A Novel Analog Modulation Classification: Discrete Wavelet Transform-Extreme Learning Machine (DWT-ELM)

Year 2021, Volume: 10 Issue: 2, 492 - 506, 07.06.2021

Mehmet Ustundag

https://doi.org/10.17798/bitlisfen.852909

Abstract

The aim of this study is to propose a method using discrete wavelet transform and extreme learning machine (DWT-ELM) in classification of communication signals. Six types of analog modulated signals as “AM”, “DSB”, “USB”, “LSB”, “FM” and “PM” are used for classification and analog modulated signal dataset consists of 1920 signals. These signals are also added white noise. Feature extraction is performed using different DWT filters. The feature vector obtained from DWT is used in classification. ELM is preferred due to its advantages over conventional back-propagation based classification. The feature vector is fed by the inputs of the ELM. The performance of the proposed method is evaluated for different types of DWT filters. In addition, compared results with similar study are presented to be able to determine the success of the proposed method.

Keywords

DWT-ELM, ELM classification, Wavelet Transform, Analog modulated signals

A Novel Analog Modulation Classification: Discrete Wavelet Transform-Extreme Learning Machine (DWT-ELM)

Abstract

Bu çalışma, analog modüle edilmiş iletişim sinyallerinin sınıflandırılması için ayrık dalgacık dönüşümü - aşırı öğrenme makinesine (ADD-AÖM) dayalı yeni bir yöntem önermektedir. Sınıflandırma için AM, DSB, USB, LSB, FM ve PM olmak üzere altı tip analog modüle edilmiş sinyal kullanılır ve analog modüle edilmiş sinyal veri seti 1920 sinyalden oluşur. Bu sinyallere ayrıca beyaz gürültü eklenir. Özellik çıkarma işlemi, farklı ADD filtreleri kullanılarak gerçekleştirilir. ADD'den elde edilen öznitelik vektörü sınıflandırmada kullanılır. AÖM, geleneksel geri yayılmaya dayalı sınıflandırmaya göre avantajları nedeniyle tercih edilmektedir. Özellik vektörü, AÖM sınıflandırıcısının girişine beslenir. Önerilen yöntemin performansı, farklı ADD filtreleri için değerlendirilir. Ayrıca, önerilen yöntemin performansını değerlendirmek için benzer çalışma ile karşılaştırılan sonuçlar sunulmuştur

Keywords

ADD-AÖM, AÖM sınıflandırma, Dalgacık Dönüşümü, Modüle edilmiş analog sinyaller

References

• Fabrizi P.M., Lopes L.B., Lockhart G.B. 1986. Receiver recognition of analogue modulation types. In: IERE conference on radio receiver and associated systems, 1-4 July, University of Bangor, Wales, 135-140.
• Chan Y., Gadbois L., Yansouni P. 1985. Identification of the modulation type of a signal. In: ICASSP ’85. IEEE International Conference on Acoustics, Speech, and Signal Processing, 26-29 April, Tampa, FL, USA, 10: 838-841.
• Nagy P.A.J. 1994. Analysis of a method for classification of analogue modulated radio signals. in In: European association for signal processing VII conference, Edinburgh, Scotland, 1015-1018.
• Jovanic S.D., Doroslovacki M.I., Dragosevic M.V. 1994. Recognition of low modulation index AM signals in additive Gaussian noise, in Recognition of low modulation index AM signals in additive Gaussian noise. In European Association for Signal Processing V Conference, Edinburgh, Scotland, 1923-1926.
• Al-Jalili Y.O. 1995. Identification algorithm of upper sideband and lower sideband SSB signals. Signal Processing, 42 (2): 207-213.
• Azzouz E.E., Nandi A.K. 1996. Procedure for automatic recognition of analogue and digital modulations. IEE Proc.-Commun., 143 (5): 259.
• Wong M.L.D., Nandi A.K. 2004. Automatic digital modulation recognition using artificial neural network and genetic algorithm. Signal Processing, 84 (2): 351-365.
• Kavalov D., Kalinin V. 2001. Improved noise characteristics of a SAW artificial neural network RF signal processor for modulation recognition. In: IEEE Ultrasonics Symposium. Proceedings. An International Symposium (Cat. No.01CH37263), 7-10 October, Atlanta, GA, USA, 1: 19-22.
• Kremer S.C., Shiels J. 1997. A testbed for automatic modulation recognition using artificial neural networks. In: CCECE ’97, Canadian Conference on Electrical and Computer Engineering. Engineering Innovation: Voyage of Discovery. Conference Proceedings, 1: 67-70.
• Nandi A.K., Azzouz E.E. 1998. Algorithms for automatic modulation recognition of communication signals. IEEE Trans. Commun., 46 (4): 431-436.
• Avci E. 2007. Performance comparison of wavelet families for analog modulation classification using expert discrete wavelet neural network system. Expert Syst. Appl., 33 (1): 23-35.
• Zhang J., Walter G.G., Miao Y., Wayne L.W.N. 1995. Wavelet neural networks for function learning. IEEE Trans. Signal Process., 43 (6): 1485-1497.
• Kociołek M., Materka A., Strzelecki M., Szczypiński P. 2001. Discrete Wavelet Transform – Derived Features for Digital Image Texture Analysis. Proc. of Interational Conference on Signals and Electronic Systems, 18-21 September, Lodz, Poland, 18-21.
• Avci E., Turkoglu I., Poyraz M. 2005. Intelligent target recognition based on wavelet packet neural network. Expert Syst. Appl., 29 (1): 175-182.
• Thuillard M. 2000. A Review of Wavelet Networks, Wavenets, Fuzzy Wavenets and their Applications. Advances in Computational Intelligence and Learning, 43-60.
• Wesfreid E., Wickerhauser M.V. 1993. Adapted local trigonometric transforms and speech processing. IEEE Trans. Signal Process., 41 (12): 3596-3600.
• Huang G.B., Wang D. H., Lan Y. 2011. Extreme learning machines: a survey. Int. J. Mach. Learn. Cybern., 2 (2): 107-122.
• Huang G.B., Zhou H., Ding X., Zhang R. 2012. Extreme Learning Machine for Regression and Multiclass Classification. IEEE Trans. Syst. Man, Cybern. Part B, 42 (2): 513-529.
• Bengio Y. 2009. Learning Deep Architectures for AI. Found. Trends® Mach. Learn., 2 (1): 1-127.
• Daliri M.R. 2012. A hybrid automatic system for the diagnosis of lung cancer based on genetic algorithm and fuzzy extreme learning machines. J. Med. Syst., 36 (2): 1001-1005.
• Qu Y., Shang C., Wu W., Shen Q. 2011. Evolutionary fuzzy extreme learning machine for mammographic risk analysis. Int. J. Fuzzy Syst., 13 (4): 282-291.
• Xu Y., Dong Z.Y., Meng K., Wong K.P., Zhang R. 2013. Short-term load forecasting of Australian National Electricity Market by an ensemble model of extreme learning machine. IET Gener. Transm. Distrib., 7 (4): 391-397.
• Avci E., Coteli R. 2012. A new automatic target recognition system based on wavelet extreme learning machine. Expert Syst. Appl., 39 (16): 12340-12348.
• Cao J., Lin Z., Huang G. 2010. Composite function wavelet neural networks with extreme learning machine. Neurocomputing, 73 (7): 1405-1416.
• Malathi V., Marimuthu N.S., Baskar S. 2010. Intelligent approaches using support vector machine and extreme learning machine for transmission line protection. Neurocomputing, 73 (10): 2160-2167.
• Malathi V., Marimuthu N.S., Baskar S., Ramar K. 2011. Application of extreme learning machine for series compensated transmission line protection. Eng. Appl. Artif. Intell., 24 (5): 880-887.
• Banerjee K.S. 1973. Generalized Inverse of Matrices and Its Applications. Technometrics, 15 (1): 197-197.
• Schmidt W.F., Kraaijveld M.A., Duin R.P.W. 1992. Feed Forward Neural Networks with Random Weights. In International Conference on Pattern Recognition, August, 1-4.
• White H. 1989. An additional hidden unit test for neglected nonlinearity in multilayer feedforward networks. International Joint Conference on Neural Networks, 2: 451-455.
• White H. 2006. Approximate Nonlinear Forecasting Methods. Handbook of Economic Forecasting, 459-512.
• Azzouz E.E., Nandi A.K. 1997. Automatic modulation recognition-II. J. Franklin Inst., 334 (2): 275-305.
• Wu Z., Ren G., Wang X., Zhao Y. 2004. Automatic Digital Modulation Recognition Using Wavelet Transform and Neural Networks. Springer, Berlin, Heidelberg, 936-940.