Full-Text Search:
Home|About CNKI|User Service|中文
Add to Favorite Get Latest Update

Study on Error Evaluating Index for Spatialisation of Attribute Data

LIAO Shunbao1,ZHANG Sai1,2(1 Institute of Geographical Sciences and Natural Resources Research,CAS,Beijing 100101,China;2 Graduate school of Chinese Academy of Sciences,Beijing 100049,China)  
As one way to process geo-data,spatialisation of attribute data has become one of research focuses in GIS field.Spatialisation of attribute data can produce errors to a certainty like other data processing methods.It is very important to put forward a suit of evaluating index of errors for spatialisation of attribute data.In this paper,the evaluating index is composed of three parts which are corresponding to three different stages in spatialisating of attribute data: data source analyzing,spatialising modeling and data products.Evaluating index for data sources includes density of data observatory,density of contour line,and density of polygon pattern and equality of data.Evaluating index for spatialising model includes correlation ratio,significance of model(correlation ratio test;F test;t test)and estimation error of the model.Evaluating index for spatialised data products includes mean value,maximum value,value distribution range and spatial distribution of errors.Errors based on samples are divided into absolute errors and relative errors.These indexes are foundation for integrated evaluation of errors for spatialisation of attribute data and could enhance quality of data products.Among these evaluating indexes of error for spatialisation of attribute data,errors of spatialised data products are determined by precisions of data sources and spatialising models.The same precision of data sources with different precision of spatialising models leads to different precision of spatialised data products.The same precision of spatialising models with different precision of data sources also leads to different precision of spatialised data products.Therefore,error evaluating for spatialisation of attribute data should be carried out on the three stages consisting of data sources,modeling and spatialised results.
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©CNKI All Rights Reserved