Fusion of imprecise qualitative information

In this paper, we present a new 2-tuple linguistic representation model, i.e. Distribution Function Model (DFM), for combining imprecise qualitative information using fusion rules drawn from Dezert-Smarandache Theory (DSmT) framework. Such new approach allows to preserve the precision and efficiency of the combination of linguistic information in the case of either equidistant or unbalanced label model. Some basic operators on imprecise 2-tuple labels are presented together with their extensions for imprecise 2-tuple labels. We also give simple examples to show how precise and imprecise qualitative information can be combined for reasoning under uncertainty. It is concluded that DSmT can deal efficiently with both precise and imprecise quantitative and qualitative beliefs, which extends the scope of this theory.     

An interval 2-Tuple linguistic Fine-Kinney model for risk analysis based on extended ORESTE method with cumulative prospect theory

The risk assessment is one of the most significant procedures for identifying, preventing, and controlling Occupational Health and Safety (OHS) risks. One of many kinds of techniques for OHS risk assessment is based on the Fine-Kinney model. Most of the Fine-Kinney-based risk assessment approaches can consider the relative importance degree of risk parameters. Nevertheless, the current Fine-Kinney-based risk assessment approaches do not have abilities to capture the reference dependence effects and detailed relationships among hazards. In addition, these approaches overlook the influence of the deviation of risk evaluation information. To overcome these limitations, in this paper, an improved Fine-Kinney model is proposed for OHS risk assessment by integrating the weighted power average (WPA) operator, ORESTE (Organísation, rangement et Synthèse de données relarionnelles (in French)) method, and cumulative prospect theory. First, the interval 2-Tuple linguistic variables are adopted to transform linguistic risk information into quantitative risk rating information. Then, an extended WPA operator is proposed to fuse the risk evaluation information from decision-makers, in which an optimization model is constructed to determine the weights of decision-makers. Next, an extended ORESTE method based on cumulative prospect theory and interval 2-Tuple linguistic variables is incorporated into the Fine-Kinney model to prioritize OHS risk. After that, the OHS risk assessment of the automobile components manufacturing process is presented to test the applicability and rationality of the improved Fine-Kinney model. After that, a sensitivity analysis is conducted to further illustrate the proposed model. Finally, the comparative analyses between the proposed risk assessment approach and other Fine-Kinney models are led to illustrating its effectiveness and advantages.     

Multi-period multi-attribute group decision-making under linguistic assessments

In fuzzy environments, decision information is more suitable to be expressed in linguistic labels than exact numerical values. Group decision-making with linguistic assessments has received more and more attention over the last decades. Most research on this topic has focused on situations where all the original decision information is provided at the same time and refers to one and same period. However, in many decision areas, such as multi-period investment decision-making, medical diagnosis, personnel dynamic examination, military system efficiency dynamic evaluation, etc., the original decision information is usually collected at different periods and/or refers to different moments in time. This paper investigates the multi-period multi-attribute group decision-making problems where all decision information is expressed by decision-makers in multiplicative linguistic labels at different periods. The paper first introduces a new operator called a dynamic linguistic weighted geometric (DLWG) operator and uses the minimum variability model to derive the time series weights associated with the DLWG operator, and then utilises, respectively, the linguistic weighted geometric (LWG) operator and the DLWG operator to aggregate the given linguistic labels. Moreover, the paper develops an approach to multi-period multiple attribute group decision-making under linguistic assessments so as to derive the final ranking of alternatives, and finally, gives an illustrative example and extends the above results to uncertain linguistic environments.     

A new version of 2-tuple fuzzy linguistic representation model for computing with words

In this paper, we provide a new (proportional) 2-tuple fuzzy linguistic representation model for computing with words (CW), which is based on the concept of "symbolic proportion." This concept motivates us to represent the linguistic information by means of 2-tuples, which are composed by two proportional linguistic terms. For clarity and generality, we first study proportional 2-tuples under ordinal contexts. Then, under linguistic contexts and based on canonical characteristic values (CCVs) of linguistic labels, we define many aggregation operators to handle proportional 2-tuple linguistic information in a computational stage for CW without any loss of information. Our approach for this proportional 2-tuple fuzzy linguistic representation model deals with linguistic labels, which do not have to be symmetrically distributed around a medium label and without the traditional requirement of having "equal distance" between them. Moreover, this new model not only provides a space to allow a "continuous" interpolation of a sequence of ordered linguistic labels, but also provides an opportunity to describe the initial linguistic information by members of a "continuous" linguistic scale domain which does not necessarily require the ordered linguistic terms of a linguistic variable being equidistant. Meanwhile, under the assumption of equally informative (which is defined by a condition based on the concept of CCV), we show that our model reduces to Herrera and Mart/spl inodot//spl acute/nez's (translational) 2-tuple fuzzy linguistic representation model.     

A 2-tuple fuzzy linguistic representation model for computing withwords

The fuzzy linguistic approach has been applied successfully to many problems. However, there is a limitation of this approach imposed by its information representation model and the computation methods used when fusion processes are performed on linguistic values. This limitation is the loss of information; this loss of information implies a lack of precision in the final results from the fusion of linguistic information. In this paper, we present tools for overcoming this limitation. The linguistic information is expressed by means of 2-tuples, which are composed of a linguistic term and a numeric value assessed in (-0.5, 0.5). This model allows a continuous representation of the linguistic information on its domain, therefore, it can represent any counting of information obtained in a aggregation process. We then develop a computational technique for computing with words without any loss of information. Finally, different classical aggregation operators are extended to deal with the 2-tuple linguistic model     

A model for linguistic partial information in decision-making problems

A model is proposed for dealing with decision-making problems in which the decision maker has a vague (linguistically assessed) and incomplete information about results and external factors (a quite usual situation in real decision cases). It is assumed here that utilities are evaluated in a term set of labels and the incomplete information is supposed to be a partial linguistic assignment of probability with values on a term set of linguistic likelihoods. the first step is to discuss a well-fitted interpretation of that model. After that, basic decision rules based on fuzzy risk intervals are developed. Additionally the suitability of considering a hierarchical structure (represented by a tree) for the set of utility labels is analyzed. © 1994 John Wiley & Sons, Inc.     

Linguistic multi-criteria decision-making model with output variable expressive richness

In general, traditional decision-making models are based on methods that perform calculations on quantitative measures. These methods are usually applied to assess possible solutions to a problem, resulting in a ranking of alternatives. However, when it comes to making decisions about qualitative measures —such as service quality—, the quantitative assessment is a bit difficult to interpret. Therefore, taking into account the maturity of the linguistic assessment models, this paper puts forth a new solution proposal. It is a decision-making model that uses linguistic labels —represented with the 2-tuple notation— and a variable expressive richness when providing output results. This solution allows expressing results in a manner closer to the human cognitive system. To achieve this goal, a mechanism has been implemented for measuring the distance among the aggregate ratings, providing the decision-maker with a fast and intuitive answer. The proposal is illustrated with an application example based on the TOPSIS model, using linguistic labels throughout the entire process.     

Linguistic decision-making models

Using linguistic values to assess results and information about external factors is quite usual in real decision situations. In this article we present a general model for such problems. Utilities are evaluated in a term set of labels and the information is supposed to be a linguistic evidence, that is, is to be represented by a basic assignment of probability (in the sense of Dempster-Shafer) but taking its values on a term set of linguistic likelihoods. Basic decision rules, based on fuzzy risk intervals, are developed and illustrated by several examples. the last section is devoted to analyzing the suitability of considering a hierarchical structure (represented by a tree) for the set of utility labels. © 1992 John Wiley & Sons, Inc.     

融合CNN-SAM与GAT的多标签文本分类模型

现有基于神经网络的多标签文本分类研究方法存在两方面不足,一是不能全面提取文本信息特征,二是很少从图结构数据中挖掘全局标签之间的关联性。针对以上两个问题,提出融合卷积神经网络-自注意力机制（CNNSAM）与图注意力网络（GAT）的多标签文本分类模型（CS-GAT）。该模型利用多层卷积神经网络与自注意力机制充分提取文本局部与全局信息并进行融合,得到更为全面的特征向量表示;同时将不同文本标签之间的关联性转变为具有全局信息的边加权图,利用多层图注意力机制自动学习不同标签之间的关联程度,将其与文本上下文语义信息进行交互,获取具有文本语义联系的全局标签信息表示;使用自适应融合策略进一步提取两者特征信息,提高模型的泛化能力。在AAPD、RCV1-V2与EUR-Lex三个公开英文数据集上的实验结果表明,该模型所达到的多标签分类效果明显优于其他主流基线模型。     

Multicriteria decision making with 2‐dimension linguistic aggregation techniques

In this paper, we represent evaluation information by 2‐dimension linguistic labels so as to avoid biased results and achieve high accuracy in multicriteria decision making. We analyze the relationship between a 2‐dimension linguistic label and a common linguistic label, and then quantify a certain 2‐dimension linguistic label by using a generalized triangular fuzzy number (TFN). On the basis of the mapping function from 2‐dimension linguistic labels to the corresponding generalized TFNs and its inverse function, we develop a 2‐dimension linguistic weighted averaging (2DLWA) operator and a 2‐dimension linguistic ordered weighted averaging (2DLOWA) operator. Furthermore, we verify the feasibility of the 2DLWA and 2DLOWA operators by discussing their properties and investigating their applications to produce reliable decision results in multicriteria decision making under linguistic evaluations. Finally, an example of selecting the outstanding postgraduate dissertation(s) is used to illustrate the practicability and validity of these two 2‐dimension linguistic aggregation techniques. © 2012 Wiley Periodicals, Inc.     

A Proposal for the Genetic Lateral Tuning of Linguistic Fuzzy Systems and Its Interaction With Rule Selection

Linguistic fuzzy modeling allows us to deal with the modeling of systems by building a linguistic model which is clearly interpretable by human beings. However, since the accuracy and the interpretability of the obtained model are contradictory properties, the necessity of improving the accuracy of the linguistic model arises when complex systems are modeled. To solve this problem, one of the research lines in recent years has led to the objective of giving more accuracy to linguistic fuzzy modeling without losing the interpretability to a high level. In this paper, a new postprocessing approach is proposed to perform an evolutionary lateral tuning of membership functions, with the main aim of obtaining linguistic models with higher levels of accuracy while maintaining good interpretability. To do so, we consider a new rule representation scheme base on the linguistic 2-tuples representation model which allows the lateral variation of the involved labels. Furthermore, the cooperation of the lateral tuning together with fuzzy rule reduction mechanisms is studied in this paper, presenting results on different real applications. The obtained results show the good performance of the proposed approach in high-dimensional problems and its ability to cooperate with methods to remove unnecessary rules.     

HNLOWA集成算法应用于推荐系统评估

针对复杂决策环境下的决策者倾向于使用定性评价数据和现实环境中数据信息通常存在正态分布规律的问题,构建了基于犹豫正态语言有序加权平均（hesitant normal linguistic ordered weighted average,HNLOWA）算子的决策模型。将正态模糊数和犹豫模糊语言元相结合,引入了犹豫正态语言元（hesitant normal linguistic element,HNLE）的概念,其不仅能够运用语言变量来描述决策信息,还能传递出语言决策信息的分布情况;定义了HNLE之间的基本运算法则和大小判别准则,并设计HNLOWA算子用于对HNLE进行信息融合,同时探究了HNLOWA算子的相关性质;构建了基于HNLOWA集成算子的多属性决策方法,并运用推荐系统选择评估案例进行了模型的验证分析。     

A framework for semiqualitative reasoning in engineering applications

In most cases the models for experimentation, analysis, or design in engineering applications take into account only quantitative knowledge. Sometimes there is a qualitative knowledge that is convenient to consider in order to obtain better conclusions. These qualitative concepts can be labels such as ''high,'' ''very negative,'' ''little acid,'' ''monotonically increasing'' or symbols such as >>, , , etc… Engineers have already used this type of knowledge implicitly in many activities. The framework that we present here lets us express explicitly this knowledge. This work makes the following contributions. First, we identify the most important classes of qualitative concepts in engineering activities. Second, we present a novel methodology to integrate both qualitative and quantitative knowledge. Third, we obtain significant conclusions automatically. It is named semiqualitative reasoning. Qualitative concepts are represented by means of closed real intervals. This approximation is accepted in the area of Artificial Intelligence. A modeling language is specified to represent qualitative and quantitative knowledge of the model. A numeric constraint satisfaction problem is obtained by means of corresponding rules of transformation of the semantics of this language. In order to obtain conclusions, we have developed algorithms that treat the problem in a symbolic and numeric way. The interval conclusions obtained are transformed into qualitative labels through a linguistic interpretation. Finally, the capabilities of this methodology are illustrated on different problems.     

A quality evaluation methodology for health-related websites based on a 2-tuple fuzzy linguistic approach

Nowadays, the patients and physicians use the health-related websites as an important information source and, therefore, it is critical the quality evaluation of health- related websites. The quality assessment of health-related websites becomes especially relevant because their use imply the existence of a wide range of threats which can affect people’s health. Additionally, website quality evaluation can also contribute to maximize the exploitation of invested resources by organizations in the development of user-perceived quality websites. But there is not yet a clear and unambiguous definition of the concept of website quality and the debate about quality evaluation on the Web remains open. In this paper, we present a qualitative and user-oriented methodology for assessing quality of health-related websites based on a 2-tuple fuzzy linguistic approach. To identify the quality criteria set, a qualitative research has been carried out using the focus groups technique. The measurement method generates linguistic quality assessments considering the visitors’ judgements with respect to those quality criteria. The combination of the linguistic judgements is implemented without a loss of information by applying a 2-tuple linguistic weighted average operator. This methodology means an improvement on quality evaluation of health websites through the commitment to put users first.     

Constructing <Emphasis Type="Italic">n</Emphasis>-gram rules for natural language models through exploring the limitation of the Zipf–Mandelbrot law

The Zipf–Mandelbrot law is widely used to model a power-law distribution on ranked data. One of the best known applications of the Zipf–Mandelbrot law is in the area of linguistic analysis of the distribution of words ranked by their frequency in a text corpus. By exploring known limitations of the Zipf–Mandelbrot law in modeling the actual linguistic data from different domains in both printed media and online content, a new algorithm is developed to effectively construct n-gram rules for building natural language (NL) models required for a human-to-computer interface. The construction of statistically-oriented n-gram rules is based on a new computing algorithm that identifies the area of divergence between Zipf–Mandelbrot curve and the actual frequency distribution of the ranked n-gram text tokens extracted from a large text corpus derived from the online electronic programming guide (EPG) for television shows and movies. Two empirical experiments were carried out to evaluate the EPG-specific language models created using the new algorithm in the context of NL-based information retrieval systems. The experimental results show the effectiveness of the algorithm for developing low-complexity concept models with high coverage for the user’s language models associated with both typed and spoken queries when interacting with a NL-based EPG search interface.     

A comparative study on automatic audio–visual fusion for aggression detection using meta-information

Multimodal fusion is a complex topic. For surveillance applications audio–visual fusion is very promising given the complementary nature of the two streams. However, drawing the correct conclusion from multi-sensor data is not straightforward. In previous work we have analysed a database with audio–visual recordings of unwanted behavior in trains (Lefter et al., 2012) and focused on a limited subset of the recorded data. We have collected multi- and unimodal assessments by humans, who have given aggression scores on a 3 point scale. We showed that there are no trivial fusion algorithms to predict the multimodal labels from the unimodal labels since part of the information is lost when using the unimodal streams. We proposed an intermediate step to discover the structure in the fusion process. This step is based upon meta-features and we find a set of five which have an impact on the fusion process. In this paper we extend the findings in (Lefter et al., 2012) for the general case using the entire database. We prove that the meta-features have a positive effect on the fusion process in terms of labels. We then compare three fusion methods that encapsulate the meta-features. They are based on automatic prediction of the intermediate level variables and multimodal aggression from state of the art low level acoustic, linguistic and visual features. The first fusion method is based on applying multiple classifiers to predict intermediate level features from the low level features, and to predict the multimodal label from the intermediate variables. The other two approaches are based on probabilistic graphical models, one using (Dynamic) Bayesian Networks and the other one using Conditional Random Fields. We learn that each approach has its strengths and weaknesses in predicting specific aggression classes and using the meta-features yields significant improvements in all cases.     

A hierarchical fuzzy system for modeling driver’s behavior

The study of human behavior during driving is of primary importance for improving the driver??s security. In this study, we propose a hierarchical driver_vehicle_environment fuzzy system to analyze driver??s behavior under stress conditions on a road. We include climate, road and car conditions in fuzzy modeling. For obtaining fuzzy rules, experts?? opinions are benefited by means of questionnaires on effects of parameters such as climate, road and car conditions on driving capabilities. The number of fuzzy rules is optimized by Particle Swarm Optimization (PSO) algorithm. Also the frequency of pressing on brake and gas pedals and the number of car??s direction changes are used to determine the driver??s behavior under different conditions. Three different positions are considered for driving and decision making; one position in driving lane and two positions in opposite lane. A fuzzy model called Model 1 is presented for modeling the change of steering angle and speed control by considering time distances with existing cars in these three positions, the information about the speed and direction of car, and the steering angle of car. The behaviors of different drivers under two stress conditions are investigated. Also we obtained two other models based on fuzzy rules called Model 2 and Model 3 by using Sugeno fuzzy inference. Model 2 has two linguistic terms and Model 3 has four linguistic terms for estimating the time distances with other cars. The results of three models are compared. The comparative studies have shown that simulation results are in good agreement with the real world situations.     

Grey relational analysis model for dynamic hybrid multiple attribute decision making

In this paper, the dynamic hybrid multiple attribute decision making problems, in which the decision information, provided by decision makers at different periods, is expressed in real numbers, interval numbers or linguistic labels (linguistic labels can be described by triangular fuzzy numbers), respectively, are investigated. The method first utilizes three different GRA (grey relational analysis (real-valued GRA, interval-valued GRA and fuzzy-valued GRA) to calculate the individual grey relational degree of each alternative to the positive and negative ideal alternatives based on the decision information expressed in real numbers, interval numbers and linguistic labels, respectively, provided by each decision maker at each period, and then adopt the concept of fuzzy membership grade and clustering to aggregate the grey relational degree of all the evaluated periods. Finally, an illustrative example is given to verify the developed approach and to demonstrate its practicality and effectiveness.     

Type‐1 OWA Unbalanced Fuzzy Linguistic Aggregation Methodology: Application to Eurobonds Credit Risk Evaluation

In decision making, a widely used methodology to manage unbalanced fuzzy linguistic information is the linguistic hierarchy (LH), which relies on a linguistic symbolic computational model based on ordinal 2‐tuple linguistic representation. However, the ordinal 2‐tuple linguistic approach does not exploit all advantages of Zadeh's fuzzy linguistic approach to model uncertainty because the membership function shapes are ignored. Furthermore, the LH methodology is an indirect approach that relies on the uniform distribution of symmetric linguistic assessments. These drawbacks are overcome by applying a fuzzy methodology based on the implementation of the type‐1 ordered weighted average (T1OWA) operator. The T1OWA operator is not a symbolic operator and it allows to directly aggregate membership functions, which in practice means that the T1OWA methodology is suitable for both balanced and unbalanced linguistic contexts and with heterogeneous membership functions. Furthermore, the final output of the T1OWA methodology is always fuzzy and defined in the same domain of the original unbalanced fuzzy linguistic labels, which facilitates its interpretation via a visual joint representation. A case study is presented where the T1OWA operator methodology is used to assess the creditworthiness of European bonds based on real credit risk ratings of individual Eurozone member states modeled as unbalanced fuzzy linguistic labels.     

Implementing an extension of the analytical hierarchy process using ordered weighted averaging operators with fuzzy quantifiers in ArcGIS

This paper focuses on the integration of GIS and an extension of the analytical hierarchy process (AHP) using quantifier-guided ordered weighted averaging (OWA) procedure. AHP_OWA is a multicriteria combination operator. The nature of the AHP_OWA depends on some parameters, which are expressed by means of fuzzy linguistic quantifiers. By changing the linguistic terms, AHP_OWA can generate a wide range of decision strategies. We propose a GIS-multicriteria evaluation (MCE) system through implementation of AHP_OWA within ArcGIS, capable of integrating linguistic labels within conventional AHP for spatial decision making. We suggest that the proposed GIS-MCE would simplify the definition of decision strategies and facilitate an exploratory analysis of multiple criteria by incorporating qualitative information within the analysis.