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：
针对航运信息中大样本聚类问题，根据k-means聚类过程中大部分簇的调整发生在初始迭代阶段的特性，提出了一种调整簇阀值的加速聚类方法，并对该算法进行实例测试，实验结果证明了该方法在满足原有的聚类精度的基础上，减少了聚类的计算量。本文将该方法应用到船舶航线设计中。
英文摘要：
Considering most adjustments of clusters happen in the initial stage of iteration in the clustering process of k-means algorithm, an accelerated clustering analysis algorithm is proposed to perform the clustering for large amounts of samples based on cluster threshold adjusted. Experiments prove that the improved algorithm can obtain the good clustering result, and accelerate the speed of clustering. Finally, an application of clustering is given for designing routes from the marine database.
同期刊论文项目
同项目期刊论文
Representation of uncertain multi-channel digital signal spaces and study of pattern recognition bas
DELAY-DEPENDENT STABILITY CRITERION AND H infinity STATE-FEEDBACK CONTROL FOR UNCERTAIN DISCRETE-TIM
Brief Paper Improved exponential stability criteria and stabilisation of T-S model-based neutral sys
Similarity Relation of Two-Dimensional Frustum Pyramid Fuzzy Numbers Based on the Geometry and Its A
Delay-dependent global robust stability criterion for neural networks with neutral-type time-varying
Distributed Kalman filtering fusion with packet loss or intermittent communications from local estim
Constructing n-cell numbers by using double-side separation degrees and pattern recognition based on
Uniqueness and Explosion Time of Solutions of Stochastic Differential Equations Driven by Fractional
A near-optimal iterative algorithm via alternately optimizing sensor and fusion rules in distributed
位置：