摘要
该文将免疫系统的免疫机制引入到粒子群优化算法的设计中.模拟免疫系统、群集智能的信息处理机制,提出了免疫粒子群优化算法。这种免疫粒子群算法结合了粒子群的近似全局优化能力和由Hopfield神经网络构成的免疫系统的快速信息处理机制,加快了算法的收敛速度,并提高了粒子群算法的全局收敛能力。然后在CDMA系统中,利用此算法设计了多用户检测器,仿真结果证明该文的方法能够快速收敛到全局最优解,并且抗多址干扰能力和抗远近效应能力都优于传统方法和一些应用优化算法的多用户检测器。
In this paper, idea on immune information processing mechanism of immune system is introduced to particle swarm optimization algorithm. By simulating the information processing mechanism of biological immune system and swarm intelligence, We proposed the immune particle swarm optimization algorithm（IPSO）. The proposed algorithms have both the properties of the original particle swarm optimization algorithm and the faster convergence of immune system which is consist of neuron of Hopfield neural network, can improve the abilities of seeking the global excellent result and convergence speed. Experiments have been carried out on the method can improved on the multiuser detection in CDMA systems, the simulation results show that IPSO detector can achieve the global optimization in fast convergence rate, and also show that the proposed detector is obviously superior to the conventional receiver and multiuser detectors based on some optimum algorithm in terms of the multiple access interfere and the mitigation of near- far effect.
出处
《杭州电子科技大学学报（自然科学版）》
2006年第2期47-51,共5页
Journal of Hangzhou Dianzi University：Natural Sciences
关键词
多用户检测
粒子群优化算法
免疫系统
神经网络
multiuser detection
particle swarm optimization algorithm
immune system
hopfield neural network
