No abstract

The Zhang neural network (ZNN), as a special class of recurrent neural network (RNN), has been proposed by Zhang et al. for the online solution of various time-varying problems. More importantly, such a ZNN is based on the Zhang function (ZF) as the error-monitoring function, which is indefinite and quite different from the usual error functions in the study of conventional algorithms, such as a scalar-valued norm-based energy function involved in the gradient-based neural network (GNN). Meanwhile, the resultant ZNN model can guarantee the global/exponential convergence performance for online time-varying problems solving by following Zhang et al.'s design method. In this paper, focusing on solving the time-varying complex matrix-inversion problem, the complex ZNN models are proposed, developed and investigated for timevarying complex matrix inversion. In addition, by introducing different complex ZFs, different corresponding complex ZNN models can be proposed and developed for time-varying complex matrix inversion. Finally, through some simulations and verifications, the illustrative results substantiate the efficacy of the complex ZNN models based on different complex ZFs for time-varying complex matrix inversion.

Spectrum sensing is a crucial issue in cognitive radio networks for primary user detection. Energy detection is widely makes the detector unreliable due to the varied noise power. In this paper, we take noise uncertainty into consideration for three kinds of hard fusion strategies (OR rule, AND rule, and Majority rule), and compare the sensing performance for these fusion rules to achieve the reliable fusion rule [1] in different networks and different channels (AWGN and Rayleigh). Extensive simulations indicate that AND rule performs the best for most cases over AWGN channels, while OR rule applies to the network with few sensors at low probability of false alarm. However, in Rayleigh channels OR rule is a good choice except the case that noise uncertainty is low and the number of cognitive sensors is large.I.

No abstract