基于幅值相位型离散Hopfield神经网络的多进制振幅键控盲检测

针对统计量算法盲检测多进制振幅键控(MPSK)信号的缺陷, 提出了一种幅值相位型连续多值复数Hopfield神经网络算法, 构造了适用于MPSK信号的幅相型离散多电平激活函数,并分别在异步和同步更新模式下证明了该神经网的稳定性.当该神经网的权矩阵借助接收数据补投影算子构成时, 该幅相型离散Hopfield神经网络可有效地实现MPSK信号盲检测. 仿真试验表明:该算法所需接收数据较短,可到达全局真解点,并且适用于含公零点信道.

Blind detection of M-ary quaternary phase shift keying signals by a complex Hopfield neural network with amplitude-phase-type hard-multistate-activation-function

Considering the disadvantage of the algorithms based on statistics, a novel algorithm based on complex Hopfield neural network with amplitude-phase-type hard-multistate-activation-function (CHNN-APHM) is proposed to detect M-ary quaternary phase shift keying (MPSK) signals blindly. An amplitude-phase-type hard-multistate-activation-function is constructed. The stabilities of the CHNN-APHM with asynchronous and synchronous operating mode are also analyzed separately. While the weighted matrix of CHNN-APHM is constructed by the complementary projection operator of received signals, the problem of quadratic optimization with integer constraints can be successfully solved with the CHNN-APHM, and the MPSK signals are blindly detected. Simulation results show that the algorithm reaches the real equilibrium points with shorter received signals and if is applicable for channel with common zeros.