| A NON-PARAMETRIC CLASS MODELLING TECHNIQUE |
| |
| 作者姓名： | M.P.DERDE L.KAUFMAN D.L.MASSART |
| |
| 作者单位： | Laboratory for Pharmaceutical Chemistry，Laboratory for Pharmaceutical Chemistry，Laboratory for Pharmaceutical and Biomedical Analysis Pharmaceutical Institute Vrije Universiteit Brussel Laarbeeklaan 103 B-1090 Brussels Belgium |
| |
| 摘 要： | A non-parametric method for supervised pattern recognition is presented. The method is of the classmodelling type, meaning that a classification rule is developed for each class, using the dissimilaritiesbetween the objects of the class. The dissimilarities between the objects within a class are related to thedistances between all pairs of training objects. As distance metric, a measure is proposed that takes thecorrelation between the interval-scale variables into account, and that moreover can be used for mixedtypes of variables. The classification rule is based on the construction of a boundary in the measurementspace. For the determination of the class boundary, several strategies are proposed and compared. The performance of the technique is evaluated on the basis of several data sets. Comparison with theclass modelling technique UNEQ shows its usefulness for practical applications.
|
A NON-PARAMETRIC CLASS MODELLING TECHNIQUE |
| |
| M.P.DERDE,L.KAUFMAN,D.L.MASSART.A NON-PARAMETRIC CLASS MODELLING TECHNIQUE[J].Journal of Geographical Sciences,1989(1). |
| |
| Authors: | M P DERDE L KAUFMAN D L MASSART Laboratory for Pharmaceutical Chemistry and Laboratory for Pharmaceutical and Biomedical Analysis Pharmaceutical Institute Vrije Universiteit Brussel Laarbeeklaan B- Brussels Belgium |
| |
| Abstract: | A non-parametric method for supervised pattern recognition is presented. The method is of the class modelling type, meaning that a classification rule is developed for each class, using the dissimilarities between the objects of the class. The dissimilarities between the objects within a class are related to the distances between all pairs of training objects. As distance metric, a measure is proposed that takes the correlation between the interval-scale variables into account, and that moreover can be used for mixed types of variables. The classification rule is based on the construction of a boundary in the measurement space. For the determination of the class boundary, several strategies are proposed and compared. The performance of the technique is evaluated on the basis of several data sets. Comparison with the class modelling technique UNEQ shows its usefulness for practical applications. |
| |
| Keywords: | Non-parametric method Pattern recognition Classification |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《地理学报(英文版)》浏览原始摘要信息 |
| 点击此处可从《地理学报(英文版)》下载免费的PDF全文 |
