Unsupervised Learning for Robust Signal Classification

Abstract:

Cognitive Radio Networks (CRNs) have been proposed to increase the efficiency of channel utilization; presently the demand for wireless bandwidth is increased. Cognitive Radio Network can enable the sharing of channels among unlicensed and licensed users on a non-interference basis. An unlicensed user (i.e., secondary user) should monitor for the presence of a licensed user (i.e., primary user) to avoid interfering with a primary user. However to get more gain, an attacker also called self-ish secondary user may copy a primary user’s signal to cheat other secondary users. Therefore a primary user detection method is needed to detect the difference between a primary user’s signal and secondary user’s signal. In this paper, unsupervised learning methods such as K-means and SOM techniques are used to classify the signals and also measure the performance parameters such as throughput, end-to-end delay, energy consumption, packet delivery ratio and collision rate of the channel.

• Periodical: Applied Mechanics and Materials (Volume 573)
• Pages: 429-434
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.573.429
• Online since: June 2014
• Authors: A. Uma Maheswari*, K. Latha
• Keywords: Cognitive Radio Network, Dynamic Spectrum Access, IEEE 802, QAM, Signal Classification, TV White Space, VSB

References

[1] T. Charles Clancy, A. Khawar and Timothy R. Newman, Robust Signal Classification Using Unsupervised Learning, IEEE Transactions on wiresless communications., vol. 10, No. 4, pp.1289-1299, April (2011).

DOI: 10.1109/twc.2011.030311.101137

[2] T. Charles Clancy, Timothy R. Newman, Robust Signal classification using unsupervised learning, April (2009).

[3] T. Newman and T. Clancy, Security threats to cognitive radio signal classifiers, , in Vitgina Tech Wireless Personal Commun Symp., June (2009).

[4] A. Khawar and T. Clancy, Signal classifier using self-organising maps: performance and robustness, in SDR Forum Technical Conf., Dec (2009).

[5] T. Clancy and A. Khawar, Security threats to cognitive radio radio signal classifiers, in International Conf. Cognitive Radio Oriented wireless Netw. Commun., June (2009).

DOI: 10.1109/crowncom.2009.5189050

[6] A. Fehske, J. Gaeddert and J. Reed, A new approach to signal classification using signal correlation and neural networks, in New Frontiers Dynamic Spectrum access Netw., Nov (2005).

DOI: 10.1109/dyspan.2005.1542629

[7] T. Yucek and H. Arslan. A survey of spectrum sensing algorithms for cognitive radio applications, IEEE Commun Surveys Tutorials, vol. 11 Mar (2009).

DOI: 10.1109/surv.2009.090109

[8] R. Chen, J. Park and J. Reed, Defence against primary user emulation attacks in cognitive radio networks, IEEE J. Sel. Areas Commun, vol 26, pp.25-37, Jan (2008).

DOI: 10.1109/jsac.2008.080104

[9] S. Kay and J. Marple Spectrum analysis-a modem perspective, proc. IEEE, vol. 69, pp.1380-1419, Nov. (1981).

DOI: 10.1109/proc.1981.12184

[10] W.A. Gardner, Stasistical Spectal Analysis: A Nonprobabilistic Theory. Prentice Hall. (1988).

[11] W.A. Gardner, Introduction to Random Process with Applications to Signals and System. Macmillan. (1996).

[12] P. Sutton. K Nolan and L. Dovle. Cyclostationary signatures for rendezyous in OFDM-based dynamic spectrum access networks. , 2nd IEEE International Symp, New Frontiers Dynamic Spectrum Access New. Pp. 220-231, Apr. (2007).

DOI: 10.1109/dyspan.2007.37

[13] J. Hartigan and M. Wong, A K-means clustering algorithm, Applied Stastistics, vol. 28 pp.100-108, (1979).

[14] T. Kohonen. The self-organizing map, , Neurocomputing, vol. 21, pp.1-6 Nov-(1998).

[15] T. Clancy and N. Geoergen, Security in congnitive radio networks: threats and mitigation, , in International Conf. Cognitive Radio Oriented Wireless Netw. Commun. May (2008).

DOI: 10.1109/crowncom.2008.4562534

[16] D. Pelleg and A. Moore, X-means: extending k-means with efficient estimation of the number of clusters, , in International Conf. Machine Learning. June (2000).

[17] J. Mitola, Cognitive radio: an integrated agent architecture for software defined radio, Ph. D dissertation, KTH (2000).

[18] FCC, FCC adopts rules for unlicensed use of television white spaces,. Available: http: /hraunfoss. fcc. gov/edocs_public/attachmatch/FCC-04-113A1. pdf.