Associated probabilities aggregations in multistage investment decision-making

PurposeThe attributes that influence the selection of applicants and the relevant crediting decisions are naturally distinguished by interactions and interdependencies. A new method of possibilistic discrimination analysis (MPDA) was developed for the second stage to address this phenomenon. The method generates positive and negative discrimination measures for each alternative applicant in relation to a particular attribute. The obtained discrimination pair reflects the interaction of attributes and represents intuitionistic fuzzy numbers (IFNs). For the aggregation of applicant's discrimination intuitionistic fuzzy assessments (with respect to attributes), new intuitionistic aggregation operators, such as AsP-IFOWA and AsP-IFOWG, are defined and studied. The new operators are certain extensions of the well-known Choquet integral and Yager OWA operators. The extensions, in contrast to the Choquet aggregation, take into account all possible interactions of the attributes by introducing associated probabilities of a fuzzy measure.Design/methodology/approachFor optimal planning of investments distribution and decreasing of credit risks, it is crucial to have selected projects ranked within deeply detailed investment model. To achieve this, a new approach developed in this article involves three stages. The first stage is to reduce a possibly large number of applicants for credit, and here, the method of expertons is used. At the second stage, a model of improved decisions is built, which reduces the risks of decision making. In this model, as it is in multi-attribute decision-making (MADM) + multi-objective decision-making (MODM), expert evaluations are presented in terms of utility, gain, and more. At the third stage, the authors construct the bi-criteria discrete intuitionistic fuzzy optimization problem for making the most profitable investment portfolio with new criterion: 1) Maximization of total ranking index of selected applicants' group and classical criterion and 2) Maximization of total profit of selected applicants' group.FindingsThe example gives the Pareto fronts obtained by both new operators, the Choquet integral and Yager OWA operators also well-known TOPSIS approach, for selecting applicants and awarding credits. For a fuzzy measure, the possibility measure defined on the expert evaluations of attributes is taken.Originality/valueThe comparative analysis identifies the applicants who will receive the funding sequentially based on crediting resources and their requirements. It has become apparent that the use of the new criterion has given more credibility to applicants in making optimal credit decisions in the environment of extended new operators, where the phenomenon of interaction of all attributes was also taken into account.

Segmenting the Optic Disc Using a Deep Learning Ensemble Model Based on OWA Operators

The optic disc (OD) is the point where the retinal vessels begin. OD carries essential information linked to Diabetic Retinopathy and glaucoma that may cause vision loss. Therefore, accurate segmentation of the optic disc from eye fundus images is essential to develop efficient automated DR and glaucoma detection systems. This paper presents a deep learning-based system for OD segmentation based on an ensemble of efficient semantic segmentation models for medical image segmentation. The aggregation of the different DL models was performed with the ordered weighted averaging (OWA) operators. We proposed the use of a dynamically generated set of weights that can give a different contribution to the models according to their performance during the segmentation of OD in the eye fundus images. The effectiveness of the proposed system was assessed on a fundus image dataset collected from the Hospital Sant Joan de Reus. We obtained Jaccard, Dice, Precision, and Recall scores of 95.40, 95.10, 96.70, and 93.90%, respectively.

A Study of OWA Operators Learned in Convolutional Neural Networks

Ordered Weighted Averaging (OWA) operators have been integrated in Convolutional Neural Networks (CNNs) for image classification through the OWA layer. This layer lets the CNN integrate global information about the image in the early stages, where most CNN architectures only allow for the exploitation of local information. As a side effect of this integration, the OWA layer becomes a practical method for the determination of OWA operator weights, which is usually a difficult task that complicates the integration of these operators in other fields. In this paper, we explore the weights learned for the OWA operators inside the OWA layer, characterizing them through their basic properties of orness and dispersion. We also compare them to some families of OWA operators, namely the Binomial OWA operator, the Stancu OWA operator and the exponential RIM OWA operator, finding examples that are currently impossible to generalize through these parameterizations.

Deriving pertinent systems requirements : a methodology

Poor understanding of needs results in incompletely captured requirements and causes project failures. Analysts and developers by training, practice preoccupation and lacking suitable methodologies are ill equipped to capture various dimensions of requirements. In early stages needs are vaguely expressed. They have to be extracted and reasoned with stakeholders using relevant vocabulary. Business reality limits time at stakeholders' disposal to participate in requirements development. Methodologies that are more workable are required. Working with early stage goal oriented concepts from Goal Oriented Requirements Engineering (GORE) and fuzzy set theory based value aggregation, this thesis proposes a methodology to develop and select pertinent requirements. We use GORE concepts for identifying requirements and fuzzy aggregation to select alternatives. Use of fuzzy set theory and Ordered Weighted Aggregation (OWA) operators allows quantitative structuring of early stage decision problem consistent with human thinking and reasoning. The methodology is illustrated via two case studies.

Deriving pertinent systems requirements : a methodology

Poor understanding of needs results in incompletely captured requirements and causes project failures. Analysts and developers by training, practice preoccupation and lacking suitable methodologies are ill equipped to capture various dimensions of requirements. In early stages needs are vaguely expressed. They have to be extracted and reasoned with stakeholders using relevant vocabulary. Business reality limits time at stakeholders' disposal to participate in requirements development. Methodologies that are more workable are required. Working with early stage goal oriented concepts from Goal Oriented Requirements Engineering (GORE) and fuzzy set theory based value aggregation, this thesis proposes a methodology to develop and select pertinent requirements. We use GORE concepts for identifying requirements and fuzzy aggregation to select alternatives. Use of fuzzy set theory and Ordered Weighted Aggregation (OWA) operators allows quantitative structuring of early stage decision problem consistent with human thinking and reasoning. The methodology is illustrated via two case studies.

Sustainable Development Goals Analysis with Ordered Weighted Average Operators

The present research proposes a new method to analyze the sustainable development goals (SDGs) index using ordered weighted average (OWA) operators. To develop this method, five experts evaluated and designated the relative importance of each of the 17 SDGs defined by the United Nations (UN), and with the use of the OWA and prioritized OWA (POWA) operators, rankings were generated. With the results, it is possible to visualize that the ranking of countries can change depending on the weights related to each SDG because the OWA and POWA operator methods can capture the uncertainty of the phenomenon.

OWA aggregation with dual preferences for basic uncertain information

Basic Uncertain Information (BUI) as a newly introduced concept generalized a wide range of uncertain information. The well-known Ordered Weighted Averaging (OWA) operators can flexibly and effectively model bipolar preferences of decision makers over given real valued input vector. However, there are no extant methods for OWA operators to be carried out over given BUI vectors. Against this background, this study firstly discusses the interval transformation for BUI and elaborately explains the reasonability within it. Then, we propose the corresponding preference aggregations for BUI in two different decisional scenarios, the aggregation for BUI vector without original information influencing and the aggregation for BUI vector with original information influencing after interval transformation. For each decisional scenario, we also discuss two different orderings of preference aggregation, namely, interval-vector and vector-interval orderings, respectively. Hence, we will propose four different aggregation procedures of preference aggregation for BUI vector. Some illustrative examples are provided immediately after the corresponding aggregation procedures.