Showing papers in "International Journal of Approximate Reasoning in 2018"

TL;DR: It is suggested that, in many situations, the power of granular computing is indeed thePower of three-way decision, i.e., thinking in threes.

TL;DR: A novel correlation coefficient is proposed which takes into consideration both the non-intersection and the difference among the focal elements and satisfies all the requirements for a metric.

TL;DR: A new definition of entropy of basic probability assignments in the Dempster–Shafer theory of belief functions, which is interpreted as a measure of total uncertainty in the BPA, is proposed, which satisfies all six properties in the list, whereas none of the existing definitions do.

TL;DR: The proposed decision model and method is applied to an emergency decision making problem of unconventional emergency events and the steps and the principle of the proposed method are illustrated by a numerical example with the background of emergency decision-making.

TL;DR: A review of fuzzy set theory based methodologies applied to safety and reliability engineering, which include fuzzy FTA, fuzzy FMEA, fuzzy ETA, fuzzy Bayesian networks, fuzzy Markov chains, and fuzzy Petri nets is presented.

TL;DR: A theoretic framework called local rough set is introduced, and a series of corresponding concept approximation and attribute reduction algorithms with linear time complexity are developed, which can efficiently and effectively work in limited labeled big data.

TL;DR: Experimental results on four datasets from UCI machine learning repository suggests that the GTRS significantly improves the generality while keeping similar levels of accuracy in comparison to other three-way and similar models.

TL;DR: In this article, the authors proposed revised axioms for defining inconsistency indicators in pairwise comparisons, including the new findings that PC submatrix cannot have a worse inconsistency indicator than the PC matrix containing it and that there must be a PC sub-matrix with the same inconsistency as the given PC matrix.

TL;DR: This work introduces the concept of an inconsistency degree in an incomplete decision system and proves that the attribute reduction based on the inconsistency degree is equivalent to thatbased on the positive region and proposes the framework of the incremental attribute reduction algorithm.

TL;DR: This work proposes a joint model of multiple Convolutional Neural Networks in which each individual representation of the input is handled by one CNN, and focuses on three kinds of representation including word embeddings from the two methods and the one-hot character vectors.

TL;DR: This paper investigates information structures and uncertainty measures in a fully fuzzy information system, and results will be very helpful for establishing a framework of granular computing in information systems.

TL;DR: Four clustering models for multivariate time series are proposed, with the following characteristics: the Partitioning Around Medoids (PAM) framework is considered, and a robust metric approach is used, i.e., the exponential transformation of dissimilarity measures.

TL;DR: The authors compare the results of an experiment in which participants were asked to judge dialogues in terms of agreement and structure and compare their findings with the aforementioned assumptions as well as with the constellation and epistemic approaches to probabilistic argumentation and bipolar argumentation.

TL;DR: This paper presents an approach that takes advantage of the possible conceptual domains' overlaps for build general models able to compute the polarity of texts belonging to arbitrary domains and demonstrates the effectiveness of the presented strategy.

TL;DR: A general unified approach to Interval Pairwise Comparison Matrices, based on Abelian linearly ordered groups is proposed, which will be able to compare the inconsistency and the indeterminacy of different kinds of Interval pairs, e.g. multiplicative, additive, and fuzzy, on a unique Cartesian coordinate system.

TL;DR: A new Semi-supervised clustering approach based on an Evidential Label Propagation strategy (SELP) is proposed to incorporate limited domain knowledge into the community detection model and demonstrates the effectiveness of SELP on both graphs and classical data sets.

TL;DR: In this model, three-way decisions is responsible for minimizing uncertainty, whereas ensemble learning is in charge of optimizing label associations, and this model achieves competitive performance against state-of-the-art multi-label classification algorithms.

TL;DR: A kind of canonical model construction can be used to decide defeasible subsumption and instance queries in under rational and the stronger relevant entailment in so-called typicality models, which reproduce the entailments obtained from materialisation-based rational and relevant closure and obtain stronger versions of rational andrelevant entailment.

TL;DR: It is proved that the proposed AC-RRNS algorithm based on modified threshold Asmuth–Bloom and Mignotte secret sharing schemes satisfies the formal definition of computational security and ensures security under several types of attacks.

TL;DR: The aim of this work is to study a fuzzy implication, obtained from the composition of a fuzzy negation and a t-norm, and to provide a way to construct fuzzy subsethood measures by means of (T,N)-implications.

TL;DR: This work studies two different relaxations, one related to the new weighted defence the authors propose, by checking the difference between the composition of inward and outward attack-weights, and another related to how much inconsistency they are willing to tolerate inside an extension.

TL;DR: It is shown that there is a categorical isomorphism between algebraic fuzzy closure operators and fuzzy convex structures and the relationship between fuzzy closure systems and fuzzy Convex structures is investigated.

TL;DR: This paper has proposed a new heuristic-based dependency calculation method that comprises a set of two rules called Direct Dependency Calculation (DDC) to calculate attribute dependency, which calculates the number of unique/non-unique classes directly by using attribute values.

TL;DR: A model where decision makers may express their preferences among the possible conflict scenarios using upper and lower probabilities in the graph model for conflict resolution (GMCR) is proposed, and eight stability definitions (solution concepts) that are generalizations of the four stability concepts commonly used in the GMCR model are proposed.

TL;DR: This paper focuses on the latter class of techniques, which have been developed independently and had not been put in perspective until now, and existing definitions for frequency-calibrated belief functions as well as corresponding construction methods are reviewed.

TL;DR: Two kinds of interval extensions for ( G , N ) - Implications and QL -implications derived from overlap and grouping functions are introduced, namely interval ( G, N )-implications and interval ( O, G ,N ) -implication, respectively.

TL;DR: A framework of distance-based double-quantitative rough fuzzy set (Db-Dq-RFS) with logic operation is proposed by forming a distance- based fuzzy similarity relation in an information system with continuous data to simultaneously solve the two limitations of the classical rough set model.

TL;DR: A hybrid method, MAG Max–Min Hill-Climbing (M3HC) that takes as input a data set of continuous variables, assumed to follow a multivariate Gaussian distribution, and outputs the best fitting maximal ancestral graph.

TL;DR: This paper investigated 32 pairs of neighborhood-based dual lower and upper approximation operators and successfully obtained all the matrix representations of them.