Novel Piecewise Normalized Bistable Stochastic Resonance Strengthened Cooperative Spectrum Sensing

Abstract

A novel piecewise normalized bistable stochastic resonance (PNBSR) strengthened cooperative spectrum sensing is established by the PNBSR, residual covariance matrices, credibility weighted matrix fusion and a convolutional neural network (CNN) classification at low signal-to-noise ratios (SNRs). First, the PNBSR based on the traditional bistable stochastic resonance (TBSR) is proposed to improve the SNRs of received signals. Second, the output of the PNBSR is demodulated to obtain in-phase (I) and quadrature-phase (Q) covariance matrices. Third, the I/Q covariance matrices from different secondary users (SUs) are Cholesky decomposed to construct residual covariance matrices in a fusion center (FC). Subsequently, a new credibility weighted coefficient is proposed to fuse residual covariance matrices of the SUs. Finally, both training and test samples of the fusion detection statistics are fed into the CNN to train a high-performance classification model of cooperative spectrum sensing. The main innovations include the PNBSR, optimization index, Cholesky decomposition-based matrix cancellation to construct residual covariance matrices and credibility weighted matrix fusion. Simulation results show that the SNR of received signals strengthened by the PNBSR is improved by 3.36 dB other than received signals on average, which is 0.22dB larger than that of the TBSR. The detection probability of the proposed scheme also outperforms those of the support vector machine (SVM) and CNN schemes by 77% and 75% at -15 dB, respectively.