Search - k means

Search - k means - List

[Console] wykmeans DL : 0: 基于c语言实现的聚类算法，运行与visual c++环境下，可以实现均值聚类。-c language based on the clustering algorithm, the operating environment with visual c, means clustering can be achieved.
Date : 2025-12-31 Size : 241kb User : 王莹
[Console] Knn DL : 0: K最近邻分类的代码，附有输入输出和程序使用说明。-K nearest neighbor classification code, with input and output and procedures for use.
Date : 2025-12-31 Size : 506kb User : 胡芬芬
[Console] kmeans DL : 0: 这是基本的k均值算法是模式识别的聚分类问题，这是用C实现其算法以下是程序源代码，希望对大家有所帮助。-This is the basic k-means algorithm is a pattern recognition classification of polyethylene, which is used to achieve its algorithm C Following is the source code, I hope all of you to help.
Date : 2025-12-31 Size : 3kb User : 夜水晶
[Console] K-means DL : 0: 简单实用的k均值聚类算法，可以实现多位向量的简单聚类-Simple and practical k-means clustering algorithm, can achieve more than a simple vector clustering
Date : 2025-12-31 Size : 5kb User : chunxiao
[Console] GA1E1 DL : 0: 用Ｋ均值和遗传算法实现了半监督聚类算法，这是个一个已经发表的论文的源程序-Using K-means and genetic algorithm to achieve a semi-supervised clustering algorithm, this is a paper published source
Date : 2025-12-31 Size : 3.96mb User : 张帅
[Console] knear DL : 0: K均值算法，用于聚类，程序写得比较好，容量读-K means algorithm for clustering, procedures written better, capacity Reading
Date : 2025-12-31 Size : 790kb User : Spring
[Console] bufengtouzhen DL : 0: 布冯投针找一根铁丝弯成一个圆圈，使其直径恰恰等于平行线间的距离d。可以想象得到，对于这样的圆圈来说，不管怎么扔下，都将和平行线有两个交点。因此，如果圆圈扔下的次数为n次，那么相交的交点总数必为2n。现在设想把圆圈拉直，变成一条长为πd的铁丝。显然，这样的铁丝扔下时与平行线相交的情形要比圆圈复杂些，可能有4个交点，3个交点，2个交点，1个交点，甚至于都不相交。由于圆圈和直线的长度同为πd，根据机会均等的原理，当它们投掷次数较多，且相等时，两者与平行线组交点的总数可望也是一样的。这就是说，当长为πd的铁丝扔下n次时，与平行线相交的交点总数应大致为2n。现在转而讨论铁丝长为l的情形。当投掷次数n增大的时候，这种铁丝跟平行线相交的交点总数m应当与长度l成正比，因而有：m=kl，式中k是比例系数。为了求出k来，只需注意到，对于l=πd的特殊情形，有m=2n。于是求得k=(2n)/(πd)。代入前式就有：m≈(2ln)/(πd)从而π≈(2ln)/(dm) -Find a wire bent into a circle, so that the diameter is precisely equal to the distance d between the parallel lines. Imagine, for this circle, no matter how dropped and parallel lines have two points of intersection. Therefore, if the circle dropped the number of n times, then the total number of the intersection point of intersection must be 2n. Now imagine the circle straightened into a long πd the wire. Obviously, this wire dropped the case of parallel lines intersect than circle complex, there may be four intersection of the three intersection 2 intersection, an intersection, and even do not intersect. As the circle and the length of the straight line with πd, according to the principle of equality of opportunity, when they throw more frequently, and equal, the total number of the intersection of two parallel lines group is also expected the same. This means that when the wire length πd dropped n times the total number of the intersection with the parallel lines intersect should b
Date : 2025-12-31 Size : 1.15mb User : s沈云航
[Console] k DL : 0: k均值算法，数据挖掘里面比较基础的算法，实现类聚-k-means algorithm, which based on the comparison of data mining algorithms to achieve clustering
Date : 2025-12-31 Size : 1kb User : l梁伟滔
[Console] K-means DL : 0: KMeans算法，经典的数据挖掘算法，设置了三个中心点，初始化是采用读取数据集的三个点作为中心的。-KMeans Algorithm, it is very famous data mining algorithm, i set three center, and it was initialed by the data we classify.
Date : 2025-12-31 Size : 2.11mb User : lida
[Console] kmean DL : 0: 实现了K-均值算法，并有简单的案例实现，简单易懂-K- means algorithm implements, and there is a simple case of realization, easy to understand
Date : 2025-12-31 Size : 1kb User : Sherman
[Console] ClusterAnalysis_2014.11.4 DL : 0: 模式识别的聚类分析。K均值聚类算法是先随机选取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。这个过程将不断重复直到满足某个终止条件。终止条件可以是没有（或最小数目）对象被重新分配给不同的聚类，没有（或最小数目）聚类中心再发生变化，误差平方和局部最小。-Pattern recognition clustering analysis. K-means clustering algorithm is to randomly K objects as the initial cluster centers. Then calculate the distance of each object and each seed cluster centers, assigning each object to its distance the nearest cluster center. Cluster centers and the object assigned to them on behalf of a cluster. Once all the objects are assigned, the cluster centers of each cluster will be recalculated based on the existing cluster object. This process is repeated until a termination condition is satisfied. Termination condition may not be (or smallest numbers) is reassigned to a different target cluster, no (or a minimum number) and then change the cluster centers, and a local minimum squared error.
Date : 2025-12-31 Size : 32.02mb User : 周思洁