Abstract
Automatic classification of modulation type in detected signals is an intermediate step between channel equalization and signal demodulation. This subsystem is an essential task for an intelligent receiver in various civil and military applications. Most of automatic modulation classification algorithms have been evaluated in SNR aware case which is obviously an unrealistic case. In this paper, we propose a semi-supervised online passive-aggressive classifier that uses a self-training approach for additive white Gaussian noise channels with unknown or variable signal to noise ratios to classify the modulated signals. An appropriate set of selected feature helps the general system work for a set of initial samples of each class. In the adaptation phase, unlabeled high confidence samples are used to adapt to system. An appropriate confidence measure is proposed to collect confident samples. Simulation results shows that adding unlabeled input samples to the training set improve the generalization capacity of the presented classifier in the target SNR. In addition to online characteristics of the algorithm that make the approach suitable for cognitive radio systems, this algorithm converges with a few number of signal samples. Simulation results in SNR unaware conditions show that employing this learning method results in high classification rate close to SNR aware conditions.
Similar content being viewed by others
References
Dobre, O. A., Abdi, A., Bar-Ness, Y., & Su, W. (2007). Survey of automatic modulation classification techniques: Classical approaches and new trends. IET Communications, 1(2), 137–156.
Wu, H. C., Saquib, M., & Yun, Z. (2008). Novel automatic modulation classification using cumulant features for communications via multipath channels. IEEE Transactions Wireless Communications, 7(8), 3089–3105.
Prakasam, P., & Madheswaran, M. (2009). Intelligent decision making system for digital modulation scheme classification in software radio using wavelet transform and higher order statistical moments. Wireless Personal Communications, 50(4), 509–528.
Hsue, S. Z., & Soliman, S. S. (1990). Automatic modulation classification using zero crossing. IEE Proceedings for Radar and Signal Processing, 137(6), 459–464.
Mobasseri, B. G. (2000). Digital modulation classification using constellation shape. Signal Processing, 80(2), 251–277.
Azzouz, E. E., & Nandi, A. K. (1995). Automatic identification of digital modulation types. Signal Processing, 47(1), 55–69.
Nandi, A. K., & Azzouz, E. E. (1998). Algorithms for automatic modulation recognition of communication signals. IEEE Transactions on Communications, 46(4), 431–436.
Swami, A., & Sadler, B. M. (2000). Hierarchical digital modulation classification using cumulants. IEEE Transactions on Communications, 48(3), 416–429.
Zhao, Y., Ren, G., Wang, X., Wu, Z., & Gu, X. (2003). Automatic digital modulation recognition using artificial neural networks. In: Proceedings of ICNNSP, pp. 257–260.
Wang, F., & Wang, X. (2010). Fast and robust modulation classification via Kolmogorov–Smirnov Test. IEEE Transactions on Communications, 58(8), 2324–2332.
Zhao, C., & Yang, W. (2013). Modulation Recognition of MFSK signals based on multifractal spectrum. Wireless Personal Communications, 72, 1903–1914.
Zhu, Z., Aslam, M. W., & Nandi, A. K. (2013). Genetic algorithm optimized distribution sampling test for M-QAM modulation classification. Signal Processing, 94, 264–277.
Zadeh, A. E. (2010). Automatic recognition of radio signals using a hybrid intelligent technique. Expert Systems with Applications, 37(8), 5803–5812.
Sengur, A. (2009). Multiclass least-squares support vector machines for analog modulation classification. Expert Systems with Applications, 36(3), 6681–6685.
Dulek, B., Ozdemir, O., Varshney, P. K., & Su, W. (2014). A novel approach to dictionary construction for automatic modulation classification. Journal of the Franklin Institute, 351(5), 2991–3012.
Adankon, M. M., & Cheriet, M. (2011). Help-training for semi-supervised support vector machines. Pattern Recognition, 44(1), 2220–2230.
Zhu, X. (2008). Semi-supervised learning literature survey, Technical Report 1530. Computer Sciences, University of Wisconsin-Madison.
Zhu, X., & Goldberg, A. B. (2009). Introduction to semi-supervised learning. Morgan and Claypool Publishers.
Chapelle, O., Scholkopf, B., & Zien, A. (2006). Semi-supervised learning. Cambridge, MA: MIT Press.
Seeger, M. (2001). Learning with labeled and unlabeled data. Technical Report, Institute for Adaptive and neural Computation, University of Edinburgh.
Hosseinzadeh, H., Razzazi, F., & Haghbin, A. (2012). An Adaptable Architecture for Blind Modulations Classification in Variable SNR Environments. In: Proceedings of IEEE International Conference on Intelligent systems, 1, pp. 164–169.
Li, Y., & Long, P. M. (2002). The relaxed online maximum margin algorithm. Machine Learning, 46, 361–387.
Gentile, C. (2001). A new approximate maximal margin classification algorithm. Journal of Machine Learning Research, 2, 213–242.
Kivinen, J., Smola, A. J., & Williamson, R. C. (2002). Online learning with kernels. IEEE Transactions Signal Processing, 52, 2165–2176.
Orabona, F., Castellini, C., Caputo, B., Jie, L., & Sandini, (2010). On-line independent support vector machines. Pattern Recognition, 43, 1402–1412.
Crammer, K., Dekel, O., Keshet, J., Shalev-shwartz, S., & Singer, Y. (2006). Online passive-aggressive algorithms. Journal of Machine Learning Research, 7, 551–585.
Chang, C.C., Lee, Y.J., & Pao, H.K. (2010). A Passive-Aggressive Algorithm for Semi-supervised Learning. In: Proceedings of International Conference on Technologies and Applications of Artificial Intelligence, pp. 335–341.
Schapire, R. E. & Singer, Y. (1998). Improved boosting algorithms using confidence-rated predictions. In: Proceedings of the Eleventh Annual Conference on Computational Learning Theory, pp. 80–91.
Crammer, K., & Singer, Y. (2003). A new family of online algorithms for category ranking. Journal of Machine Learning Research, 3, 1025–1058.
Maulic, U., & Chakraborty, D. (2011). A self-trained ensemble with semisupervised SVM: An application to pixel classification of remote sensing imagery. Pattern Recognition, 24, 615–623.
Proakis, J. G. (2001). Digital Communications. New York: McGraw-Hill.
Burges, C. C. (1998). A tutorial on support vector machines for pattern recognition. In: Proceedings of International Conference on Data Mining and Knowledge Discovery, 2, pp. 121–167.
Lopatka, J., & Macrej, P. (2000). Automatic modulation classification using statistical moments and a fuzzy classifier. In: Proceedings of International Conference on Signal Processing (ICSP’00), pp. 1500–1506.
Chandrashekar, G., & Sahin, F. (2014). A survey on feature selection methods. Computers and Electrical Engineering, 40(1), 16–28.
Ebrahimzade, A. (2012). A novel method for automatic modulation recognition. Applied Soft Computing, 12, 453–461.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hosseinzadeh, H., Razzazi, F. & Haghbin, A. A Self Training Approach to Automatic Modulation Classification Based on Semi-supervised Online Passive Aggressive Algorithm. Wireless Pers Commun 82, 1303–1319 (2015). https://doi.org/10.1007/s11277-015-2284-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11277-015-2284-7