The performance evaluation of a spectrum sensing implementation using an automatic modulation classification detection method with a Universal Software Radio Peripheral

Authors:
Jide Julius Popoola;Rex Van Olst
Affiliations:
Centre for Telecommunications Access and Services, School of Electrical and Information Engineering, University of the Witwatersrand, Johannesburg, South Africa;Centre for Telecommunications Access and Services, School of Electrical and Information Engineering, University of the Witwatersrand, Johannesburg, South Africa
Venue:
Expert Systems with Applications: An International Journal
Year:
2013

Citing 12
Cited 0

Original Contribution: A scaled conjugate gradient algorithm for fast supervised learning

Neural Networks
NeXt generation/dynamic spectrum access/cognitive radio wireless networks: a survey

Computer Networks: The International Journal of Computer and Telecommunications Networking
Spectrum sensing measurements of pilot, energy, and collaborative detection

MILCOM'06 Proceedings of the 2006 IEEE conference on Military communications
Access Strategies for Spectrum Sharing in Fading Environment: Overlay, Underlay, and Mixed

IEEE Transactions on Mobile Computing
Applications of Machine Learning to Cognitive Radio Networks

IEEE Wireless Communications
Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information

IEEE Transactions on Information Theory
Compressed sensing

IEEE Transactions on Information Theory
COGNITIVE RADIOS FOR DYNAMIC SPECTRUM ACCESS - The Throughput Potential of Cognitive Radio: A Theoretical Perspective

IEEE Communications Magazine
Cooperative spectrum sensing in cognitive radio networks: A survey

Physical Communication
Cognitive radio: brain-empowered wireless communications

IEEE Journal on Selected Areas in Communications
Spectrum sensing: A distributed approach for cognitive terminals

IEEE Journal on Selected Areas in Communications
Defense against Primary User Emulation Attacks in Cognitive Radio Networks

IEEE Journal on Selected Areas in Communications

Quantified Score

Hi-index	12.05

Visualization

Abstract

Based on the inherent capability of automatic modulation classification (AMC), a new spectrum sensing method is proposed in this paper that can detect all forms of primary users' signals in a cognitive radio environment. The study presented in this paper focuses on the sensing of some combined analog and digitally primary modulated signals. In achieving this objective, a combined analog and digital automatic modulation classifier was developed using an artificial neural network (ANN). The ANN classifier was combined with a GNU Radio and Universal Software Radio Peripheral version 2 (USRP2) to develop the Cognitive Radio Engine (CRE) for detecting primary users' signals in a cognitive radio environment. The detailed information on the development and performance of the CRE are presented in this paper. The performance evaluation of the developed CRE shows that the engine can reliably detect all the primary modulated signals considered. Comparative performance evaluation carried out on the detection method presented in this paper shows that the proposed detection method performs favorably against the energy detection method currently acclaimed the best detection method. The study results reveal that a single detection method that can reliably detect all forms of primary radio signals in a cognitive radio environment, can only be developed if a feature common to all radio signals is used in its development rather than using features that are peculiar to certain signal types only.