基于混沌粒子群算法的Tikhonov正则化参数选取

Tikhonov正则化方法是求解不适定问题最为有效的方法之一,而正则化参数的最优选取是其关键.本文将混沌粒子群优化算法与Tikhonov正则化方法相结合,基于Morozov偏差原理设计粒子群的适应度函数,利用混沌粒子群优化算法的优点,为正则化参数的选取提供了一条有效的途径.数值实验结果表明,本文方法能有效地处理不适定问题,是一种实用有效的方法.

Optimal Choosing of Tikhonov Regularization Parameter Based on Chaos Particle Swarm Optimization Algorithm

Tikhonov regularization method is one of the most effective ways for solving the ill-posed problems.In the method,choosing a regularization parameter is the key step.Then a chaos particle swarm optimization(CPSO) algorithm is introduced to calculate the optimal regularization parameter by using the advantages of CPSO.And the fitness function of particle swarm is defined based on the Morozov discrepancy principle.The numerical experimental results show that the proposed method can solve the ill-posed problem...