946 publications from this institution
This paper presents several fundamental concepts of game theory, and shows how they relate to the game formulation for a small cluster of opportunistic wireless nodes in cognitive radio networks. It is shown that in some resource allocation scenarios, it may be an optimal strategy for the wireless nodes to endure short-term losses for longer-term gains. In such scenarios, maximum total payoff may be achieved not by simultaneous mutual cooperation, but by taking turns defecting. The paper presents a novel idea of modeling cooperation and coordination for the opportunistic spectrum access as a turn-taking Prisoners dilemma. In our model, a small cluster of cognitive wireless nodes opportunistically access spectrum using spectrum shaped Oppermann sequences. Simulation results show that for the proposed resource allocation game turn-taking memory two strategies outperform traditional tit-for-tat and grim-trigger strategies.
End-to-end learning of a communications system using the deep learning-based autoencoder concept has drawn interest in recent research due to its simplicity, flexibility and its potential of adapting to complex channel models and practical system imperfections. In this paper, we have compared the bit error rate (BER) performance of autoencoder based systems and conventional channel coded systems with convolutional coding (CC), in order to understand the potential of deep learning-based systems as alternatives to conventional systems. From the simulations, autoencoder implementation was observed to have a better BER in 0-5 dB $E_{b}/N_{0}$ range than its equivalent half-rate convolutional coded BPSK with hard decision decoding, and to have only less than 1 dB gap at a BER of $10^{-5}$. Furthermore, we have also proposed a novel low complexity autoencoder architecture to implement end-to-end learning of coded systems in which we have shown better BER performance than the baseline implementation. The newly proposed low complexity autoencoder was capable of achieving a better BER performance than half-rate 16-QAM with hard decision decoding over the full 0-10 dB $E_{b}/N_{0}$ range and a better BER performance than the soft decision decoding in 0-4 dB $E_{b}/N_{0}$ range.
