Knowledge-Driven Possibilistic Clustering with Automatic Cluster Elimination

Traditional Fuzzy C-Means(FCM)and Possibilistic C-Means(PCM)clustering algorithms are data-driven,and their objective function minimization process is based on the available numeric data.Recently,knowledge hints have been introduced to formknowledge-driven clustering algorithms,which reveal a data structure that considers not only the relationships between data but also the compatibility with knowledge hints.However,these algorithms cannot produce the optimal number of clusters by the clustering algorithm itself;they require the assistance of evaluation indices.Moreover,knowledge hints are usually used as part of the data structure(directly replacing some clustering centers),which severely limits the flexibility of the algorithm and can lead to knowledgemisguidance.To solve this problem,this study designs a newknowledge-driven clustering algorithmcalled the PCM clusteringwith High-density Points(HP-PCM),in which domain knowledge is represented in the form of so-called high-density points.First,a newdatadensitycalculation function is proposed.The Density Knowledge Points Extraction(DKPE)method is established to filter out high-density points from the dataset to form knowledge hints.Then,these hints are incorporated into the PCM objective function so that the clustering algorithm is guided by high-density points to discover the natural data structure.Finally,the initial number of clusters is set to be greater than the true one based on the number of knowledge hints.Then,the HP-PCM algorithm automatically determines the final number of clusters during the clustering process by considering the cluster elimination mechanism.Through experimental studies,including some comparative analyses,the results highlight the effectiveness of the proposed algorithm,such as the increased success rate in clustering,the ability to determine the optimal cluster number,and the faster convergence speed.

On Weighted Possibilistic Mean,Variance and Correlation of Interval-valued Fuzzy Numbers

In this paper, the concept of weighted possibilistic mean of interval- valued fuzzy number is first introduced. Further, the notions of weighted possibilistic variance, covariance and correlation of interval-valued fuzzy numbers are presented. Meantime, some important properties of them and relationships between them are studied.

Modified possibilistic clustering model based on kernel methods

A novel model of fuzzy clustering using kernel methods is proposed. This model is called kernel modified possibilistic c-means （KMPCM） model. The proposed model is an extension of the modified possibilistic c-means （MPCM） algorithm by using kernel methods. Different from MPCM and fuzzy c-means （FCM） model which are based on Euclidean distance, the proposed model is based on kernel-induced distance. Furthermore, with kernel methods the input data can be mapped implicitly into a high-dimensional feature space where the nonlinear pattern now appears linear. It is unnecessary to do calculation in the high-dimensional feature space because the kernel function can do it. Numerical experiments show that KMPCM outperforms FCM and MPCM.

Methodology to Estimate Remaining Service Life of Steel Structure by Possibilistic Reliability Theory

Steel structure system of crane deteriorates over time due to environmental effects, material fatigue, and overloading. System structural reliability and remaining service life assessment methods are developed during the few decades. But until now estimating remaining service life methods of crane steel system by reliability theory begin to develop. Safety assessment of existing steel structure system requires the development of a methodology that allows for an accurate evaluation of reliability and prediction of the remaining life. Steel structures are the supporting elements in the special equipment such as hoisting machinery. Structure reliability and remaining service life safe assessment are important for steel structures. For finding the reason which caused the failure modes （such as fatigue strength failure, stiffness failure and stability failure）, incremental loading method based on possibilistic reliability is applied into dynamic structure failure path research. Through reliability analyzing and calculating for crane, it is demonstrated that fatigue damage is the most common failure mode. Fuzzy fatigue damage accumulation theory is used for basis theory and Paris-Eadogan equations are used for mathematical modeling. All fatigue parameter values of the welding box girder of bridge cranes are determined and fatigue remaining life formulas are deduced. After field test and collecting working parameters of numerous cranes, typical fatigue load spectrum was compiled for the dangerous point of box girders used in the area. Fatigue remaining life is assessed for different types and lifting capacities. Safety for steel structure system of bridge crane is assessed by two quantitative indexs： reliability and remaining life. Therefore, the evaluation means is more comprehensive and reasonable. The example shows that the two quantitative indexs are mutually correlated. Through analyzing the 120 t-22.5 m bridge crane of a certain enterprise, a new methodology to estimate remaining service life of steel structure by possibilistic reliability theory is introduced for safety evaluation of structure system.

Possibilistic entropy-based measure of importance in fault tree analysis

With respect to the subjective factors and nonlinear characteristics inherent in the important identification of fault tree analysis （FTA）, a new important measure of FTA is proposed based on possibilistic information entropy. After investigating possibilistic information semantics, measure-theoretic terms, and entropy-like models, a two-dimensional framework has been constructed by combining both the set theory and the measure theory. By adopting the possibilistic assumption in place of the probabilistic one, an axiomatic index of importance is defined in the possibility space and then the modelling principles are presented. An example of the fault tree is thus provided, along with the concordance analysis and other discussions. The more conservative numerical results of importance rankings, which involve the more choices can be viewed as “soft” fault identification under a certain expected value. In the end, extension to evidence space and further research perspectives are discussed.

An Approach to Solve a Possibilistic Linear Programming Problem

The objective of the paper is to deal with a kind of possibilistic linear programming (PLP) problem involving multiple objectives of conflicting nature. In particular, we have considered a multi objective linear programming (MOLP) problem whose objective is to simultaneously minimize cost and maximize profit in a supply chain where cost and profit coefficients, and related parameters such as available supply, forecast demand and budget are fuzzy with trapezoidal fuzzy numbers. An example is given to illustrate the strategy used to solve the aforesaid PLP problem.

Keystroke Dynamics Based Authentication Using Possibilistic Renyi Entropy Features and Composite Fuzzy Classifier

This paper presents the formulation of the possibilistic Renyi entropy function from the Renyi entropy function using the framework of Hanman-Anirban entropy function. The new entropy function is used to derive the information set features from keystroke dynamics for the authentication of users. A new composite fuzzy classifier is also proposed based on Mamta-Hanman entropy function and applied on the Information Set based features. A comparison of the results of the proposed approach with those of Support Vector Machine and Random Forest classifier shows that the new classifier outperforms the other two.

Improved Kernel Possibilistic Fuzzy Clustering Algorithm Based on Invasive Weed Optimization

Fuzzy c-means(FCM) clustering algorithm is sensitive to noise points and outlier data, and the possibilistic fuzzy c-means(PFCM) clustering algorithm overcomes the problem well, but PFCM clustering algorithm has some problems: it is still sensitive to initial clustering centers and the clustering results are not good when the tested datasets with noise are very unequal. An improved kernel possibilistic fuzzy c-means algorithm based on invasive weed optimization(IWO-KPFCM) is proposed in this paper. This algorithm first uses invasive weed optimization(IWO) algorithm to seek the optimal solution as the initial clustering centers, and introduces kernel method to make the input data from the sample space map into the high-dimensional feature space. Then, the sample variance is introduced in the objection function to measure the compact degree of data. Finally, the improved algorithm is used to cluster data. The simulation results of the University of California-Irvine(UCI) data sets and artificial data sets show that the proposed algorithm has stronger ability to resist noise, higher cluster accuracy and faster convergence speed than the PFCM algorithm.

可能性扩展规则的推理和知识编译

在扩展规则的基础上提出了可能性扩展规则.给出了基于可能性扩展规则的可能性逻辑推理方法,利用互补因子的概念来估价推理问题的复杂度.扩展了经典逻辑的蕴含可控制类和可满足可控制类的定义,提出了可能性蕴含可控制类、不一致性程度计算可控制类的概念.在可能性扩展规则的基础上提出了EPPCCCL(each pair of possibilistic clauses contains complementary literals)理论,并证明了该理论是在最优化形式蕴含可控制类和不一致性程度计算可控制类中的,可以作为可能性知识编译的目标语言.

ALLIED FUZZY c-MEANS CLUSTERING MODEL

A novel model of fuzzy clustering, i.e. an allied fuzzy c means （AFCM） model is proposed based on the combination of advantages of fuzzy c means （FCM） and possibilistic c means （PCM） clustering. PCM is sensitive to initializations and often generates coincident clusters. AFCM overcomes this shortcoming and it is an ex tension of PCM. Membership and typicality values can be simultaneously produced in AFCM. Experimental re- suits show that noise data can be well processed, coincident clusters are avoided and clustering accuracy is better.

Finding a Link between Randomness and Fuzziness

If sample realizations are intervals, if the upper and the lower boundaries of such intervals are realizations of two independently distributed random variables, the two probability laws together lead to some interesting assertions. In this article, we shall attempt to remove certain confusions regarding the relationship between probability theory and fuzzy mathematics.

Fuzzy Mathematical Model for Solving Supply Chain Problem

In a real world application supply chain, there are many elements of uncertainty such as supplier performance, market demands, product price, operation time, and shipping method which increases the difficulty for manufacturers to quickly respond in order to fulfil the customer requirements. In this paper, the authors developed a fuzzy mathematical model to integrate different operational functions with the aim to provide satisfy decisions to help decision maker resolve production problem for all functions simultaneously. A triangular fuzzy number or possibilistic distribution represents all the uncertainty parameters. A comparison between a fuzzy model, a possibilistic model and a deterministic model is presented in this paper in order to distinguish the effectiveness of model in dealing the uncertain nature of supply chain. The proposed models performance is evaluated based on the operational aspect and computational aspect. The fuzzy model and the possibilistic model are expected to be more preferable to respond to the dynamic changes of the supply change network compared to the deterministic model. The developed fuzzy model seems to be more flexible in undertaking the lack of information or imprecise data of a variable in real situation whereas possibilistic model is more practical in solving an existing systems problem that has available data provided.

Automatic Fall Detection Using Membership Based Histogram Descriptors

t We propose a framework for automatic fall detection based on video visual feature extraction. The proposed approach relies on a membership histogram descriptor that encodes the visual properties of the video frames. This descriptor is obtained by mapping the original low-level visual features to a more discriminative descriptor using possibilistic memberships. This mapping can be summarized in two main phases. The first one consists in categorizing the low-level visual features of the video frames arid generating homogeneous clusters in an unsupervised way. The second phase uses the obtained membership degrees generated by the clustering process to compute the membership based histogram descriptor （MHD）. For the testing stage, the proposed fall detection approach categorizes unlabeled videos as ＂Fall＂ or ＂Non-Fall＂ scene using a possibilistic K-nearest neighbors classifier. The proposed approach is assessed using standard videos dataset that simulates patient fall. Also, we compare its performance with that of state-of-the-art fall detection techniques.

MERGING FUZZY STATISTICAL DATA WITH IMPRECISE PRIOR INFORMATION

Solving complex decision problems requires the usage of information from different sources. Usually this information is uncertain and statistical or probabilistic methods are needed for its processing. However, in many cases a decision maker faces not only uncertainty of a random nature but also imprecision in the description of input data that is rather of linguistic nature. Therefore, there is a need to merge uncertainties of both types into one mathematical model. In the paper we present methodology of merging information from imprecisely reported statistical data and imprecisely formulated fuzzy prior information. Moreover, we also consider the case of imprecisely defined loss functions. The proposed methodology may be considered as the application of fuzzy statistical methods for the decision making in the systems analysis.