基于改进量子遗传算法的聚类算法

摘要

传统K-均值算法的初始聚类中心从数据集中随机产生,容易陷入局部最优解.提出了一种改进量子遗传聚类方法,用量子比特构成染色体,用实数对量子比特进行编码,用量子旋转门进行染色体更新,用量子Hadamard门进行染色体变异,结合了目标函数的梯度信息,对旋转门的旋转角进行动态调整.每条基因代表一个优化解,在染色体数目相同时,可使搜索空间加倍.实验结果表明,提出的方法在稳定性和分类准确率上都有所提高.%The initial clustering center of the traditional K - means algorithm is generated randomly from the data set, and easy to trap into the local minimum. A clustering algorithm based on improved quantum genetic algorithm was proposed. In this study, chromosomes were comprised of quantum bits encoded by real number. The chromosomes were renovated by quantum rotating gates and mutated by quantum hadamard gate. The gradients of object function were utilized in adjusting the value of rotating angle by a dynamic strategy. Each chain of genes represents an optimization result. Therefore, a double searching space was acquired for the same number of chromosomes. Experimental results show that the proposed method improves the stability and the accuracy of classification.