[文章摘要]Constructing knowledge from multivariate spatiotemporal data: integrating geographical visuali

来源:互联网 发布:金蝶软件常见问题 编辑:程序博客网 时间:2024/06/05 20:39
文章:Constructing knowledge from multivariate spatiotemporal data: integrating geographical visualization with knowledge discovery in database methods
作者:MacEachren A M, Wachowicz M, Edsall R, et al.
来源:International Journal of Geographical Information Science, 1999, 13(4): 311-334.


本文的web link已经变为了:

http://www.geovista.psu.edu/publications/ijgis99/


Geographic Visualization (GVis) and Knowledge Discovery in Databases (KDD),
GVis和KDD的集成,强调通过用户交互来迭代地发现模式


本文解决the development and integration of data analysis and visualization methods designed to facilitate identification and interpretation of spatial and spatiotemporal features.


GVis和KDD有相似的目标,不同在于手段不同,以来人类视觉或计算机的计算能力。

GVis是一个process,其特点:
(1) the iterative nature of successful human interpretation of visual displays
(2)高度的交互性:迭代
(3)目标是发现模式和关系


This integrated cognitive-semiotic perspective serves as a base fromwhich to consider three categories of visualizationmeta-operations that are at the heart of the data exploration components of the Apoala Project:feature identification, feature comparison, and feature interpretation. These three operation forms are defined below, linked to three categories of KDD operations.


KDD也是一个过程,包含了交互迭代随着知识的精化,很多步骤可能需要重复
KDD的三个meta-operations
(1)concept hierarchy and structure extraction: (a process in which data abstractions are derived and linked at multiple conceptual levels)
(2)categories extraction and classi® cation (a process of deriving classes, clusters, rules, and/or patterns from target data and using the result to assign data to classes that result from the categorization process), 
(3)phenomenon extraction (a process of deriving representations of real-world phenomena from a target data set).




从上面的分析可以看到,GVis和KDD有相似的目标,都强调迭代的中心作用。



本文的集成有三个层次;
概念层、操作层和实现层。


view的三种表达方式:
1,geoviews
2,3D scatterplot:空间化 spatialization,隐喻:近=相似,远=不同。
3,PCP





交互:
-assignment:
PCP给不同的轴赋予不同的属性,可以将任意两个轴放在一起,或者多个轴排成一个序列,
甚至可以将重复的属性放在一个序列里来查询特别的“签名”。当然,还可以改变颜色,符号大小。
-brushing:发现outlier等
-Focusing:改变阈值,阈值上高亮一类,阈值下高亮一类等。
-colourmap manipulation:替换color方案,
有序列的颜色方案,有发散的颜色方案,分别用于不同的目的,还可以自定义。
-viewpoint manipulation:视点变换,GIS中常用的,旋转,平移、缩放。
-Sequencing:搜寻随时间变化的趋势等。
0 0
原创粉丝点击