Informatica

The 2-tuple linguistic computational model is an important tool to deal with linguistic information. To extend the application of hesitant fuzzy linguistic term sets and avoid information loss, this paper introduces hesitant fuzzy 2-tuple linguistic term sets that are expressed by using several symbolic numbers in $[0\mathrm{,}1]$. Considering the order relationship between hesitant fuzzy 2-tuple linguistic term sets, measures of expected value and variance are defined. Meanwhile, several induced generalized hesitant fuzzy 2-tuple linguistic aggregation operators are defined, by which the comprehensive attribute values of alternatives can be obtained. Then, models for the optimal weight vector on a decision maker set, on an attribute set and on their ordered sets are constructed, respectively. Furthermore, an approach to multi-granularity group decision making with hesitant fuzzy linguistic information is developed. Finally, an example is selected to illustrate the feasibility and practicality of the proposed procedure.

In this paper, we focus on group decision making problems with uncertain preference ordinals, in which the weight information of decision makers is completely unknown or partly unknown. First of all, the consistency and deviation measures between two uncertain preference ordinals are defined. Based on the two measures, a multi-objective optimization model which aims to maximize the deviation of each decision maker’s judgements and the consistency among different decision makers’ judgements is established to obtain the weights of decision makers. The compromise solution method, i.e. the VIKOR method is then extended to derive the compromise solution of alternatives for group decision making problems with uncertain preference ordinals. Finally, three examples are utilized to illustrate the feasibility and effectiveness of the proposed approach.

We present a new aggregation operator called the generalized ordered weighted proportional averaging (GOWPA) operator based on an optimal model with penalty function, which extends the ordered weighted geometric averaging (OWGA) operator. We investigate some properties and different families of the GOWPA operator. We also generalize the GOWPA operator. The key advantage of the GOWPA operator is that it is an aggregation operator with theoretic basis on aggregation, which focuses on its structure and importance of arguments. Moreover, we propose an orness measure of the GOWPA operator and indicate some properties of this orness measure. Furthermore, we introduce the generalized least squares method (GLSM) to determine the GOWPA operator weights based on its orness measure. Finally, we present a numerical example to illustrate the new approach in an investment selection decision making problem.

The aim of this paper is to investigate intuitionistic fuzzy multiple attribute group decision making problems where the attribute values provided by experts are expressed in intuitionistic fuzzy numbers, and the weight information about the experts is to be determined. We present a new method to derive the weights of experts and rank the preference order of alternatives based on projection models. We first derive the weights of the decision makers according to the projection of the individual decision on the ideal decision. The expert has a large weight if his evaluation value is close to the ideal decision, and has a small weight if his evaluation value is far from the ideal decision. Then, based on the weighted projection of the alternatives on the intuitionistic fuzzy ideal solution (IFIS), we develop a straightforward and practical algorithm to rank alternatives. Furthermore, we extend the developed model and algorithm to the multiple attribute group decision making problems with interval-valued intuitionistic fuzzy information. Finally, an illustrative example is given to verify the developed approach and to demonstrate its practicality and effectiveness.

Speaker identification problem is investigated. The identification is carried out comparing feature vectors (parameters of LPC model) of the “criminal” and “suspicious” speakers. Both likelihood ratio and cepstral distances are used for comparing feature vectors. The feature vectors are extracted from pseudostationary parts of speech utterances. The identification approach is suitable for text-dependent and text-independent identification. Experimental results illustrate the performance of the algorithm.