基于SOM聚类的垃圾处理方式可视化分析方法

Visual Analysis Method of Garbage Disposal Modes Based on Self-organizing Maps Clustering

针对全国各省份垃圾处理方式的数据,提出一种混合可视分析方法。为了从多角度分析数据,混合U矩阵、平行坐标以及Small-Multiple 3种可视化技术,设计并实现了3种可视化视图的交互联动。首先,对数据进行聚类处理,将各省份近年的垃圾处理方式划分类别,采用SOM神经网络聚类算法实现聚类。然后,针对SOM聚类结果,采用U矩阵的方式进行可视化,并采用平行坐标描述每个聚类结果的各个属性。为了分析数据的地理属性及时序属性,采用Small-Multiple可视化技术。最后,实现多视图联动、刷新技术等交互方式,帮助用户自行探索数据,实现多视图的交互展示与分析。实验表明,这种混合可视方式可达到较好的多属性交互可视化效果,能够帮助用户了解并分析我国垃圾处理方式的分布及趋势。

A hybrid visual analysis method was proposed for the data of garbage disposal modes in various provinces of China.In order to analyze the data from multiple views,this paper combined three visualization techniques including unified distance matrix,parallel coordinate and Small-Multiple,designed and realized the interactions among the three views.Firstly,the data are processed by clustering so that the garbage disposal modes of different provinces in recent years can be divided into different categories.The clustering used in this paper is based on self-organizing maps(SOM)neural network clustering algorithm.Secondly,according to the results of SOM clustering,the unified distance matrix is used for visualization,and the parallel coordinate is used to describe the attributes of each clustering result.In order to analyze the geographical and sequential attributes of data,the Small-Multiple visualization technology is used.Thirdly,interactions such as multi-view linkage and refreshing are implemented to help users explore the data on their own and achieve interactive display and analysis of multiple views.The experimental results show that the hybrid visualization method can achieve a good visualization effect of multi-attributes interaction and can help users to understand the distribution and trend analysis of garbage disposal modes in China.