针对K-means聚类算法易受到初始聚类中心的影响且易陷入局部最优值的不足,提出一种基于改进蜣螂优化算法的K-means聚类算法。首先,引入分段线性混沌映射(Piecewise Linear Chaotic Map, PWLCM)改善种群多样性,提高算法的求解精度和收敛...针对K-means聚类算法易受到初始聚类中心的影响且易陷入局部最优值的不足,提出一种基于改进蜣螂优化算法的K-means聚类算法。首先,引入分段线性混沌映射(Piecewise Linear Chaotic Map, PWLCM)改善种群多样性,提高算法的求解精度和收敛速度;其次,受鱼鹰算法位置识别和捕鱼策略的启发,使用其全局勘探策略替换蜣螂优化算法滚球阶段策略,可以弥补算法在滚球阶段中只依赖最差值,无法与其它蜣螂进行交流的缺点,从而增强算法的全局探索能力;然后,加入动态选择的自适应t分布扰动,增加全局开发以及局部搜索能力,通过CEC2017测试函数验证改进蜣螂优化算法的有效性和优越;最后,将改进后的蜣螂优化算法与K-means聚类算法相结合,从UCI数据集中选取6个真实的数据集与其他学者提出的群智能算法优化的K-means进行对比仿真实验,结果表明本文改进后的聚类算法具有更好的求解精度和鲁棒性。展开更多
为有效改善多图像加密质量及其对数据传输的安全性,提出一种基于超混沌系统的多权限多图像加密算法.首先,将L幅明文图像分别进行分段线性混沌映射(piece-wise linear chaotic map,PWLCM)的双层交叉耦合操作,并通过异或进行合并得到类噪...为有效改善多图像加密质量及其对数据传输的安全性,提出一种基于超混沌系统的多权限多图像加密算法.首先,将L幅明文图像分别进行分段线性混沌映射(piece-wise linear chaotic map,PWLCM)的双层交叉耦合操作,并通过异或进行合并得到类噪声图像;接着,采用最低有效位嵌入算法将类噪声图像嵌入到第L+1幅明文图像信息中,得到半加密图像;最后,通过结合一维的cubic映射和一维帐篷映射,产生一个二维cubic-帐篷混沌映射(two-dimensional cubic-tent modular map,2D-CTMM),利用其对半加密图像扩散后进行双层阶梯置乱,得到密文图像.实验结果表明:所提方法对明文以及密钥十分敏感,密钥空间大,可以有效抵御统计攻击和差分攻击,并且该算法在保证安全性的前提下,实现了用户多权限解密以及用户部分解密工作.展开更多
In this paper, first, we investigate a novel one-dimensional logistic-PWLCM（LP） modulation map which is derived from the logistic and PWLCM maps. Second, we propose a novel PCLML spatiotemporal chaos in pseudo-rando...In this paper, first, we investigate a novel one-dimensional logistic-PWLCM（LP） modulation map which is derived from the logistic and PWLCM maps. Second, we propose a novel PCLML spatiotemporal chaos in pseudo-random coupling method that can accelerate the system behavior of the fully spatial chaos. Here, because the better chaotic properties include a wide range of parameter settings and better ergodicity than a logistic map, the LP is used in PCLML as f（x）. The Kolmogorov–Sinai entropy density and universality and the bifurcation diagram are employed to investigate the chaotic behaviors of the proposed PCLML model. Finally, we apply the LP and PCLML chaotic systems to image encryption to improve the effectiveness and security of the encryption scheme. By combining self-generating matrix model M and dynamic substitution box（S-Box） methods, we design a new image encryption algorithm. Numerical simulations and security analysis have been carried out to demonstrate that the proposed algorithm has a high security level and can efficiently encrypt several different kinds of images into random-like images.展开更多
文摘针对K-means聚类算法易受到初始聚类中心的影响且易陷入局部最优值的不足,提出一种基于改进蜣螂优化算法的K-means聚类算法。首先,引入分段线性混沌映射(Piecewise Linear Chaotic Map, PWLCM)改善种群多样性,提高算法的求解精度和收敛速度;其次,受鱼鹰算法位置识别和捕鱼策略的启发,使用其全局勘探策略替换蜣螂优化算法滚球阶段策略,可以弥补算法在滚球阶段中只依赖最差值,无法与其它蜣螂进行交流的缺点,从而增强算法的全局探索能力;然后,加入动态选择的自适应t分布扰动,增加全局开发以及局部搜索能力,通过CEC2017测试函数验证改进蜣螂优化算法的有效性和优越;最后,将改进后的蜣螂优化算法与K-means聚类算法相结合,从UCI数据集中选取6个真实的数据集与其他学者提出的群智能算法优化的K-means进行对比仿真实验,结果表明本文改进后的聚类算法具有更好的求解精度和鲁棒性。
基金Project supported by the National Natural Science Foundation of China(Grant Nos.61672124,61370145,and 61173183)the Password Theory Project of the13th Five-Year Plan National Cryptography Development Fund,China(Grant No.MMJJ20170203)+1 种基金the Program for New Century Excellent Talents in Fujian Province Universitythe Natural Science Foundation of Fujian Province of China(Grant No.2018J01100)
文摘In this paper, first, we investigate a novel one-dimensional logistic-PWLCM（LP） modulation map which is derived from the logistic and PWLCM maps. Second, we propose a novel PCLML spatiotemporal chaos in pseudo-random coupling method that can accelerate the system behavior of the fully spatial chaos. Here, because the better chaotic properties include a wide range of parameter settings and better ergodicity than a logistic map, the LP is used in PCLML as f（x）. The Kolmogorov–Sinai entropy density and universality and the bifurcation diagram are employed to investigate the chaotic behaviors of the proposed PCLML model. Finally, we apply the LP and PCLML chaotic systems to image encryption to improve the effectiveness and security of the encryption scheme. By combining self-generating matrix model M and dynamic substitution box（S-Box） methods, we design a new image encryption algorithm. Numerical simulations and security analysis have been carried out to demonstrate that the proposed algorithm has a high security level and can efficiently encrypt several different kinds of images into random-like images.
