2015
DOI: 10.1016/j.chemolab.2015.08.006
|View full text |Cite
|
Sign up to set email alerts
|

How to weight Hasse matrices and reduce incomparabilities

Abstract: 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… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0

Year Published

2016
2016
2021
2021

Publication Types

Select...
3
2
1

Relationship

1
5

Authors

Journals

citations
Cited by 13 publications
(5 citation statements)
references
References 14 publications
0
5
0
Order By: Relevance
“…One approach to optimizing a multipenalty based model using multiple measures of model quality is multicriteria (multiresponse) optimization [1][2][3][4][5][6][7]. Broadly speaking, multicriteria optimization involves "Making a systematic and rational decision of the best alternative among several candidates when multiple (and often conflicting) criteria are present."…”
Section: Introductionmentioning
confidence: 99%
“…One approach to optimizing a multipenalty based model using multiple measures of model quality is multicriteria (multiresponse) optimization [1][2][3][4][5][6][7]. Broadly speaking, multicriteria optimization involves "Making a systematic and rational decision of the best alternative among several candidates when multiple (and often conflicting) criteria are present."…”
Section: Introductionmentioning
confidence: 99%
“…These ordering relationships are represented as graphs, where the objects are the vertexes and the orderings are the edges. In particular, the recently proposed wR-Hasse [50] was used, since it gives an optimal representation when many variables are present and resulted efficient to compare model performances [53]. In this study, we considered a given distance measure as better than the other if it gave higher NER% values in at least the 60% of the cases.…”
Section: General Analysismentioning
confidence: 99%
“…A comprehensive solution to both these shortcomings has been proposed by Grisoni et al [1] in the form of the weighted regularized Hasse method. It is this improved method that has been chosen to solve the discussed problem.…”
Section: Chosen Methodologymentioning
confidence: 99%
“…project team, taking into consideration the weights of the respective criteria. To accomplish that, the approach proposed by Grisoni et al [1] was followed.…”
Section: Selection Proceduresmentioning
confidence: 99%
See 1 more Smart Citation