elsayed Azzouz,et al.  Automatic identification of digital modulation types , 1995, Signal Process..

[6]  Bijan G. Mobasseri,et al.  Digital modulation classification using constellation shape , 2000, Signal Process..

[7]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 2000, Springer Berlin Heidelberg.

[8]  J. Sills.  Maximum-likelihood modulation classification for PSK/QAM , 1999, MILCOM 1999. IEEE Military Communications. Conference Proceedings (Cat. No.99CH36341).

[9]  Bernhard Schölkopf,et al.  Extracting Support Data for a Given Task , 1995, KDD.

[10]  J. Lopatka,et al.  Automatic modulation classification using statistical moments and a fuzzy classifier , 2000, WCC 2000 - ICSP 2000. 2000 5th International Conference on Signal Processing Proceedings. 16th World Computer Congress 2000.

[11]  Achilleas Anastasopoulos,et al.  Likelihood ratio tests for modulation classification , 2000, MILCOM 2000 Proceedings. 21st Century Military Communications. Architectures and Technologies for Information Superiority (Cat. No.00CH37155).

[12]  Brian M. Sadler,et al.  Hierarchical digital modulation classification using cumulants , 2000, IEEE Trans. Commun..

[13]  C. Louis,et al.  Automatic modulation recognition with a hierarchical neural network , 1994, Proceedings of MILCOM '94.

[14]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1996, Springer Berlin Heidelberg.

[15]  Alfred O. Hero,et al.  Digital modulation classification using power moment matrices , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[16]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[17]  Hai-Bing Guan,et al.  Modulation classification based on spectrogram , 2004, Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826).

[18]  Christophe Le Martret,et al.  A general maximum likelihood classifier for modulation classification , 1998, 9th European Signal Processing Conference (EUSIPCO 1998).

[19]  Jerry M. Mendel,et al.  Maximum-likelihood classification for digital amplitude-phase modulations , 2000, IEEE Trans. Commun..

[20]  John G. Proakis,et al.  Digital Communications , 1983 .

[21]  P. McCullagh.  Tensor Methods in Statistics , 1987 .

[22]  Lu Mingquan,et al.  Cyclic spectral features based modulation recognition , 1996, Proceedings of International Conference on Communication Technology. ICCT '96.