Support vector machines (SVMs) based on fuzzy theory have attracted widespread attentions in pattern recognition and machine learning. However, these SVMs have some limitation in dealing with some classification problems with fuzzy outputs, which results in the ignorance of the fuzziness of fuzzy outputs. Motivated by this, the possibility and necessity of fuzziness of fuzzy outputs are discussed, and the dynamic partitioning methods of these fuzzy output training samples are demonstrated based on credibility measure. Then, the corresponding dynamic credibility support vector machines based on fuzzy outputs are established, and the feasibility and effectiveness of credibility SVMs are shown by experimental results.
We propose a model for the pricing of the minimum guarantee option embedded in equity-linked life insurance policies under uncertainty of randomness and fuzziness. The future lifetime of the insured is modelled as a random variable and the asset price evolution is described using a fuzzy binomial-tree model. In order to deal with both randomness and fuzziness, we model the present value of liabilities as a fuzzy random variable. Our results can be used by the actuary to understand the incidence of the minimum guarantee on the premium and to define the appropriate coverage strategies. A numerical example illustrates how our methodology works. (C) 2017 Elsevier Inc. All rights reserved.
The theory of rough sets found wider applications in knowledge discovery and datamining. This paper deals with indexing the records of an information system by using afuzzy decision attribute. The method of indexing is obtained by using the hedges of thefuzzy attribute.
In fuzzy clustering, the fuzzy c-means (FCM) algorithm is the most commonly used clustering method. Various extensions of FCM had been proposed in the literature. However, the FCM algorithm and its extensions are usually affected by initializations and parameter selection with a number of clusters to be given a priori. Although there were some works to solve these problems in FCM, there is no work for FCM to be simultaneously robust to initializations and parameter selection under free of the fuzziness index without a given number of clusters. In this paper, we construct a robust learning-based FCM framework, called a robust-learning FCM (RL-FCM) algorithm, so that it becomes free of the fuzziness index m and initializations without parameter selection, and can also automatically find the best number of clusters. We first use entropy-type penalty terms for adjusting bias with free of the fuzziness index, and then create a robust learning-based schema for finding the best number of clusters. The computational complexity of the proposed RL-FCM algorithm is also analyzed. Comparisons between RL-FCM and other existing methods are made. Experimental results and comparisons actually demonstrate these good aspects of the proposed RL-FCM where it exhibits three robust characteristics: 1) robust to initializations with free of the fuzziness index, 2) robust to (without) parameter selection, and 3) robust to number of clusters (with unknown number of clusters). (C) 2017 Elsevier Ltd. All rights reserved.
We investigate the detectability thresholds of various modular structures in the stochastic block model. Our analysis reveals how the detectability threshold is related to the details of the modular pattern, including the hierarchy of the clusters. We show that certain planted structures are impossible to infer regardless of their fuzziness.
This paper is an amendment to Hop's paper INN. Hop, Solving linear programming problems under fuzziness and randomness environment using attainment values, Information Sciences 177 (2007) 2971-2984], in solving linear programming problems under fuzziness and randomness environments. Hop introduced a new characterization of relationship, attainment values, to enable the conversion of fuzzy (stochastic) linear programming models into corresponding deterministic linear programming models. The purpose of this paper is to provide a correction and an improvement of Hop's analytical work through rationalization and simplification. More importantly, it is shown that Hop's analysis does not support his demonstration or the solution-finding mechanism; the attainment values approach as he had proposed does not result in superior performance as compared to other existing approaches because it neglects some relevant and inevitable theoretical essentials. Two numerical examples from Hop's paper are also employed to show that his approach, in the conversion of fuzzy (stochastic) linear programming problems to corresponding problems, is questionable and can neither find the maximum nor the minimum in the examples. The models of the examples are subsequently amended in order to derive the correct optimal solutions.
We review the existing measures of uncertainty (entropy) for Atanassov's intuitionistic fuzzy sets (AIFSs). We demonstrate that the existing measures of uncertainty for AIFS cannot capture all facets of uncertainty associated with an AIFS. We point out and justify that there are at least two facets of uncertainty of an AIFS, one of which is related to fuzziness while the other is related to lack of knowledge or non-specificity. For each facet of uncertainty, we propose a separate set of axioms. Then for each of fuzziness and non-specificity we propose a generating family (class) of measures. Each family is illustrated with several examples. In this context we prove several interesting results about the measures of uncertainty. We prove some results that help us to construct new measures of uncertainty of both kinds.
This study proposes a solution for the topological representation and interpretation of moving regions under vagueness in a geographic information system (GIS). The problem is multifaceted, and different aspects will be discussed. We investigate the impact of several types of fuzzy logic on results and address which is more convenient for the region connection calculus under fuzziness (FRCC). By recognising that the main and basic relation to evaluate topological relations is the connection relation, we adopt a qualitative strategy based on fuzzy inference and resemblance relations. We also define topological differences and introduce fuzzy transition relations (FTRs) to distinguish how a transition from one topological situation to another occurs for a pair of objects during a time period. As pure topological relations are not sufficient for a complete qualitative perception, an orientation-based method (OBM) will be proposed. Using this method, we can interpret, for example, a region that partially overlaps another region mostly on its northern part. Most importantly, some step-by-step algorithms and constructs are proposed and evaluated such that the model can apply to regions stored in vector data models.
Cloud computing enables a revolutionary paradigm of consuming ICT services. However, due to the inadequately described service information, users often feel confused while trying to find the optimal services. Although some approaches are proposed to deal with cloud service retrieval and recommendation issues, they would only work for certain restricted scenarios in dealing with basic service specifications. Indeed, the missing extent is that most of the cloud services are "agile" whilst there are many vague service terms and descriptions. This paper proposes an agility-oriented and fuzziness-embedded cloud service ontology model, which adopts agility-centric design along with OWL2 (Web Ontology Language) fuzzy extensions. The captured cloud service specifications are maintained in an open and collaborative manner, as the fuzziness in the model accepts rating updates from users on the fly. The model enables comprehensive service specification by capturing cloud concept details and their interactions, even across multiple service categories and abstraction levels. Utilizing the model as a knowledge base, a service recommendation system prototype is developed. Case studies demonstrate that the approach can outperform existing practices by achieving effective service search, retrieval and recommendation outcomes. (C) 2015 Elsevier B.V. All rights reserved.
How to carry out the fuzzy signal processing to an image is a problem to be solved urgently in many departments. For fuzziness on image processing, this paper studies a variety of fuzzy signal, implements the denoising fuzziness processing, presents some methods and algorithms for fuzzy signal processing, and compares with other methods on image processing. At the same time, this paper uses the wavelet analysis to carry out feature extraction of target for the first time, extracts the coefficient feature and energy feature of image decomposition, gives the matching and recognition methods, compares with the existing target recognition methods by experiment, and presents a target recognition method based on region of interest. Using the combining method of simulation and instance experiments, this paper systematically analyzes the validity of the model and algorithms. Moreover, using the wavelet transform to carry out the image decomposition, this paper extracts the coefficient feature of wavelet transform, gives the matching and recognition methods, and compares with the existing target recognition methods by experiment. Through experiment results, the proposed recognition method has the high precision, fast speed, and its correct recognition rate is improved by an average 5.16% than that of existing recognition methods. These researches in this paper can provide a new way of thinking for the researchers in pattern recognition field.