AFRYCA/features/afryca.consensusmodel.default.feature/feature.properties

#Properties file for afryca.consensusmodel.default.feature
featureName=Default consensus models
providerName=Sinbad\u00B2
description=Default consensus models:\
\
-- Chiclana2008 --\
Paper:\
F. Chiclana, F. Mata, L. Martínez, E. Herrera-Viedma, S. Alonso, Integration of a consistency control module within a consensus model. International Journal of Uncertainty, Fuzziness and Knowledge-based Systems, vol. 16, issue supp01, pp. 35-53, 2008.\
Description:\
A model characterized by an adaptive feedback mechanism, in which the direction rules generated for experts depend on the level of agreement achieved at each round. To do this, three different consensus threshold are utilized. Consensus is computed at three levels based on similarity degrees between pairs of experts in their assessments.\
\
-- HerreraViedma2002 --\
Paper:\
E. Herrera-Viedma, F. Herrera, F. Chiclana, A consensus model for multiperson decision making with different preference structures. IEEE Transactions on Systems, Man and Cybernetics - Part A: Systems and Humans, vol. 32, issue 3, pp. 394-402, 2002.\
Description:\
This model operates with fuzzy preference relations, although in the related paper it is proposed the use of different preference structures by experts. Each expert chooses his/her most suitable preference structure, and they are internally conducted into fuzzy preference relations. Preference orderings and a collective ordering are then computed to measure consensus. Furthermore, the feedback mechanism is based on proximity measures and direction rules.\
\
-- Kacprzyk2010 --\
Papers:\
J. Kacprzyk, S. Zadrozny. Supporting consensus reaching processes under fuzzy preferences and a fuzzy majority via linguistic summaries. Studies in Fuzziness and Soft Computing 257 (2010), pp. 149-157.\
J. Kacprzyk, S. Zadrozny. Soft computing and web intelligence for supporting consensus reaching. Soft Computing 14(2010), pp. 833-846.\
Description:\
Consensus model based on the notion of 'soft consensus' under fuzzy preference relations. Similarities between pairs of experts are computed at level of assessment, as alpha-degrees of sufficient agreement. Consensus degrees are obtained at different levels from such similarities, based on quantifier-guided OWA aggregation. The feedback mechanism identifies the pairs of alternatives with lowest degree of agreement, and then generates recommendations for experts.\
\
-- Palomares2011 --\
Paper:\
I. Palomares, L. Martínez, A Semi-Supervised Multi-Agent System Model to support Consensus Reaching Processes. IEEE Transactions on Fuzzy Systems, In press, DOI: http://dx.doi.org/10.1109/TFUZZ.2013.2272588.\
Description:\
This model was proposed as part of a multi-agent based consensus support system. AFRYCA implements a full automatic version of it, in which a feedback mechanism generates advices on assessments, but agents apply all changes automatically. The model utilized fuzzy preference relations and it computes consensus at three levels, based on degrees of similarity between experts.\
\
-- Palomares2014 --\
Paper:\
I. Palomares, F.J. Quesada, L. Martínez, An Approach based on Computing with Words to Manage Experts Behavior in Consensus Reaching Processes with Large Groups. 2014 International Conference on Fuzzy Systems (FUZZ-IEEE), pp. 476-483, 2014.\
Description:\
Consensus model that incorporates a novel mechanism based on computing with words and fuzzy set theory to assign weights to experts based on their behavior at each round of the consensus process. Each expert's behavior is evaluated based on the amount of received feedback that they apply in favor of consensus, and assigns them an importance weight accordingly, which is taken into account when computing the group preference.\
\
-- Quesada2015 --\
Paper:\
F.J. Quesada, I. Palomares, L. Martínez, Managing Experts Behavior in Large-Scale Consensus Reaching Processes with Uninorm Aggregation Operators. Applied Soft Computing, submitted.\
Description:\
This consensus model extends the one presented in Palomares et al. (FUZZ-IEEE 2014) by introducing an approach based on uninorm aggregation operators to manage the behavior of experts in the consensus process. Due to the full reinforcement property of uninorm operators, they allow to weight experts based not only on their behavior at the current round, but also on their previous behavior since the beginning of the discussion. Furthermore, this approach reinforces positively or negatively the weight of experts with a repeated good or bad behavior, respectively, in several consensus rounds.\
\
-- Wu2012 --\
Paper:\
Z. Wu, J. Xu, A concise consensus support model for group decision making with reciprocal preference relations based on deviation measures. Fuzzy Sets and Systems, vol. 206, pp. 58-73, 2012.\
Description:\
Automatic consensus model based on fuzzy preference relations, in which experts have associated importance weights. Consensus is computed for each expert individually, as the distance between his/her preference and the collective preference. In the update mechanism, experts with low consensus index are identified, and all their assessments are updated by means of an updating coefficient.\
\
-- Xu2013 --\
Paper:\
Y. Xu, K. Li, H. Wang, Distance-based consensus models for fuzzy and multiplicative preference relations. Information Sciences, vol. 253, pp. 56-73, 2013.\
Description:\
Automatic consensus model based on fuzzy preference relations, in which experts have associated importance weights. Consensus is computed at individual and collective level, based on the distance between each preference and the collective preference. The update mechanism identifies assessments of experts farthest to consensus, and applies an update to them by assigning the collective value of such assessments.