搜索资源列表
kmean
- k-means 算法的工作过程说明如下:首先从n个数据对象任意选择 k 个对象作为初始聚类中心;而对于所剩下其它对象,则根据它们与这些聚类中心的相似度(距离),分别将它们分配给与其最相似的(聚类中心所代表的)聚类;然后再计算每个所获新聚类的聚类中心(该聚类中所有对象的均值);不断重复这一过程直到标准测度函数开始收敛为止。-k-means algorithm process as follows: First of all, the object data from the n choose k
k-means-clustering
- 用C语言程序通过先随机选取K个对象作为初始的聚类中心。然后计算每个对象与各个种子聚类中心之间的距离,把每个对象分配给距离它最近的聚类中心。聚类中心以及分配给它们的对象就代表一个聚类。一旦全部对象都被分配了,每个聚类的聚类中心会根据聚类中现有的对象被重新计算。-C Programming Language by first randomly selected the K object as initial cluster centers. And then calculate the distan
3upload
- This algorithm is designed to segment an satellite image using Kmeans, and then all kmeans clusters Satellite image (target image) and template image using local binary pattern (LBP) and then applied various template matching techniques between LBP K
KMeans
- K-均值聚类算法,属于无监督机器学习算法,发现给定数据集的k个簇的算法。 首先,随机确定k个初始点作为质心,然后将数据集中的每个点分配到一个簇中,为每个点找距其最近的质心, 将其分配给该质心对应的簇,更新每一个簇的质心,直到质心不在变化。 K-均值聚类算法一个优点是k是用户自定义的参数,用户并不知道是否好,与此同时,K-均值算法收敛但是聚类效果差, 由于算法收敛到了局部最小值,而非全局最小值。 K-均值聚类算法的一个变形是二分K-均值聚类算法,该算法首先将所有点作为一个簇,然
clusterWSN
- All five matlab file relate to the cluster structure of wireless sensor network. LEACH, BCDCP, ERP, HEED and so on are very helpful to do the simulation.
PIM-fuzzy-c-means
- Partition index is a measure ofvalidity similar to partition coeGcient, based on using Pj = ci=1 (uij)m as a measure ofhow well the jth data point has been classi- 2ed. The closer a pixel is to a codebook entry, the closer Pj is to one. Ifa
fingtun
- 包括AHP,因子分析,回归分析,聚类分析,完整的图像处理课设,包含所有源代码,汽车图像,各种kalman滤波器的设计。- Including AHP, factor analysis, regression analysis, cluster analysis, Complete class-based image processing, contains all of the source code, auto image, Various kalman filter design.