一种改进K-means算法在受力分析中的应用

Study on Application of an Improved K-means Algorithm in Force Analysis

阐述K-means算法是一种根据距离作为划分标准的经典聚类算法,应用广泛,但其对初始聚类中心的选取具有依赖性和较强敏感性等问题。为适应不同领域需求,可以根据数据集的特点对K-means算法进行改进。探讨对K-means算法在受力分析中的应用,采用基于受力面数据分布密度进行初始聚类中心设置的改进K-means算法,通过柔性压力传感器阵列采集人体臀部和腿部对坐凳坐垫受力面的压力数据,利用两种K-means算法对数据分别进行处理分析。实验结果表明,改进的K-means算法在分析结果准确率、稳定性方面优于传统K-means算法。

This paper expounds that k-means algorithm is a classical clustering algorithm based on distance, which is widely used, but it has dependence and strong sensitivity on the selection of initial clustering center. In order to meet the needs of different fields, the k-means algorithm can be improved according to the characteristics of the data set. It discusses the application of K-means algorithm in force analysis, adopts the improved k-means algorithm based on the data distribution density of the force surface to set the initial clustering center, collects the pressure data of the force surface of the seat cushion of the human hip and legs through the flexible pressure sensor array, and uses two kinds of k-means algorithm to process and analyze the data respectively. The experimental results show that the improved k-means algorithm is better than the traditional K-means algorithm in the accuracy and stability of the analysis results.