Raquel Ureña

Bio: Raquel Ureña is an academic researcher from De Montfort University. The author has contributed to research in topics: Group decision-making & Preference. The author has an hindex of 14, co-authored 41 publications receiving 1136 citations. Previous affiliations of Raquel Ureña include University of Cádiz & University of Granada.

Confidence-consistency driven group decision making approach with incomplete reciprocal intuitionistic preference relations

Abstract: Intuitionistic preference relations constitute a flexible and simple representation format of experts' preference on a set of alternative options, while at the same time allowing to accommodate degrees of hesitation inherent to all decision making processes. In comparison with fuzzy preference relations, the use of intuitionistic fuzzy preference relations in decision making is limited, which is mainly due to the computational complexity associated to using membership degree, non-membership degree and hesitation degree to model experts' subjective preferences. In this paper, the set of reciprocal intuitionistic fuzzy preference relations and the set of asymmetric fuzzy preference relations are proved to be mathematically isomorphic. This result can be exploited to use methodologies developed for fuzzy preference relations to the case of intuitionistic fuzzy preference relations and, ultimately, to overcome the computation complexity mentioned above and to extend the use of reciprocal intuitionistic fuzzy preference relations in decision making. In particular, in this paper, this isomorphic equivalence is used to address the presence of incomplete reciprocal intuitionistic fuzzy preference relations in decision making by developing a consistency driven estimation procedure via the corresponding equivalent incomplete asymmetric fuzzy preference relation procedure. Additionally, the hesitancy degree of the reciprocal intuitionistic fuzzy preference relation is used to introduce the concept of expert's confidence from which a group decision making procedure, based on a new aggregation operator that takes into account not only the experts' consistency but also their confidence degree towards the opinion provided, is proposed.

Automatic Facial Expression Recognition Using Features of Salient Facial Patches

Abstract: Extraction of discriminative features from salient facial patches plays a vital role in effective facial expression recognition. The accurate detection of facial landmarks improves the localization of the salient patches on face images. This paper proposes a novel framework for expression recognition by using appearance features of selected facial patches. A few prominent facial patches, depending on the position of facial landmarks, are extracted which are active during emotion elicitation. These active patches are further processed to obtain the salient patches which contain discriminative features for classification of each pair of expressions, thereby selecting different facial patches as salient for different pair of expression classes. One-against-one classification method is adopted using these features. In addition, an automated learning-free facial landmark detection technique has been proposed, which achieves similar performances as that of other state-of-art landmark detection methods, yet requires significantly less execution time. The proposed method is found to perform well consistently in different resolutions, hence, providing a solution for expression recognition in low resolution images. Experiments on CK+ and JAFFE facial expression databases show the effectiveness of the proposed system.

Trust based consensus model for social network in an incomplete linguistic information context

Abstract: Graphical abstract(A) Trust propagating aggregation and visual consensus model for MCGDM under incomplete information. (B) Visual feedback simulation: consensus levels before and after recommendations implemented by experts. Display Omitted HighlightsA theoretical framework to build consensus within a networked social group is presented.A novel trust propagation method is proposed to derive trust relationship from an incomplete connected trust network.A visual feedback process including a recommendation mechanism to provide individualised advice is implemented.The implementation of the visual feedback mechanism guarantees the convergence of the consensus reaching process. A theoretical framework to consensus building within a networked social group is put forward. This article investigates a trust based estimation and aggregation methods as part of a visual consensus model for multiple criteria group decision making with incomplete linguistic information. A novel trust propagation method is proposed to derive trust relationship from an incomplete connected trust network and the trust score induced order weighted averaging operator is presented to aggregate the orthopairs of trust/distrust values obtained from different trust paths. Then, the concept of relative trust score is defined, whose use is twofold: (1) to estimate the unknown preference values and (2) as a reliable source to determine experts' weights. A visual feedback process is developed to provide experts with graphical representations of their consensus status within the group as well as to identify the alternatives and preference values that should be reconsidered for changing in the subsequent consensus round. The feedback process also includes a recommendation mechanism to provide advice to those experts that are identified as contributing less to consensus on how to change their identified preference values. It is proved that the implementation of the visual feedback mechanism guarantees the convergence of the consensus reaching process.

Automatic Facial Expression Recognition Using Features of Salient Facial Patches

Abstract: Extraction of discriminative features from salient facial patches plays a vital role in effective facial expression recognition. The accurate detection of facial landmarks improves the localization of the salient patches on face images. This paper proposes a novel framework for expression recognition by using appearance features of selected facial patches. A few prominent facial patches, depending on the position of facial landmarks, are extracted which are active during emotion elicitation. These active patches are further processed to obtain the salient patches which contain discriminative features for classification of each pair of expressions, thereby selecting different facial patches as salient for different pair of expression classes. One-against-one classification method is adopted using these features. In addition, an automated learning-free facial landmark detection technique has been proposed, which achieves similar performances as that of other state-of-art landmark detection methods, yet requires significantly less execution time. The proposed method is found to perform well consistently in different resolutions, hence, providing a solution for expression recognition in low resolution images. Experiments on CK+ and JAFFE facial expression databases show the effectiveness of the proposed system.