• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology


Indian Journal of Science and Technology

Year: 2015, Volume: 8, Issue: 28, Pages: 1-12

Original Article

An Efficient Spectrum Sensing Framework and Attack Detection in Cognitive Radio Networks using Hybrid ANFIS


Background: Cognitive radio is being recognized as an intelligent technology due to its ability to rapidly and autonomously adapt operating parameters to changing environments and conditions. In order to reliably and swiftly detect spectrum holes in cognitive radios, spectrum sensing must be used. Accurate spectrum sensing is important in improving the efficiency of cognitive radio networks. False sensing results in either waste of spectrum or harmful interference to primary users who may remotely or physically capture the sensors and manipulate the sensing reports. Methods: A novel framework and an innovative approach have been introduced to eliminate the malicious behaviors of secondary users. It is found that spectrum sensing alone cannot prevent the malicious behavior without any information on users’ reputation. Based on the evaluation of malicious behavior resistance methods, joint spectrum sensing and malicious nodes detection approach for optimal prevention from sensing falsification is being proposed. Findings: The proposed approach minimizes Linear Minimum Mean-Square Errors (LMMSEs) when it is compared with the existing algorithms such spectrum sensing based on HSMM and FNN based spectrum sensing are plotted versus detection probability, false alarm probability. With more malicious nodes proposed schemes are more effective to restrain the false alarms. Improvement/Application: The proposed spectrum sensesframework with attack detection which is very effective to determine the malicious users in spectrum holes. 
Keywords: Fuzzy Neural Network, Linear Minimum Mean Square Error, Primary User, Secondary User, Spectrum Sensing 


Subscribe now for latest articles and news.