针对稀疏MIMO信道系统模型线性均衡过程中输入信号,输出信号都含有噪声的情况提出了一种变遗忘因子的稀疏正则化总体最小二乘算法(VFF-SRTLS)。本算法中采用总体最小二乘(TLS)的代价函数即瑞利商加入正则化的l_1范数和l_0范数作为其代...针对稀疏MIMO信道系统模型线性均衡过程中输入信号,输出信号都含有噪声的情况提出了一种变遗忘因子的稀疏正则化总体最小二乘算法(VFF-SRTLS)。本算法中采用总体最小二乘(TLS)的代价函数即瑞利商加入正则化的l_1范数和l_0范数作为其代价函数,并利用次梯度下降法产生的迭代式用以更新均衡滤波器系数,使均衡过程中代价函数最小;同时为了使算法能够适应信道快变环境而采用变遗忘因子(VFF),并且根据最速下降法得到遗忘因子的迭代式。仿真结果表明,在信噪比为10 d B的2×2 MIMO线性均衡过程中VFF--RTLS算法的收敛MSE值比RLS算法低约2 d B,VFF-l_0-RTLS算法的收敛MSE值比RLS算法低约1.5 d B。展开更多
Least squares support vector machines (LS-SVMs) are modified support vector machines (SVMs) that involve equality constraints and work with a least squares cost function, which simplifies the optimization procedure. I...Least squares support vector machines (LS-SVMs) are modified support vector machines (SVMs) that involve equality constraints and work with a least squares cost function, which simplifies the optimization procedure. In this paper, a novel training algorithm based on total least squares (TLS) for an LS-SVM is presented and applied to multifunctional sensor signal reconstruction. For three different nonlinearities of a multifunctional sensor model, the reconstruction accuracies of input signals are 0.001 36%, 0.031 84% and 0.504 80%, respectively. The experimental results demonstrate the higher reliability and accuracy of the proposed method for multifunctional sensor signal reconstruction than the original LS-SVM training algorithm, and verify the feasibility and stability of the proposed method.展开更多
文摘针对稀疏MIMO信道系统模型线性均衡过程中输入信号,输出信号都含有噪声的情况提出了一种变遗忘因子的稀疏正则化总体最小二乘算法(VFF-SRTLS)。本算法中采用总体最小二乘(TLS)的代价函数即瑞利商加入正则化的l_1范数和l_0范数作为其代价函数,并利用次梯度下降法产生的迭代式用以更新均衡滤波器系数,使均衡过程中代价函数最小;同时为了使算法能够适应信道快变环境而采用变遗忘因子(VFF),并且根据最速下降法得到遗忘因子的迭代式。仿真结果表明,在信噪比为10 d B的2×2 MIMO线性均衡过程中VFF--RTLS算法的收敛MSE值比RLS算法低约2 d B,VFF-l_0-RTLS算法的收敛MSE值比RLS算法低约1.5 d B。
基金the National Natural Science Foundation of China (Nos. 60772007 and 60672008)China Postdoctoral Sci-ence Foundation (No. 20070410258)
文摘Least squares support vector machines (LS-SVMs) are modified support vector machines (SVMs) that involve equality constraints and work with a least squares cost function, which simplifies the optimization procedure. In this paper, a novel training algorithm based on total least squares (TLS) for an LS-SVM is presented and applied to multifunctional sensor signal reconstruction. For three different nonlinearities of a multifunctional sensor model, the reconstruction accuracies of input signals are 0.001 36%, 0.031 84% and 0.504 80%, respectively. The experimental results demonstrate the higher reliability and accuracy of the proposed method for multifunctional sensor signal reconstruction than the original LS-SVM training algorithm, and verify the feasibility and stability of the proposed method.
