How to weight Hasse matrices and reduce incomparabilities

被引：11

作者：

Grisoni, Francesca ^{[1
]}

Consonni, Viviana ^{[1
]}

Nembri, Serena ^{[1
]}

Todeschini, Roberto ^{[1
]}

机构：

[1] Univ Milano Bicocca, Dept Earth & Environm Sci, Milano Chemometr & QSAR Res Grp, I-20126 Milan, Italy

来源：

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS | 2015年 / 147卷

关键词：

Multi-criteria decision making; Hasse diagrams; weighted regularized Hasse; wR-Hasse; DIAGRAM TECHNIQUE; RANKING; WATER;

D O I：

10.1016/j.chemolab.2015.08.006

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This work presents a modified version of Hasse diagram technique, the weighted Regularized Hasse (wR-Hasse), which aims to reduce the number of incomparabilities and derive weighted rankings of the objects. These objectives are accomplished by (a) introducing a mathematical threshold on the definition of incomparability and (b) weighting criteria according to their relevance. In order to test the new approach, we used eight data sets from literature, aiming at extensively investigating the effect of thresholds and weighting schemes on the outcome. Results showed how (a) wR-Hasse effectively reduces the number of incomparabilities with respect to the original Hasse and (b) weighting schemes tune the contribution of relevant criteria to the final outcome. Moreover, this approach allows to obtain statistics useful to further investigate data structure and relationships between object ranks. (C) 2015 Elsevier B.V. All rights reserved.

引用

页码：95 / 104

页数：10

共 22 条

[1] Three-dimensional quantitative structure-activity relationship analyses using comparative molecular field analysis and comparative molecular similarity indices analysis to elucidate selectivity differences of inhibitors binding to trypsin, thrombin, and factor Xa [J].