Jammer detection in M-QAM-OFDM by learning a dynamic Bayesian model for the cognitive radio

Communication and information field has witnessed recent developments in wireless technologies. Among such emerging technologies, the Internet of Things (IoT) is gaining a lot of popularity and attention in almost every field. IoT devices have to be equipped with cognitive capabilities to enhance spectrum utilization by sensing and learning the surrounding environment. IoT network is susceptible to the various jamming attacks which interrupt users communication. In this paper, two systems (Single and Bank-Parallel) have been proposed to implement a Dynamic Bayesian Network (DBN) Model to detect jammer in Orthogonal Frequency Division Multiplexing (OFDM) sub-carriers modulated with different M-QAM. The comparison of the two systems has been evaluated by simulation results after analyzing the effect of self-organizing map's (SOM) size on the performance of the proposed systems in relation to M-QAM modulation.