欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
基于模糊C均值（FCM）聚类算法建立了实测洪水过程的模糊聚类模型,模型可将实测样本分为若干类,每一类的聚类中心即为一个典型洪水过程.由于传统FCM聚类算法易陷入局部极值点,难以适应洪水过程分类具有的数据量大、维数较高的特点,因此采用遗传算法对其进行了改进.应用改进算法对一个实例进行聚类分析,并结合基于可能性定理的聚类有效性准则,对聚类结果作进一步的有效性评价.分析表明：改进算法产生的分类结果比较合理,较接近于实际情况,可以应用于洪水过程分类.
英文摘要：
A fuzzy clustering model for flood hydrograph classification was established based on fuzzy C-means （FCM） clustering algorithm. All observed samples can be classified into some clusters by using this model and the cluster prototype of each cluster can be regarded as one of typical hydrographs. Because the conventional FCM algorithm is prone to fall into local extreme points, especially when dealing with massive and high-dimensional data sets as in cluster analysis for flood hydrograph classification, genetic algorithms were used to improve it. An example was included to illustrate the improved FCM algorithm and the feasible clustering results were respectively evaluated by using a cluster validity function based on possibility distribution theory. The agreement of the optimal clustering result and the actual data indicates that the proposed method performs well and can be used for flood hydrograph classification.
同期刊论文项目
同项目期刊论文
位置：