基于粒子群优化的独立分量分析算法研究

Research on Independent Component Analysis Based on Particle Swarm Optimization Algorithms

在分析独立分量分析算法的基础上,给出了一种基于粒子群优化的独立分量分析算法。该算法以互信息量最小化为目标函数,通过对粒子群位置矢量和速度矢量更新的改进,得到全局最优值,从而得到分离矩阵。仿真实验表明,基于粒子群优化的独立分量分析算法是一种非常有效的盲源分离算法。

On the basis of analyzing the independent component analysis algorithms, a novel method based on particle swarm optimization was proposed to minimize the mutual information, which through improving position vector and velocity vector to get the global optimization solution and then separate the mixed signals. The simulation results showed that the independent component analysis based on particle swarm optimization was a more efficient algorithm.