Search

First, a new pattern classification model with T-fuzzy data is built on the basis of definition in T-fuzzy data and of its operation properties. Besides, T-fuzzy data are determined to measure T-fuzzy numbers by using a distance formula, so that a model is also decided. Meanwhile four methods to the model are presented, which are applied to pattern classification and recognition of environmental quality. The result gained from a sample coincides with practice, providing a valid method for a pursuit of indeterminacy problems in human imitation identification, because the sample contains more information, where a little training results from the sample is integrated with estimation from expert's experience, and information resources are made full use of in analysis of confirmation. Finally, we give some method with which T-fuzzy data is obtained. [ABSTRACT FROM AUTHOR]

It is well-known that the financial market is affected by many nonprobabilistic factors. In a fuzzy uncertain economic environment, the future states of returns and risks of risky assets cannot be predicted accurately. Based on this fact, possibilistic portfolio selection problem under investing constrains is discussed in this paper. The possibilistic mean value of the return is termed measure of investment return and the possibilistic variance of the return is termed measure of investment risk. We further present a quadratic programming model replaced Markowitz's mean-variance model when returns of assets are trapezoidal fuzzy numbers, the conventional probabilistic mean-variance model is simplified and extended. A numerical example of a possibilistic fuzzy portfolio selection problem is given to illustrate our proposed effective means and approaches. [ABSTRACT FROM AUTHOR]

Short message service (SMS) is a mechanism of delivery of short messages over the mobile networks. Because of its popularity, SMS is now a ubiquitous way of communicating. In order to improve its efficiency and intelligence, this paper examines methods for analyzing message entry techniques by using a query against a knowledge base which has been acquired background information. People can also use SMS to perform reasoning or discover implicit knowledge. This study proposes application and architecture of intelligent knowledge query answering system based on SMS. Short message processing module and knowledge query module are two main parts of this system. The first module includes correlative AT command & PDU data format analysis and processing flow of short message. The second module analyses query sentence by using natural language understanding technology which tries to understand query sentence by using a conceptual network model to organize knowledge. Conceptual network is adopted to systematically organize relationships among concepts and represent different features of each concept so as to substantially improve people's ability to get specific information in response to specific needs. Furthermore, the paper discusses PDU coding format and question analysis in detail. [ABSTRACT FROM AUTHOR]

Designing the approximate reasoning matching schemes and the corresponding algorithms with similarity relation ℚ instead of equivalence relation ℚ can reflect the nature of approximate reasoning and meet more application expectations. This paper bases on similarity relation ℚ and introduces the type V matching scheme and the corresponding approximate reasoning type V ℚ-algorithm with the given input A* and knowledge A → B. We also present type V completeness and type V perfection of knowledge base K in ℚ-logic ℂℚ in this paper. [ABSTRACT FROM AUTHOR]

There are always uncertainty, incompleteness and imprecision existing in decision making information. These are why fuzzy set theory is commonly used in decision making. Vague set can indicate the decision makers' preference information in terms of favor against and neutral. When dealing with uncertain information, vague set indicates information more abundant than fuzzy set. According to the theories of multiobjective decision making and fuzzy game, the multiobjective two-person zero-sum matrix game, whose payoff values are vague values is researched. Firstly, the concept of vague set and the order function is introduced. Then the model of multiobjective two-person zero-sum matrix game based on vague set is described. Thirdly, two solutions of vague multiobjective two-person zero-sum matrix game are discussed: one is making the vague multiobjective game problem crisp through the order function of vague values, then turning it into single objective game; the other method is turning vague multiobjective game problem into vague single objective game problem first, then making it crisp through the order function of vague values. Finally, numerical examples are given to apply the proposed methods. [ABSTRACT FROM AUTHOR]

This paper considers a class of fuzzy linear programming (FLP) problems where the coefficients of the objective function are characterized by LR-fuzzy intervals or LR-fuzzy numbers with the same shapes. The existing methods mainly focus on the problems whose fuzzy coefficients are linear shape. In this paper, we are interested in the solution of FLP problems whose fuzzy coefficients are nonlinear shapes. Specifically, we show that the FLP problem can be transformed into a multi-objective linear programming problem with four objectives if LR-fuzzy numbers have the same shape, and therefore the optimal solutions can be found by the relationships between FLP problems and the resulting parameter linear programming problems. An example is also presented to demonstrate that the method is invalid if fuzzy coefficients have different shapes. Then, we discuss the relationships among FLP problems, possibility and necessity maximization problems, and obtain a conclusion that all Pareto optimal solutions of the possibility-necessity approaches are the subset of the weak dominated solutions of the FLP problem. Finally, one numerical example is given to illustrate the solution procedure. [ABSTRACT FROM AUTHOR]

In this paper, by the use of the concept of cut set and information entropy, uncertainty and rough entropy about fuzzy knowledge are described. A new definition of rough entropy of a set X about knowledge R is given, and definition of rough entropy of fuzzy rough set is proposed. [ABSTRACT FROM AUTHOR]

For the general two-dimensional fuzzy controller, the output control value is a rigid function with respect to the error and the change in error, so it is difficult to obtain the desired effects for the plant that is uncertain and time-varying. Aimed at the problem, the paper applies gradient descent learning algorithm to correct the mean and variance of Gaussian membership functions of all fuzzy sets in the input and output universes, in this way, the fuzzy control system is adaptive. Selecting input signals as step, ramp, acceleration and sine signals, respectively, all simulation studies were carried out. The results demonstrate that the control algorithm is feasible, and its effect is better than that of the fuzzy control system without adaptability. [ABSTRACT FROM AUTHOR]

In this paper, we introduced the notions of fuzzy lattice filter (briefly, FL-filter), and normal fuzzy filters (briefly, NF-filter) of lattice implication algebras. And we also studied the properties of FL-filters, NF-filters in lattice implication algebra. Several characteristic of FLfilters and NF-filters are given. Respectively the relation between FL-filters and NF-filters, between fuzzy filters and FL-filters are investigated. This article aims at discussing new development of fuzzy filters and its properties. [ABSTRACT FROM AUTHOR]

Based on experiment of plastic mulching and drip irrigation in greenhouse, nine treatments of different irrigation and fertilization were evaluated with multi-factor fuzzy synthesis evaluation method. Linear function was selected as membership function in fuzzy synthesis evaluation model. The weighting of factors set which included the yield, fruit qualities, water use efficiency and fertilizer utilization efficiency was confirmed by principal component analysis method. The evaluation result showed that the optimum treatment of integral indicators that fertilizer amount was pure N 337.5 kg·ha−1 and pure K2O 337.5 kg·ha−1, lower and high limit of irrigation were respective 40 kPa and 6 kPa. [ABSTRACT FROM AUTHOR]

This dissertation adopts programming theory to carry on the demonstration of the logistics distribution system of a large commodity manufacturer in Guangzhou. Aiming at solving the layout of location on the regional distributing center (RDC) of the actual logistics distribution system of the company, a programming model on the optimization of location is put forward. This model is applied to solve the location programming problem with the help of MATLAB6.5 tool, and a decisive supporting system that can examine the accuracy of the model result automatically is designed through the application of C++ BUILDER6.0. It is of great significance of optimization and making decision to the operating of logistics. [ABSTRACT FROM AUTHOR]

Decision-tree algorithms provide one of the most popular methodologies for symbolic knowledge acquisition. The resulting knowledge, a symbolic decision tree along with a simple inference mechanism, has been praised for comprehensibility. The most comprehensible decision trees have been designed for perfect symbolic data. Over the years, additional methodologies have been investigated and proposed to deal with continuous or multi-valued data, and with missing or noisy features. Recently, with the growing popularity of fuzzy representation, some researchers have proposed to utilize fuzzy representation in decision trees to deal with similar situations. This paper presents a survey of current methods for FDT (Fuzzy Decision Tree) designs and the various existing issues. After considering potential advantages of FDT's over traditional decision tree classifiers, the subjects of FDT attribute selection criteria, inference for decision assignment, and decision and stopping criteria are discussed. To be best of our knowledge, this is the first overview of fuzzy decision tree classifier. [ABSTRACT FROM AUTHOR]

In the field of Kansei Engineering, Semantic Differential (SD) is a typical method in evaluating conceptual products. We design a WEB-based kansei questionnaire system to generate a Decision Table(DT) which is composed of typical form features(condition attributes) and kansei words(decision attributes) through SD methods; by using statistical tools, frequent records are stored to DT as decision rules which are indexed by kansei word. First, some rules which have important contributions to the corresponding kansei evaluation will be extracted through the attribute reduction algorithm of Rough Set Theory(RST). Second, the size of decision table has been reduced through association rule mining based on Rough set and rules joining operating; finally, strong association rule set which describe the relation between the key form feature and the corresponding kansei word is generated. The proposed method has been successfully implemented in cell phone design case. [ABSTRACT FROM AUTHOR]

A novel method is proposed in the paper, called A Region-Based Image Retrieval Method with Fuzzy Features (RBIRFF), which partitions images into regions firstly, then computes each region fuzzy features for color, texture and shape with fuzzy set theory, finally computes similarity between images and gets the retrieval results according to the similarity sequences. The design and realization of RBIRFF system is also introduced in the paper, and its retrieval effectiveness is evaluated by experiments. [ABSTRACT FROM AUTHOR]

Decision-Tree (DT) is a widely-used approach to retrieve new interesting knowledge. Fuzzy decision trees (FDT) can handle symbolic domains flexibly, but its preprocess and tree-constructing are much costly. In this paper, we propose a hybrid decision tree (HDT) model by introducing credibility entropy into FDT. Entropy of multi-valued and continuous-valued attributes are both calculated with credibility theory, while entropy of other attributes is dealt with general Shannon method. HDT can decrease the cost of preprocess and tree-constructing significantly. We apply the model into geology field to find out the factors which cause landslide. Experiment results show that the proposed model is more effective and efficient than fuzzy decision tree and C4.5. [ABSTRACT FROM AUTHOR]

Granulometry formalizes the intuitive geometric notion of a sieving process. It was initially set oriented to extract size distribution from binary images, and has been extended to function operators to analyze and extract texture features in grey-scale images. In this paper, we study and establish granulometry with respect to grey-scale morphological operators based on fuzzy logic. We discuss applications of the granulometry in image analysis. A numerical experiment shows that granulometry is a powerful tool for image denoising for image analysis and processing. [ABSTRACT FROM AUTHOR]

In this paper, a novel threshold multi-group-secret sharing scheme is proposed based on Chan et al.'s scheme. Multiple groups of secrets are packed into a group of large secrets by using the Chinese Remain Theorem, and then shared by constructing a secret polynomial such that its coefficients are those large secrets. In the proposed scheme, the secret distribution procedure is needed only once to share multiple groups of secrets, which reduces the amount of computation largely. Moreover, each group of secrets has a different threshold access structure and includes a distinct number of secrets. Analysis results show that the proposed scheme needs fewer public values and is higher in efficiency and easier in implementation than existing schemes, especially for sharing many groups of secrets, which makes it more practical in practice. [ABSTRACT FROM AUTHOR]

A region-based image segmentation method with kernel fuzzy c-means clustering (FCM) is proposed. This method firstly extracts color, texture, and location features for each pixel by selecting suitable color space. Then, according to the feature vectors, pixeles are clustering by kernel FCM. The number and the center of clusters are decided by the proposed selecting the optimal cluster number method. Each pixel is grouped and labeled according to its membership degree. Finally, according to the pixels' neighbor connection theory, the regions with the same label are segmented again. [ABSTRACT FROM AUTHOR]

The development of Exposition Economy has greatly influenced over the global economy. Having done little research work of Exposition Economy, the writer tried to build an economical model through the theory of Exposition multiplier, the urban development potential and the pull on the national economy, as well as through the knowledge relevant to econometrics, hoping to explain the reaction over the national economy. [ABSTRACT FROM AUTHOR]

Knowledge reduction is an important issue when dealing with huge amounts of data. Rough set theory provides two fundamental concepts to deal with this special problem: attribute reduction and core, where attribute reduction is the key problem. There are a lot of methods available for attribute reduction, but very little work has been done for attribute reduction for the cases of deleting and modifying. Therefore, in this paper, we introduce a new updating method based on discernibility matrix for attribute reduction for the case of deleting. When a few old objects are deleted from a decision information system, a core and a new attribute reduction can be obtained quickly because it only deletes a few old rows and columns, or inserts a few rows and updates corresponding columns when updating the discernibility matrix. [ABSTRACT FROM AUTHOR]

The concept of interval valued fuzzy sets (IV FSs), proposed by Dubois et al and Gorza lczany, has gained attention from researchers for its applications in various fields. Although many measures of similarity between FSs have been proposed in the literature, those measures cannot deal with the similarity measures between IV FSs. In this paper, the definition of the degree of similarity between IV FSs is introduced. Then similarity measures between IV FSs are proposed and corresponding proofs are given. Finally, the similarity measures are applied to pattern recognitions. [ABSTRACT FROM AUTHOR]

The support vector machine (SVM) is a class of powerful classification tools that have many successful applications. Their classification results usually belong to either one class or the other. But in many real-world applications, each data point no more exactly belongs to one of the two classes, it may 70% belong to one class and 30% to another. That is, there is a fuzzy membership associated with each data. In such an environment, fuzzy SVM (FSVM), which treats every sample as both positive and negative classes with the fuzzy membership, were introduced. In this way the FSVM will have more generalization ability, while preserving the merit of insensitive to outliers. Although the FSVM has good generalization capability, the computational complexity of the existing FSVM is rather large because the final solution is obtained from solving a quadratic programming (QP) problem. For reducing the complexity, this study proposes a least squares method to solve FSVM. In the proposed model, we consider equality constraints instead of inequalities for the classification problem with a formulation in a least squares sense. As a result the solutions follow directly from solving a set of linear equations instead of QP thus reducing the computational complexity greatly relative to the classical FSVM. For illustration purpose, a real-world credit risk assessment dataset is used to test the effectiveness of the LS-FSVM model. [ABSTRACT FROM AUTHOR]

Rough model is proposed to model vague geographic objects based on the definition of rough regions, lower approximation regions, upper approximation regions and boundary regions. With the combination of rough model and RCC-D-8, which is a discrete version of RCC extended into two-dimensional discrete space (ℤ2), 599 topological relations are got between simple vague geographic objects in raster regions described by intersection and containing matrix. [ABSTRACT FROM AUTHOR]

Rough sets theory is a relatively new soft computing tool to deal with vagueness and uncertainty. Considering the feature of remote sensing images and the basic theory and applications of rough sets, we put forward a remote sensing image classification algorithm based on rough set theory. In this article we first introduce the basic theory and character of rough sets and its applications in recent years are also pointed out. Then the theory of rough sets is introduced into the processing of remote image classify. Experiment research and classification effects are showed in this article about the new technology and it seems innovational and useful. [ABSTRACT FROM AUTHOR]

Compared with the rule form in traditional data mining techniques, expressing knowledge in the form of rank list can avoid many disadvantages, and may be applied for the investigation of targeted marketing widely, identifying potential market values of customers or products. Based on the rough sets theory in granular computing, this paper proposes a Granular Ranking Algorithm with the time complexity O(nm), gives the framework of algorithm and the concrete algorithm steps. The core of new algorithm is the construction of Granular Ranking FunctionrG(χ), which guides instances in the testing dataset finish ranking. The ranked result has a strong readability. The new algorithm improves the computation efficiency further relative to existing algorithms, e.g. the Market Value Function. The experiment result shows that the computation accuracy of granular ranking algorithm approaches to the market value function. Meanwhile, the time consumption of the former one is much less than the latter. [ABSTRACT FROM AUTHOR]

The traditional rough set (RS) theory is a powerful tool to deal with complete information system, and its performance to process incomplete information system is weak, especially, its effect of combining the incomplete information system with fuzzy objective information system is weaker. The paper improves the tolerance relation proposed by M.Kryszkiewcz to obtain the γ— tolerance relation and γ— tolerance classes, presents the concept of the incomplete and fuzzy objective information system (IFOIS in short), and gives its rough set model based on the γ— tolerance relation, i.e., the rough set model in incomplete and fuzzy objective information system. Finally, the concept of precision reduction is defined, and the corresponding algorithm is provided. [ABSTRACT FROM AUTHOR]

Rough set theory usually deals with how a concept is represented with some granules. In this paper we extend rough set theory, and use it to deal with how a series of concepts are represented with a granule. We use it to seek the most possible determined reasons and the most possible reasons from decision systems, and also to reduce decision tables. This may be a new aspect of rough set research, and may extend application fields of rough set theory. [ABSTRACT FROM AUTHOR]

The classical rough set theory mostly emphasizes the differentiation among the elements of the universe, but does not investigate the structure of the universe. This paper extends rough set theory from the set to the system, making it not only can well classify elements of the universe but also can reveal the interrelation among elements of the universe. Then some properties about the approximation operators are discussed. Finally, some examples of rough sets of system are given. [ABSTRACT FROM AUTHOR]

A variable precision rough set(VPRS) is an extension of a Pawlak rough set. By setting a threshold β, VPRS loosens the strict definition of approximate boundary in Pawlak rough sets. This paper deals with uncertainty of rough sets based on the VPRS model. A measure is first defined to characterize fuzziness of a set in an information system. A pair of lower and upper approximations based on the fuzzy measure are then defined. Properties of the fuzzy measure and approximations are also examined. [ABSTRACT FROM AUTHOR]

The entropy, fuzzy positive entropy and fuzzy negative entropy measure for rough fuzzy sets are proposed. Some properties of entropy measure for rough fuzzy sets are discussed. It is also shown that the proposed measure can be defined in terms of the ratio of rough fuzzy cardinalities. [ABSTRACT FROM AUTHOR]

In rough communication, each agent taking part in rough communication may give new judge about the dynamic concept X. And this new information may be important. How to study the rough communication which concerns the useful subjective information is very important. The definition of rough communication of dynamic concept based on α — generation of two direction assistant sets is proposed in the paper. An example is presented to illustrate the reasonableness of the new definition. [ABSTRACT FROM AUTHOR]

A hot topic of rough set theory is the combination of fuzzy set theory and this one. Many researchers do the work by introducing the concept of level fuzzy sets. In this paper, we will study roughness measure in fuzzy rough set in this way, too. The lower and the upper approximation based on λ-level fuzzy set will be proposed, and their properties be discussed. Moreover we introduced the new method to the roughness measure in fuzzy rough sets according to these concepts. [ABSTRACT FROM AUTHOR]

The paper first put forward a definition of extended Intuitionistic Fuzzy Set, and then give the conception of the distance between two extended intuitionistic Fuzzy Set. By intuitionistic Fuzzy Set distance, the degree of agreement of each expert to the others is aggregated. Finally, a numerical example is given to apply this model. [ABSTRACT FROM AUTHOR]

As the matter fact that there are many joints in the hexapod walking Bio-robot and the calculation of its walking trajectory, as well as the problem of the acceleration leap caused by adopting elementary function as the robot's feet trajectory. This paper puts forward using cubic spline curves as the robots feet trajectory and designing the robot's walking gait. Then the authors conducted kinematical simulation and analyses on the model of the bionic hexapod walking robot which have done with the use of Solidworks and MSC.ADAMS. Through the simulation experiments, we validated the applicability of designed triangle gait and the feasibility of using cubic spline curve as the feet trajectory. This paper shows principle, method and course on the trajectory simulation of hexapod walking Bio-robot in detail. The way to find a converse solution under the condition of ADAMS is found, which simplifies the theory calculation and improves design efficiency. [ABSTRACT FROM AUTHOR]

This paper presents a new guaranteed cost controller design approach for a class of Takagi-Sugeno (T-S) fuzzy descriptor systems with time-varying delay. Based on the relaxed quadratic stability condition and a linear quadratic cost function, the sufficient conditions for the existence of guaranteed cost controllers via state feedback are given in terms of linear matrix inequalities (LMIs). And the design of optimal guaranteed cost controller can be reduced to a convex optimization problem. At last, a numerical example is given to illustrate the effectiveness of the proposed method and the perfect performance of the optimal guaranteed cost controller. [ABSTRACT FROM AUTHOR]

During the sensor evaluation procedure, each valuator uses his/her own ordinary linguistic truth values for the same factor because of different preference. That will brings some disadvantages to aggregate the information. For a uniform criterion, the standard linguistic truth value set is proposed. Based on the former hypothesis of transformation models of linguistic truth values, four transformation models are discussed: the model of point to point, the model of fuzzy set to point, the model of point to fuzzy set and the model of fuzzy set to fuzzy set. An example is to analyze it. [ABSTRACT FROM AUTHOR]

In this paper, we introduce Mizumota automata whose initial and final states are fuzzy. Furthermore, the equivalence of the type of Mizumoto automaton(MA) and canonical fuzzy finite automaton(CA) with single initial state and deterministic transition function is established. Then we present a method to minimize the states of automata in canonical form. [ABSTRACT FROM AUTHOR]

Aimed at the problem of cold resulted from sleeping fidget about infants, this paper explored the mechanism of the sleeping fidget, and presented the relational model between the sleeping fidget and temperature, humidity, and their changes. Authors developed the data acquisition system of the temperature and humidity based on the digital sensor, acquired lots of data about the temperature/humidity and the corresponding fidget degree, designed the neural networks model construct through analyzing the relation among three kinds of data. On this basis, the NN model was trained with the experimental data based on MATLAB NN Toolbox. The model verification shows that the sleeping fidget model can effectively implement sleeping fidget monitoring. [ABSTRACT FROM AUTHOR]

Aimed at implementation puzzles of fuzzy PID controller because of computational complexity, in this paper, in order to reduce computational complexity and realize real-time control, authors utilized universal approximation of the NN to reconstruct an equivalent NN model to accurately approximate a known fuzzy PID controller. Consequently, authors simulated to control the same process model by the fuzzy PID controller and the remodeling NN with different reference inputs, respectively. Results show that control qualities from two different controllers were extremely similar. Therefore, the fuzzy PID controller can be replaced by a remodeling NN in purpose of reducing the computational complexity, dimensional disaster and improving the real-time performance. [ABSTRACT FROM AUTHOR]

In this paper. we study the controllability for the impulsive semilinear fuzzy integrodifferential control system in EN by using the concept of fuzzy number whose values are normal, convex, upper semicontinuous and compactly supported interval in EN. [ABSTRACT FROM AUTHOR]

How to find the core attributes is important for attribute reduction based on rough set. However, there are few literatures discussing this topic, and most existing works are mainly based on Hu's discernibility matrix. Till now, there are three kinds of core attributes: Hu's core based on discernibility matrix (denoted by Core1(C)), core based on positive region (denoted by Core2(C)), and core based on information entropy (denoted by Core3(C)). Some researchers have been pointed out that these three kinds of cores are not equivalent to each other. Based on the above three kinds of core attributes, we at first propose three kinds of simplified discernibility matrices and their corresponding cores, which are denoted by SDCore1(C), SDCore2(C), and SDCore3(C) respectively. And then it is proved that Core1(C)=SDCore1(C), Core2(C)=SDCore2(C), and Core3(C)=SDCore3(C). Finally, based on three proposed simplified discernibility matrices and their corresponding cores, it is proved that $$ Core2(C) \subseteq Core3(C) \subseteq Core1(C) $$ . [ABSTRACT FROM AUTHOR]

The update of rules is the key to success for rule-based network intrusion detection system because of the endless appearance of new attacks. To efficiently extract classification rules from the vast network traffic data, this paper gives a new approach based on Particle Swarm Optimization (PSO) and introduces a new coding scheme called "indexical coding" in accord with the feature of the network traffic data. PSO is a novel optimization technique and has been shown high performance in numeric problems, but few researches have been reported in rule learning for IDS that requires a high level representation of the individual, this paper makes a study and demonstrates the performance on the 1999 KDD cup data. The results show the feasibility and effectiveness of it. [ABSTRACT FROM AUTHOR]

The uncertainty decision-making method is discussed in the paper. Pointing out the shortage of existing rule when decision information is incomplete, putting forward the colligation rule and the conception of unitary operator, the proof is given that the operator is in existence. It is an important tool when we transfer the frame of belief to the probability structure. Finally, a numerical example is given to illustrate the use of the calculation methods. [ABSTRACT FROM AUTHOR]