Neural Computing and Applications

, Volume 31, Issue 10, pp 6141–6149 | Cite as

Classification of M-QAM and M-PSK signals using genetic programming (GP)

  • Asad Hussain
  • M. F. Sohail
  • Sheraz Alam
  • Sajjad A. GhauriEmail author
  • I. M. Qureshi
Original Article


With the popularity of software-defined radio and cognitive radio-technologies in wireless communication, radio frequency devices have to adapt to changing conditions and adjust its transmitting parameters such as transmitting power, operating frequency, and modulation schemes. Thus, automatic modulation classification becomes an essential feature for such scenarios where the receiver has a little or no knowledge about the transmitter parameters. This paper presents kth nearest neighbor (KNN)-based classification of M-QAM and M-PSK modulation schemes using higher-order cumulants as input features set. Genetic programming is used to enhance the performance of the KNN classifier by creating super features from the data set. Simulation result shows improved accuracy at comparatively lower signal-to-noise ratio for all the considered modulations.


Genetic Programming Higher-order cumulants K-nearest neighbor M-QAM M-PSK 


Compliance with ethical standards

Conflict of interest

The authors declare that there is no conflict of interests regarding the publication of this paper.


  1. 1.
    Su W, Xu JL, Zhou M (2008) Real-time modulation classification based on maximum likelihood. IEEE Commun Lett 12(11):801–803CrossRefGoogle Scholar
  2. 2.
    Poli R, Langdon WB, McPhee NF (2008) A field guide to Genetic Programming. Published via
  3. 3.
    Koza JR (1992) Genetic Programming. MIT Press, CambridgezbMATHGoogle Scholar
  4. 4.
    Aslam MW, Zhu Z, Nandi AK (2012) Automatic modulation classification using combination of genetic programming and KNN. IEEE Trans Wirel Commun 11(8):2742–2750Google Scholar
  5. 5.
    Xu J, Su W, Zhou M (2011) Likelihood-ratio approaches to automatic modulation classification. IEEE Trans Syst Man Cybern 41(4):455–469CrossRefGoogle Scholar
  6. 6.
    Dobre O, Abdi A, Bar-Ness Y, Su W (2007) Survey of automatic modulation classification techniques: classical approaches and new trends’. IET Commun 1(2):137–156CrossRefGoogle Scholar
  7. 7.
    Su W (2013) Feature space analysis of modulation classification using very high-order statistics. IEEE Commun Lett 17(9):1688–1691CrossRefGoogle Scholar
  8. 8.
    Hameed F, Dobre OA, Popescu DC (2009) On the likelihood-based approach to modulation classification. IEEE Trans Wirel Commun 8(12):5884–5892CrossRefGoogle Scholar
  9. 9.
    Azzouz EE, Nandi AK (1998) Algorithms for automatic modulation recognition of communication signals’. IEEE Trans Commun 46(4):431–436CrossRefGoogle Scholar
  10. 10.
    Wang F, Wang X (2010) Fast and robust modulation classification via Kolmogorov–Smirnov test. IEEE Trans Commun 58(8):2324–2332CrossRefGoogle Scholar
  11. 11.
    Ho KC, Prokopiw W, Chan YT (2000) Modulation identification of digital signals by the wavelet transform. IEE Proc Radar Sonar Navig 147(4):169–176CrossRefGoogle Scholar
  12. 12.
    Hong, L, Ho K (1999) Identification of digital modulation types using the wavelet transform. In: Proceedings of 1999 IEEE military communications conferenceGoogle Scholar
  13. 13.
    Zhao F, Hu Y, Hao S (2008) Classification using wavelet packet decomposition and support vector machine for digital modulations. J Syst Eng Electron 19(5):914–918CrossRefGoogle Scholar
  14. 14.
    Li P, Wang F, Wang Z (2006) Algorithm for modulation recognition based on high-order cumulants and subspace decomposition. In: Proceedings of 2006 eighth international conference on signal processingGoogle Scholar
  15. 15.
    Mirarab M, Sobhani, M (2007): ‘Robust modulation classification for PSK/QAM/ASK using higher-order cumulants. In: Proceedings of 2007 sixth international conference on information, communications and signal processingGoogle Scholar
  16. 16.
    Shen L, Li S, Song S, Chen F (2006) Automatic modulation classification of MPSK signals using high order cumulants. In: Proceedings of 2006 eighth international conference on signal processingGoogle Scholar
  17. 17.
    An N, Li B, Huang M (2010) Modulation classification of higher order MQAM signals using mixed-order moments and Fisher criterion. In: Proceedings of 2010 the second international conference on computer and automation engineeringGoogle Scholar
  18. 18.
    Aslam MW, Zhu Z, Nandi AK (2010) Automatic digital modulation classification using genetic programming with K-nearest neighbor. In Proceedings 2010 military communications conference, pp 512–517Google Scholar
  19. 19.
    Shan Z, Xin Z, Ying W (2010) Improved modulation classification of MPSK signals based on high order cumulants. In: Proceedings of 2010 2nd international conference on future computer and communicationGoogle Scholar
  20. 20.
    Zhang M, Ciesielski VB, Andrea P (2003) A domain-independent window approach to multiclass object detection using genetic programming. EURASIP J Appl Signal Process 8:841–859zbMATHGoogle Scholar
  21. 21.
    Zhang L, Jack L B, Nandi AK (2005) Extending genetic programming for multi-class classification by combining k-nearest neighbor. In Proceedings IEEE international conference on acoustics, speech, and signal processing pp 349–352Google Scholar
  22. 22.
    Hazar MA, Odabasioglu N, Ensari T, Kavurucu T, Sayan O F (2017) Performance analysis and improvement of machine learning algorithms for automatic modulation recognition over Rayleigh fading channels. Neural Comput Appl, Springer, pp 1–10Google Scholar
  23. 23.
    Vladimir DO, Miroslav LD (2009) Automatic modulation classification algorithm using higher-order cumulants under real-world channel conditions. IEEE Commun Lett 13(12):917–919CrossRefGoogle Scholar
  24. 24.
    Subasi A, Ismail Gursoy M (2010) EEG signal classification using PCA, ICA, LDA and support vector machines. Expert Syst Appl 37(12):8659–8666CrossRefGoogle Scholar
  25. 25.
    Zaerin M, Seyfe B (2012) Multiuser modulation classification based on cumulants in additive white Gaussian noise channel. IET Signal Process 6(9):815–823CrossRefGoogle Scholar
  26. 26.
    Liu J, Luo Q (2012) A novel modulation classification algorithm based on daubechies wavelet and fractional In: Fourier transform in cognitive radio IEEE 14th international conference on communication technology, pp 115–120Google Scholar
  27. 27.
    Mühlhaus MS, Öner M, Dobre OA, Jondral FK (2013) A low complexity modulation classification algorithm for MIMO systems. IEEE Commun Lett 17(10):1881–1884CrossRefGoogle Scholar
  28. 28.
    Ghauri SA, Qureshi IM, Malik AN, Cheema TA (2014) Automatic digital modulation classification technique using higher order cumulants on faded channel. J Basic Appl Sci Res 4(3):1–12Google Scholar
  29. 29.
    Ghauri SA, Qureshi IM, Malik AN, Cheema TA (2014) A novel modulation classification approach using Gabor filter network. Sci World J (TSWJ) pp. 1–14Google Scholar
  30. 30.
    Ghauri SA, Qureshi IM, Basir S, Hassam (2014) modulation classification using spectral features on fading channels. Sci Int 27:147–153Google Scholar
  31. 31.
    Ghauri SA, Qureshi IM, Shah I, Khan N (2014) Modulation classification using cyclo-stationary features on fading channels. Res J Appl Sci Eng Technol (RJASET) 7(24):5331–5339CrossRefGoogle Scholar
  32. 32.
    Amuru SD, De-Silva RCM (2015) A blind preprocessor for modulation classification applications in frequency-selective non-Gaussian channels. IEEE Trans Commun 63(1):156–169Google Scholar
  33. 33.
    Ghauri SA, Qureshi IM (2015) M-PAM signals classification using modified Gabor filter network. Math Probl Eng 2015:1–10MathSciNetCrossRefGoogle Scholar
  34. 34.
    Chang DC, Shih PK (2015) Cumulants-based modulation classification technique in multipath fading channels. IET Commun 9(6):828–835CrossRefGoogle Scholar
  35. 35.
    Hussain A, Ghauri SA, Qureshi IM, Sohail MF, Khan SA (2016) KNN based classification of digital modulated signals. Int Islam Univ Malays Eng J (IIUMEJ) 17:71–82Google Scholar
  36. 36.
    Zhu Z, Aslam MW, Nandi AK (2010) Augmented genetic programming for automatic digital modulation classification. In: Proceedings 2010 IEEE international workshop on machine learning for signal processing, pp 391–396Google Scholar

Copyright information

© The Natural Computing Applications Forum 2018

Authors and Affiliations

  • Asad Hussain
    • 1
  • M. F. Sohail
    • 1
  • Sheraz Alam
    • 1
    • 2
  • Sajjad A. Ghauri
    • 4
    Email author
  • I. M. Qureshi
    • 3
  1. 1.National University of Modern LanguagesIslamabadPakistan
  2. 2.International Islamic UniversityIslamabadPakistan
  3. 3.AIR UniversityIslamabadPakistan
  4. 4.Department of electrical engineeringISRA UniversityIslamabadPakistan

Personalised recommendations