| SHORT COMMUNICATION CLASSIFICATION METHODS FOR MULTIVARIATE QUALITY PARAMETERS |
| |
| 作者姓名： | C.WEIHS W.BAUMEISTER H.SCHMIDLI |
| |
| 作者单位： | Mathematical Applications Information Services，R-1008.Z2.22，Analytical Department，Textile Dyes Division，K-420.4.04，Ciba-Geigy Ltd.，CH-4002 Basel，Switzerland，Mathematical Applications，Information Services，R-1008.Z2.22，Analytical Department，Textile Dyes Division，K-420.4.04，Ciba-Geigy Ltd.，CH-4002 Basel，Switzerland，Mathematical Applications，Information Services，R-1008.Z2.22，Analytical Department，Textile Dyes Division，K-420.4.04，Ciba-Geigy Ltd.，CH-4002 Basel，Switzerland |
| |
| 摘 要： | There are many chemical products where product conformity is decided upon by qualitative humanjudgements of overall product quality.Nowadays,quantitative instrumentally determined qualityparameters become available which are intended to replace such qualitative judgements by means ofautomatic decision rules using multivariate specification limits.Six classification methods to derive suchlimits are compared in terms of their power to predict corresponding human judgements on overall colorconformity of 17 dyestuffs based on historical quality data.Standard statistical classification methodsturned out to be unacceptable for the routine generation of decision rules because of the frequent distinctsuboptimality of their predictive power.Instead,a simple non-statistical classification method utilizinga priori knowledge about the underlying data structure yielded uniformly satisfactory decision rules.
|
SHORT COMMUNICATION CLASSIFICATION METHODS FOR MULTIVARIATE QUALITY PARAMETERS |
| |
| C.WEIHS,W.BAUMEISTER,H.SCHMIDLI.SHORT COMMUNICATION CLASSIFICATION METHODS FOR MULTIVARIATE QUALITY PARAMETERS[J].Journal of Geographical Sciences,1993(2). |
| |
| Authors: | C WEIHS WBAUMEISTER HSCHMIDLI Mathematical Applications Information Services R-Z Analytical |
| |
| Abstract: | There are many chemical products where product conformity is decided upon by qualitative human judgements of overall product quality.Nowadays,quantitative instrumentally determined quality parameters become available which are intended to replace such qualitative judgements by means of automatic decision rules using multivariate specification limits.Six classification methods to derive such limits are compared in terms of their power to predict corresponding human judgements on overall color conformity of 17 dyestuffs based on historical quality data.Standard statistical classification methods turned out to be unacceptable for the routine generation of decision rules because of the frequent distinct suboptimality of their predictive power.Instead,a simple non-statistical classification method utilizing a priori knowledge about the underlying data structure yielded uniformly satisfactory decision rules. |
| |
| Keywords: | Classification Discriminant analysis Class modeling Specification limits Cross-validation |
| 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 |
