基于混沌量子遗传改进模糊C均值聚类算法.docVIP

基于混沌量子遗传改进模糊C均值聚类算法 　　摘 要: 　　针对标准FCM对噪声和初值敏感的问题,提出一种基于实数编码混沌量子遗传算法(RCQGA)的改进的加入空间信息的FCM算法。该算法在解空间内将实数染色体通过反向变换映射到量子位, 采用量子位概率指导的实数交叉与混沌变异相结合的方法对实数染色体进行演化搜索。将RCQGA与结合空间邻域信息的FCM相结合,用改进的 FCM算法的目标函数建立适应度函数,利用混沌量子遗传算法搜索全局最优解,代替传统FCM的基于梯度下降的迭代爬山过程,从而有效地避免了模糊C?簿?值聚类算法收敛到局部最优和对噪声敏感的问题，并在此基础上实现了对遥感图像的聚类分割。实验结果表明,该算法对于遥感图像显示了较好的分割效果和较强的抗噪能力。 　　?ス丶?词: 　　模糊C均值;空间邻域信息;全局优化;实数编码混沌量子遗传算法;遥感图像 　　?ブ型挤掷嗪?: 　　TP391.41 　　文献标志码:A 　　英文标题?? 　　New FCM algorithm based on real??coded chaotic quantum??inspired?? genetic algorithm for remote sensing image segmentation 　　?び⑽淖髡呙? 　　LU Bin??bin??1, JIA Zhen??hong??1, HE Di??1, YANG Jie??2, PANG Shao??ning??3 　　?び⑽牡刂?( 　　1. College of Information Science and Engineering, Xinjiang University, Urumuqi Xinjiang 830046, China??;?? 　　2. Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai 200240, China??;?? 　　3. Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, Auckland 1020, New Zealand 　　英文摘要)?? 　　Abstract: 　　In order to overcome the sensitive of Fuzzy C??Means (FCM) algorithm to the initial value and sensitive to noise, a Real??Coded Chaotic Quantum??Inspired Genetic Algorithm (RCQGA) was proposed, which was a novel global optimization search algorithm. In this algorithm, real chromosomes were inversely mapped to Q??bits in the solution space. Q??bits probability guided real cross and chaos mutation were used to real chromosomes evolution and searching. A new segmentation algorithm was presented, which combines the RCQGA and FCM. Then the fitness function contained neighbor information was set up according to the object function in FCM algorithm. By applying RCQGA, the global optimum could be obtained. The segmentation results demonstrate that the algorithm performs more effective in searching global optimal solution and more robust to noise than standard FCM algorithm. 　　英文关键词??Key words: 　　Fuzzy C??Means (FCM); spatial neighhood information; glo