A Comparative Performance Analyses of Training Algorithms Employed in Artificial Neural Networks Based Modulation Recognition Systems

Büşra Ülgerli

A Comparative Performance Analyses of Training Algorithms Employed in Artificial Neural Networks Based Modulation Recognition Systems

Year 2016, Volume: 5 , 178 - 197, 07.11.2016

Abstract

Abstract – The performances of learning algorithms employed in artificial neural networks (ANNs) have been analyzed for classifying baseband signals that are subjected to additive white Gaussian noise (AWGN) and frequency selective Rayleigh fading channel in this paper. The high order cumulants of the received signals have been utilized in the ANN classifier. Different learning algorithms have been used in finding the optimal weight set which directly affects the performance of artificial neural networks. The performances of Levenberg Marquardt (LM) and scaled conjugate gradient (SCG) algorithm, the most widely employed learning algorithms, have been compared for training of artificial neural networks. Computer simulation results have demonstrated that the LM-ANN classifier can reach much better classification accuracy than the SCG-ANN recognizer in even low training steps.

Keywords

Modulation recognition, SCG-ANN; LM-ANN; High order cumul

References

Z. Çoban, Automatic Classification of Digital Modulation Methods in Communication Systems, MSc. Thesis, Hacettepe University, Department of Electrical and Electronics Engineering, Ankara, 2010.
E. E. Azzouz and A. K. Nandi, Automatic Modulation Recognition of Communication Signals, Kluwer Academic Publishers, 1996.
N. Ghani and R. Lamontagne, Neural Networks Applied to the Classification of Spectral Features for Automatic Modulation Recognition, Proceedings of MILCOM, pp. 1494–1498, 1993.
A. K. Nandi and E. E. Azzouz, Algorithms for Automatic Modulation Recognition of Communication Signals, IEEE Transastion on Communications, Vol. 46, pp. 431–436, 1998.
C. L. P. Sehier, Automatic Modulation Recognition with a Hierarchical Neural Network, Proceedings of MILCOM, pp. 111–115, 1993.
L. Mingquan, X. Xianci and L. Leming, Cyclic Spectral Features Based Modulation Recognition, Proceedings of ICCT, pp. 792–795, 1996.
A. Ebrahimzadeh and S. A. Seyedin, A New Method for Automatic Digital Signal Type Identification, Proceedings of CIS, 2005.
A. E. Shermeh and D. Movahedy, Automatic Identification of PSK2 and PSK4 Using SVM, Proceedings of ICIS, 2008.
L. Wang and Y. Ren, Recognition of Digital Modulation Signals Based on High Order Cumulants and Support Vector Machines, ISECS International Colloquium on Computing, Communication, Control and Management, pp. 271–274, 2009.
A. J. Jones, Genetic Algorithms and Their Applications to The Design of Neural Networks, Neural Computing & Applications, pp. 32–45, 1993.
B. Verma and R. Ghosh, A Novel Evolutionary Neural Learning Algorithm, Proceedings of the Congress of Evolutionary Computation, CEC 2002, Vol. 2, pp. 1884–1889, 2002.
A. Swami and B. M. Sadler, Hierarchical Digital Modul. Classification Using Cumulants, IEEE Transasctions on Communications Vol. 48, pp. 416-429, 2000.
K. S. Narendra and K. Parthasarathy, Identification and Control of Dynamical Systems Using Neural Networks, IEEE Transactions on Neural Networks, Vol. 1, No. 1, pp. 4-27, 1990.
Z. Yaqin, R. Guanghui, W. Xuexia, W. Zhilu, and G. Xuemai, Automatic Digital Modulation Recognition Using Artificial Neural Networks, IEEE International Conference on Neural Networks & Signal Processing, pp. 257–260, 2003.
C. Öztürk and D. Karaboğa, Hybrid Artificial Bee Colony Algorithm for Neural Network Training, IEEE Proceedings of the Congress of Evolutionary Computation, CEC 2011, pp. 84-88, 2011.
M. Ö. Efe, E. Abadoğlu and O. Kaynak, Analysis and Design of a Neural Network Assisted Nonlinear Controller for a Bioreactor, International Journal of Robust and Nonlinear Control, Vol. 9, No.11, pp. 799-815, 1999.
S. Haykin, Neural Networks: A Comprehensive Foundation, MacMillan Publishing Company, N.Y., 1994.
C. Ozturk, Training Artificial Neural Networks with Artificial Bee Colony Algorithm, Ph.D. Dissertation, Graduate School of Natural and Applied Sciences, Erciyes University, Kayseri, Turkey, 2011.
T. Ludermir, A. Yamazaki, and C. Zanchetin, An Optimization Methodology for Neural Network Weights and Architectures, IEEE Transactions on Neural Networks, Vol. 17, pp. 1452–1460, 2006.
C. Blum and K. Socha, Training Feed-Forward Neural Networks with Ant Colony Optimization: An Application to Pattern Classification, pp. 233–238, 2005.
A. Iversen, N. K. Taylor and K. E. Brown, Classification and Verification Through the Combination of the Multi-Layer Perceptron and Auto-Association Neural Networks, Proceedings of IEEE International Joint Conference on Neural Networks, Vol. 2, pp. 1166-1171, 2005.
S. Taira, Automatic Classification of QAM Signals by Neural Networks, ICASSP 2001, Vol. 2, pp. 1309–1312, 2001.
X. Yao, Evolutionary Artificial Neural Networks, International Journal of Neural Systems, Vol. 4, pp. 203-222, 1993.
B. Ülgerli and G. Yücel, A Comparative Performance Analyses of Training Algorithms Employed in Artificial Neural Networks and Particle Swarm Optimization Based Modulation Recognition Systems, Electronic Design and Aplication Thesis, Nuh Naci Yazgan University, Department of Electrical and Electronics Engineering, Kayseri, Turkey, January – 2016.
B. Ülgerli, G. Yücel, A. Altun, E. Öksüz and A. Özen, A Comparative Performance Analyses of Training Algorithms Employed in Artificial Neural Networks Based Modulation Recognition Systems, Electrical-Electronics and Computer Symposium, EEB2016, pp. 206-215, Gaziosmanpaşa University, Tokat, Turkey, 11-13 May, 2016.
J. G. Proakis, Digital Communications, Fourth Edition, Mc Graw Hill International Editions, 2001.