基于改进遗传算法的头部扩散型水肿电导率模型反演计算  

Conductivity Reconstruction of Edema in Human Brain Based on Modified Genetic Algorithm

作　　者：刘冀成[1] 黄卡玛[2] 胡雅毅[3] 

机构地区：[1]成都信息工程学院电子工程系,成都610225 [2]四川大学电子信息学院,成都610064 [3]四川大学华西第二医院,成都610041

出　　处：《生物医学工程学杂志》2007年第2期268-270,284,共4页Journal of Biomedical Engineering

基　　金：国家杰出青年科学基金资助项目(60125102)

摘　　要：为对头部扩散型水肿变化情况进行持续床旁监测,我们在理论模型的基础上,以改进遗传算法进行反演计算。提出了基于海明距离的动态交叉、变异算子,使算法在优化过程中能有效地保持种群的多样性。将改进算法应用于头部扩散型水肿模型的电导率反演计算,经与标准遗传算法对比,改进算法在提升效率的同时,保证了算法以较大概率收敛于全局最优解。It is the intent of this study to estimate the progression or regression of edema at the bedside continuously. Based on the theoretic model, the Adaptive Genetic Algorithm （AGA） has been applied in the calculation of conductivity reconstruction. Dynamic crossover and mutation operators which are based on Haiming Distance are brought forward in this paper to maintain generation＇s diversity. Then, both AGA and Standard GA （SGA） have been applied in the conductivity reconstruction of edema in human brain. It is shown that AGA not only has attained a higher degree of efficiency but also has enhanced the capability to converge to the best answer.

关 键 词：水肿 电导率 遗传算法 海明距离 算子 

分 类 号：R318[医药卫生—生物医学工程]