Hopfield神经网盲检测统计信息缺失信号

来源期刊:中南大学学报(自然科学版)2011年第z1期

论文作者:阮秀凯 张志涌

文章页码:12 - 16

关键词:盲检测;连续复Hopfield神经网络;统计信息缺失;能量函数;激活函数

Key words:blind detection; continuous complex Hopfield neural network; missing statistics information; energy function; activation function

摘    要:考虑到现代无线通信系统信号的高频化特性,采用连续输入的神经元是接近物理现实,并利用连续Hopfield型神经网络本身特点,提出如何运用复连续Hopfield网络解决统计信息缺失信号的盲检测问题。研究统计信息缺失的信号盲检测的优化问题构造和能量函数的映射,给出该特定问题的能量函数、正确盲检测信号权矩阵的配置方法。最后通过仿真验证算法的有效性和鲁棒性并指出未来的研究方向。

Abstract: Based on the fact that both the continuous Hopfield neural network (CHNN) characteristics and the high frequency characteristics of signals in modern wireless communication systems that continuous input neurons are close to true physical fact are taken into account, a new blind detection algorithm of the signals with missing statistics information using complex CHNN was proposed. The method of mapping the cost function of this optimization problem to the energy function of CHNN is proposed. How to map the cost function of this optimization problem to the energy function of CHNN was studied. Meantime, a special connective matrix was constructed to ensure the detect signals correctly was illustrated to ensure the detect signals correctly. Simulation results demonstrate the effectiveness and robustness of this new algorithm.

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号