Search

Presents a paper which states that if the fuzzy graph is a cycle, then it is a fuzzy cycle if and only if is not a fuzzy tree. Examination of the relationship between fuzzy bridges and cycles; Introduction of the concepts of fuzzy cycle rank and fuzzy cocycle rank for fuzzy graphs; Definitions of fuzzy graphs; References.

Presents a paper describing a phoneme filter neural network (PFN) approach to phoneme recognition. Drawbacks of convential speech recognition nueral networks; Description of the PFN; Results of an experiment to apply the Japanese vowel recognition task; Problems in the recognition neural networks; Preparation for phoneme categories by the PFN; Information on the results of experiment; Confirmation on PFN mapping ability and recognition performance.

Presents a paper designed to show the set of relationships proposed in the CBM. Description of topological relationships among two-dimensional features; Information on relationships with high expressiveness; Development of various models for the representation of topological relationships; Set of topological relationships offered by the CBM; References.

Presents a paper on fuzzy neural trees, and an approach for converting these trees into feedforward neural network architectures. Introduction to the use of technology as a tool within the framework; Requirements for neural network algorithms; Evaluation of the algorithm; References.

Focuses on the role in image processing, pattern recognition and computer vision; Applications of image transformation to convert an input image into another. Description of algorithms that can only process binary images; Performance of algorithms; Proposed algorithms to deal with all kinds of images; Comparison to other papers with limited application; Application of a large number of gray level and color image; Converting of input image into another; Reference.

Presents a paper introducing the notion of a rough subgroup with respect to normal subgroup a of group. Information on properties of lower and upper approximations; Discussion of rough subgroup with respect to t-level subset; Comparison of author work on studies of algebraic properties; References.

Presents a paper on qualitative synthesis technique, and its uses to construct all configurations of investment vehicles with a given desired behavior. Description of management problems; Definition of concepts; Development of qualitative synthesis technique; Information of the use of technique; Concern of risk management with the design of investment vehicles; References.

Presents a paper on the design and implementation techniques employed in a Japanese-to-Sinhales machine translation systems. Result of the work is the successful application of Bunsetu; Development of the system; Reason for the application of Bunsetsu; Information on the basic design of the system; References.

Presents a research on the problem of identifying two distinguished elements in a given set in information sciences. Use of the Group Testing model and the second model called Parity; Search of two numbers in the bidimensional space as the paper's problem; Optimal predetermined algorithms for both group.

Presents a paper which used the application of an edge detection algorithm based on homogeneous tests for the detection of moving objects. Problem of detecting moving object; Categories which detection algorithms for moving objects can be divided into; Information on the development of the detector.

Reports that a number of research papers have focused their attention on a topic called molecular computing aimed at discussing how to develop intelligent computers using biological molecules as computational devices. Insight into the most criticized point of such papers; When the theory of formal language was introduced; Background information on formal languages; Outline of the actual theory of Fuzzy Formal Language (FFL).

Introduces the papers about genetic algorithms and fuzzy systems in the August 2001 issue of the `Information Sciences Journal.' Background on the concept of genetic fuzzy systems; Classification of the papers according to their application domain; Outline of the papers.

The control of autonomous intelligent robotic agent operating in unstructured changing environments includes many objective difficulties. One major difficulty concerns the characteristics of the environment that the agent should operate in. In unstructured and changing environments the inconsistency of the terrain, the irregularity of the product and the open nature of the working environment result in complex problems of identification, sensing and control. Problems can range from the effects of varying environmental conditions on the robot sensors and traction performance through to the need to deal with the presence of unexpected situations. Another major challenge is the large amounts of uncertainty that characterises real-world environments. On the one hand, it is not possible to have exact and complete prior knowledge of these environments. On the other hand, knowledge acquired through sensing is affected by uncertainty and imprecision. The quality of sensor information is influenced by sensor noise, the limited field of view, the conditions of observation, and the inherent difficulty of the perceptual interpretation process. Because environments and users of systems continuously change, robotic agents have to be adaptive. Intelligence helps because it gives systems the capacity to adapt more rapidly to environmental changes or to handle much more complex functions. In his paper we introduce this special issue and introduce the difficulty robots are facing in unstructured environments and how learning and computational intelligence can help the robots to adapt and give them the necessary intelligence they to face the challenges they encounter in their environments. [ABSTRACT FROM AUTHOR]

The objective in this paper is to apply our proposed two-way fuzzy adaptive system that makes use of intuitionistic fuzzy sets to the identification and model-based control of a flexible-joint robot arm. Uncertainty and inconsistency are modelled in the proposed system such as uncertainty is the width of the interval introduced by the independent assignment of membership and nonmembership functions of the intuitionistic fuzzy sets; and inconsistency is the violation of the consistency inequality in this assignment. We reduce uncertainty and inconsistency through a two phase training. The first phase is to reduce inconsistency introduced by the inconsistent assignment of membership and nonmembership functions. The resultant system is an almost consistent two-way fuzzy adaptive system. Thus, an evaluation of the degree of reduction of inconsistency is needed and is carried out at the end of this phase by forming the shadowed set patterns of the membership and nonmembership functions after first phase of training. The system is further trained for a second phase in order to reduce uncertainty. The system performance has shown that this second phase of training renders the system totally one-way fuzzy adaptive. [ABSTRACT FROM AUTHOR]

The objective in this paper is to apply our proposed two-way fuzzy adaptive system that makes use of intuitionistic fuzzy sets to the identification and model-based control of a flexible-joint robot arm. Uncertainty and inconsistency are modelled in the proposed system such as uncertainty is the width of the interval introduced by the independent assignment of membership and nonmembership functions of the intuitionistic fuzzy sets; and inconsistency is the violation of the consistency inequality in this assignment. We reduce uncertainty and inconsistency through a two phase training. The first phase is to reduce inconsistency introduced by the inconsistent assignment of membership and nonmembership functions. The resultant system is an almost consistent two-way fuzzy adaptive system. Thus, an evaluation of the degree of reduction of inconsistency is needed and is carried out at the end of this phase by forming the shadowed set patterns of the membership and nonmembership functions after first phase of training. The system is further trained for a second phase in order to reduce uncertainty. The system performance has shown that this second phase of training renders the system totally one-way fuzzy adaptive. [ABSTRACT FROM AUTHOR]

Mechanical assembly by robots has traditionally depended on simple sensing systems and the robot manufacturers programming language. However, this restricts the use of robots in complex manufacturing operations. An alternative to robot programming is the creation of self-adaptive robots based on the adaptive resonance theory (ART) artificial neural network (ANN). The research presented in this paper shows how robots can operate autonomously in unstructured environments. This is achieved by providing the robot with a primitive knowledge base (PKB) of the environment. This knowledge is gradually enhanced online based on the contact force information acquired during operations. The robot resembles a blindfoM person performing the same task since no information is provided about the localisation of the fixed assembly component. The design of a novel neural network controller (NNC) based on the Fuzzy ARTMAP network and its implementation results on an industrial robot are presented, which validate the approach. [ABSTRACT FROM AUTHOR]

This paper presents an effective generation method of adjustment strategies for a fuzzy-neuro force controller (FNFC) of a robot manipulator in an unknown environment. In this method, strategies to adjust the FNFC in accordance with the environment dynamics are automatically generated in off-line manner using genetic algorithms (GA). The generated strategies are stored in a neural network and used for adjusting the FNFC in on-line. Therefore, the FNFC is automatically adjusted in accordance with the unknown dynamics of an environment using the generated strategies which are stored in the neural network. Fuzzy fitness evaluation method is proposed for the effective evolution of the neural network in the GA process. The effectiveness of the generated adjustment strategies of the FNFC has been evaluated by computer simulation with a 3DOF robot manipulator model. [ABSTRACT FROM AUTHOR]

This paper describes an autonomous navigation system for a large underground mining vehicle. The control architecture is based on a robust reactive wall-following behaviour. To make it purposeful we provide driving hints derived from an approximate nodal-map. For most of the time, the vehicle is driven with weak localization (odometry). This need only be improved at intersections where decisions must be made -- a technique we refer to as opportunistic localization. The paper briefly reviews absolute and relative navigation strategies, and describes an implementation of a reactive navigation system on a 30 tonne Load-Haul-Dump truck. This truck has achieved full-speed autonomous operation at an artificial test mine, and subsequently, at a operational underground mine. [ABSTRACT FROM AUTHOR]

This paper presents ah implemented approach to part-mating of three-dimensional non-cylindrical parts with a 6 DOF manipulator, considering uncertainties in modeling, sensing and control. The core of the proposed solution is a reinforcement learning algorithm for selecting the actions that achieve the goal in the minimum number of steps. Position and force sensor values are encoded in the state of the system by means of a neural network. Experimental results are presented for the insertion of different parts circular, quadrangular and triangular prisms - in three dimensions. The system exhibits good generalization capabilities for different shapes and location of the assembled parts. These results significantly extend most of the previous achievements in tine motion tasks, which frequently model the robot as a polygon translating in the plane in a polygonal environment or do not present actual implemented prototypes. [ABSTRACT FROM AUTHOR]

This paper describes a neuro-fuzzy controller for autonomous underwater vehicles (AUVs) of which the dynamics are highly nonlinear, coupled, and time-varying. The neuro-fuzzy controller is based on the fuzzy membership function-based neural networks (FMFNNs) with advantages of fuzzy logics and neural networks, such as inference capability and adoption of human operators' experience with fuzzy logics, and universal approximation and learning capability with neural networks. Unlike other conventional control approaches, the presented FMFNN controller does not require any information about the system, off-line learning procedures, or human intervention to adjust parameters. On-line learning of the FMFNN controller is achieved by using an inner-loop learning scheme and simplified derivatives of the vehicle system. Simulation results show effectiveness of the FMFNN controller for AUVs. [ABSTRACT FROM AUTHOR]

The goal of many gene expression experiments is to discover genes that are functionally related by clustering expression levels sampled over some time interval, with the hope that co-regulated genes also are functionally related. However, it is not necessarily always true that co-regulated genes are functionally related, or vice versa, and therefore this paper investigates the value of including gene annotation in the clustering process. Results suggest that clusters formed by a clustering of a combination of expression data and annotation in the form of enzyme classification can give results that have higher correlation with known biological data (functional and metabolic pathway) not included in the clustering process. The results show that the same is true even in a situation with only 10% of the dataset annotated, which is an estimate of the amount of enzymatic annotation available today and a sign that the inclusion of added data helps in the clustering of genes without any explicit annotation. [Copyright &y& Elsevier]

This paper reports the findings obtained through the statistical analysis of the thermodynamic measurements collected on the partially mutated anti-lysozyme antibody HyHEL-10. The data contained amino-acid sequences of 35 types of mutants of HyHEL-10 and corresponding thermodynamic measurements such as entropy and enthalpy. We examined the contribution of each of the mutated sites on VH and VL chains of HyHEL-10 to the change of measurements by using the generalized linear model (GLM). Following results were obtained: (1) the sites VH32, 33, 50 and temperature had high partial correlations to the change of entropy (DH) and enthalpy (TDS), (2) the sites VH53 and 58 had high partial correlations to the change of specific heat (DCp), (3) the sites VL31, 32 and temperature had high partial correlations to the change of free energy (DG), DH, TDS and DCp. The results also suggested that the behavior of DH, TDS and DCp were well represented by GLM, however, the behavior of combining coefficient (Ka) should have a statistical nature assumed in Weibull distribution. [Copyright &y& Elsevier]

Tissue or developmental-specificity in central nervous system (CNS) represents strong functional diversity in high eukaryote genomes. Expression profile and sequence data become two major lines of information. In this paper, we conducted evolutionary analysis for the expression profiles of 14 gene families (57 genes) in vertebrate CNS development. We found the strong association between developmental profile and the gene family diversity. We speculate that gen(om)e duplication might be the evolutionary basis for functional diversity. This expression/sequence dual informatics approach is useful for tracking the genetic regulatory changes in complex biosystem. [Copyright &y& Elsevier]

Inferring a gene regulatory network is one of the challenging topics in the field of Bioinformatics. In order to infer a network structure effectively, the new approach that allows human intervention and strategic data acquisition in the inference process seems to be necessary. In this paper, we will propose an effective approach for interactively inferring gene regulatory networks using gene expression data from DNA microarrays. We will also establish the system that realizes our approach by GA-based interactive algorithm. Experimental results show that our method can infer the network structure accurately with a relatively small amount of expression data. [Copyright &y& Elsevier]

This paper describes an Evolutionary Modeling (EM) approach to building causal model of differential equation system from time series data. The main target of the modeling is the gene regulatory network. A hybrid method of Genetic Programming (GP) and statistical analysis is featured in our work. GP and Least Mean Square method (LMS) were combined to identify a concise form of regulation between the variables from a given set of time series. Our approach was evaluated in several real-world problems. Further, Monte Carlo analysis is applied to indicate the robust and significant influence from the results for gene network analysis purpose. [Copyright &y& Elsevier]

In a transaction-time temporal object database management system (TODBMS), updating an object creates a new version of the object, but the old version is still accessible. A TODBMS will store large amounts of data, and in order to provide the necessary computing power and data bandwidth, a parallel system based on a sharednothing architecture is necessary. In order to benefit from a parallel architecture, a suitable declustering of the objects over the nodes in the system is important. In this paper, we study three low-cost declustering algorithms: (1) declustering based on the hash value of the OlD of the objects, (2) range partitioning based on the timestamp of the objects, and (3) a new hybrid algorithm, where current object versions are declustered according to the hash value of the OID, and the historical versions are range partitioned based on timestamp. In contrast to many similar studies, we study the performance with a workload including both read and update operations. We show that strategies 1 and 3 are the most scalable strategies, and that the new hybrid declustering strategy is especially suitable for low update rates, for example in geographical information systems and decision support systems with support for temporal data. However, in general declustering based on the hash value of the OID of the objects has the most stable and predictable performance. [ABSTRACT FROM AUTHOR]

In this paper, we introduce two fuzzy production inventory models with fuzzy parameters for crisp production quantity, or for fuzzy production quantity. The fuzzy total production inventory costs of these models under the fuzzy arithmetical operations of Function Principle are proposed. The final purpose is to find optimal solutions of these models by using Graded Mean Integration Representation method for defuzzifing fuzzy total production inventory cost, and by using Extension of the Lagrangean method for solving inequality constrain problem. Furthermore, we find that the optimal solutions are all crisp real numbers. In addition, when the fuzzy parameters (fuzzy inventory cost, fuzzy demand, fuzzy setup cost, fuzzy demand rate, and fuzzy production rate) are all crisp real numbers, the optimal solutions of our proposed models can be specified to meet classical production inventory models. [ABSTRACT FROM AUTHOR]

Recent researches have clarified that the function of protein depends on its molecular surface. They suggest the possibility of the protein function identification based on the molecular surface comparison, in which a molecular surface of an unknown protein is compared with many surfaces of known active sites as reference templates. This paper presents an effective surface comparison method by using normal vectors with attributes of the curvature and the physical properties on projections and depressions. The vectors that should be matched are limited by extracting two vectors at similar relative positions and with the attributes of surface in order to reduce computational complexity. The proposed method was applied to 11 surface data. As a result, the mean calculation time was about 3 min, and it was possible to compare at approximately an optimal location. This method was applied to 103 surface data. The result of identification showed 95.2% identification accuracy. [ABSTRACT FROM AUTHOR]

It is becoming clear that the function of protein is activated by a local part of its molecular surface called an active site. It is impractical to compare the input surface with all of the stored active site data, because thousands of active site data whose functions are known have been stored in the active site DB. This paper proposes a method of active site data filtering, in which only the limited active site data that are expected to be similar to the input protein are roughly filtered for the high-speed retrieval. In this method, characteristic regions, which are defined as parts of the surface that show a similar property, are extracted based on the idea that some similar regions in property and shape are observed in a set of similar protein surfaces. A similarity score between input protein and an active site is roughly calculated by using characteristic regions extracted from each of them. The method was applied to a set of 556 enzyme proteins. The effectiveness of the method was confirmed by the fact that it can shorten the retrieval time to 7.2% of the total retrieval for 90.2% input proteins. [ABSTRACT FROM AUTHOR]

Microarray expression data is being generated by the gigabyte all over the world with undoubted exponential increases to come. Annotated genomic data is also rapidly pouring into public databases. Our goal is to develop automated ways of combining these two sources of information to produce insight into the operation of cells under various conditions. Our approach is to use machine-learning techniques to identify characteristics of genes that are up-regulated or down-regulated in a particular microarray experiment. We seek models that are (a) accurate, (b) easy to interpret, and (c) stable to small variations in the training data. This paper explores the effectiveness of two standard machine-learning algorithms for this task: Naive Bayes (based on probability) and PFOIL (based on building rules). Although we do not anticipate using our learned models to predict expression levels of genes, we cast the task in a predictive framework, and evaluate the quality of the models in terms of their predictive power on genes held out from the training. The paper reports on experiments using actual E. coli microarray data, discussing the strengths and weaknesses of the two algorithms and demonstrating the trade-otis between accuracy, comprehensibility, and stability. [ABSTRACT FROM AUTHOR]

In recent years a number of methods have been proposed for reverse engineering of genetic networks from gene expression data. These methods work well on small genetic networks with very few connections between genes, but for larger networks and networks with higher connectivity, the computational cost increases dramatically and the performance of these methods is insufficient. In real systems, however, it is known that the networks are large and that genes typically have many interactions. In addition, the methods require abundant expression data for derivation of the networks. A method that can derive networks irrespective of these obstacles and have a low computational cost will be of importance. In this paper, three correlation-based methods are investigated as alternatives. Using correlation-based methods means that the computational cost is reduced, since only N/2 correlations have to be computed for a data set of N expression profiles. The presented methods are not limited by any maximum size of the network, nor by the connectivity of the network, or the amount of expression data. [ABSTRACT FROM AUTHOR]

In this paper, we consider the problem of extracting multiple unordered short motifs in upstream regions of given genes. Multiple unordered short motifs can be considered as a set of short motifs, say M = (m[sub 1],m[sub 2], …,m[sub k]). For a gene g, if each of the motifs m[sub 1], …, m[sub k] occurs in either the upstream region or its complement of g, the gene g is said to be consistent with M. We have developed a fast method to exhaustively search collections of short motifs over given short motifs for a particular set of genes, and rank collections with using multiple objective functions. This method is implemented by employing bit operations in the process of matching short motifs with upstream regions, and identifying the members of genes which are consistent with short motifs. On various putatively co-regulated genes of Sacchromyces cerevisiae, determined by gene expression profiles, our computational experiments show biologically interesting results. [ABSTRACT FROM AUTHOR]

Online analytical processing (OLAP) systems have been introduced to facilitate decision support applications. While most previous studies deal with the situation where the aggregate functions are applied to all cells in a given range, this paper considers a class of queries, called the Partial-MAX/MIN query, that are applied only to specified cells in a given range. We propose the Rank Index and Rank Decision Tree (RD-Tree) for efficient processing of the partial-max/min queries. Through experiments, we show our approach has an efficient and robust processing capability for partial-max/min queries. [ABSTRACT FROM AUTHOR]

This paper investigates non-closure properties of the classes of sets accepted by space-bounded two-dimensional alternating Turing machines and three-way twodimensional alternating Turing machines. Let 2-ATM(L(tn, n)) (resp., TR2-ATM(L(m, n))) be the class of sets accepted by L(m, n) space-bounded two-dimensional alternating Turing machines (resp., L(m, n) space-bounded three-way two-dimensional alternating Turing machines), where L(m,n): N² → N cup; {0} (N denotes the set of all the positive integers) is a function with two variables m ( = the number of rows of input tapes) and n ( = the number of columns of input tapes). We show that (i) for any function g(n) = o(log n) (resp., g(n) = o(log n/log log n)) and any monotonic non-decreasing function f(m) which can be constructed by some one-dimensional deterministic Turing machine, 2-ATM(L(m,n)) and TR2-ATM(L(m, n)) are not closed under column catenation, column +, and projection, and (ii) for any function f(m) = o(log m) (resp., f(m) = o(log m/log log m)) and any monotonic non-decreasing function g(n) which can be constructed by some one-dimensional deterministic Turing machine, 2-ATM(L(m, n)) and TR2-ATM(L(m,n)) are not closed under row catenation, row +, and projection, where L(m,n) = f(m) + g(n) (resp., L(m,n) = f(m) x g(n). [ABSTRACT FROM AUTHOR]

Sorting in database processing is frequently required through the use of Order By and Distinct clauses in SQL. Sorting is also widely known in computer science community at large. Sorting in general covers internal and external sorting. Past published work has extensively focused on external sorting on uni-processors (serial external sorting), and internal sorting on multi-processors (parallel internal sorting). External sorting on multi-processors (parallel external sorting) has received surprisingly little attention; furthermore, the way current parallel database systems do sorting is far from optimal in many scenarios. In this paper, we present a taxonomy for parallel sorting in parallel database systems, which covers five sorting methods: namely parallel merge-all sort, parallel binary-merge sort, parallel redistribution binary-merge sort, parallel redistribution merge-all sort, and parallel partitioned sort. The first two methods are previously proposed approaches to parallel external sorting which have been adopted as status quo of parallel database sorting, whereas the latter three methods which are based on redistribution and repartitioning are new that have not been discussed in the literature of parallel external sorting. Performance of these five methods is investigated and the results are reported. [ABSTRACT FROM AUTHOR]

A genetic algorithm-based efficient clustering technique that utilizes the principles of K-Means algorithm is described in this paper. The algorithm called KGA-clustering, while exploiting the searching capability of K-Means, avoids its major limitation of getting stuck at locally optimal values. Its superiority over the K-Means algorithm and another genetic algorithm-based clustering method, is extensively demonstrated for several artificial and real life data sets. A real life application of the KGA-clustering in classifying the pixels of a satellite image of a part of the city of Mumbai is provided. [ABSTRACT FROM AUTHOR]

In this paper, fuzzy quantitative models of language statistics are constructed. All suggested models are based on the assumption about a superposition of two kinds of uncertainties: probabilistic and possibilistic. The realization of this superposition in statistical distributions is achieved by the probability measure splitting procedure. In this way, the fuzzy versions of generalized binomial, Fucks and Zipf–Mandelbrot’s distributions are constructed describing the probabilistic and possibilistic organization of language at any level: morphological, syntactic or phonological. The main problem when constructing the quantitative model of some fuzzy linear structure is finding the corresponding linguistic spectrum, which is reduced to the solution of algebraic or transcendental equation systems by inverse spline-interpolation. In the final section, the general linear mathematical model of language structures is then described briefly, as well as bag statistics for consonantal structures of languages. [Copyright &y& Elsevier]

In this paper continuous-time recurrent multilayer perceptrons (RMLP) are proposed to identify nonlinear systems. Using the function approximation theorem for multilayer perceptrons (MLP), we conclude that RMLP can approximate any dynamic system in any degree of accuracy. By means of a Lyapunov-like analysis, a stable learning algorithm for RMLP is determined. The suggested learning algorithm is similar to the well-known backpropagation rule of the MLP but with an additional term which assure the stability of identification error. [Copyright &y& Elsevier]

By a data conflict in a distributed system we understand a situation (or a state of the system) in which the system sites generate and store different versions of data which represent the same subject (problem solution, event scenario, etc.). Thus in purpose to solve this problem the management system should determine one proper version for the data. The final data version is called a consensus of given versions. In this paper for given conflict situation we propose to solve a consensus problem by means of a consensus function. We present elements of a consensus system, the postulates for consensus choice functions, their analysis and algorithms for consensus determining. [Copyright &y& Elsevier]

Database systems frequently establish the B-tree style indexes for fast access to data records. Since the B-tree index could be a performance bottleneck, many concurrent algorithms have been proposed to improve concurrency of B-tree accesses. In this paper we propose a new concurrent B+-tree algorithm that provides high concurrency and an efficient tree restructuring method. As the proposed method of tree restructuring always preserves a semantically consistent state of the B+-tree, a key searcher need not require any lock for a range search and a single-key search. When handling overflow or underflow in leaf nodes, it is very crucial to maintain correctly the link fields at the leaf level constructed for efficient range searches. For this, we make each leaf node contain two key-range indicators and develop a tree restructuring method using these key-range indicators. In addition, since we prevent update processes from accessing nodes updated by others that do not commit, a recovery capability on the proposed B+-tree can be easily achieved based on the record-oriented redo/undo. [Copyright &y& Elsevier]

This paper focuses on the notion of fuzzy association rules that are of the form X⇒Y, where either X or Y is a collection of fuzzy sets. The work stems from two observations. First, in generalized association rule mining, the taxonomies concerned may not be crisp but fuzzy (e.g., “Tomato” could be regarded as both “Fruit” and “Vegetable”, each at a different degree). Second, managers often refer to decision rules in terms of linguistic expressions that may or may not be the nodes of the taxonomies (e.g., “VERY ‘Expensive cloth’ ” ⇒ “Tropical fruit”). The paper deals with the fuzziness based upon fuzzy taxonomies that reflect partial belongings among itemsets, as well as upon the extended settings for the degree of support and the degree of confidence. Apriori algorithms are extended accordingly to discover association rules across the higher-level taxonomic nodes which are fuzzy sets in general. As a result, the discovered rules are fuzzy rules. Furthermore, linguistic hedges are also incorporated in mining fuzzy rules to express more meaningful knowledge. Moreover, the extended algorithms are tested with the synthetic data, revealing similar computational complexities to that of the classical algorithm. Finally, the extended algorithms are applied to a real data set with an explanation of the semantics of discovered fuzzy rules. [Copyright &y& Elsevier]

This paper presents the control methodology for uncertain chaotic dynamics of Lorenz systems. An adaptive fuzzy control (AFC) scheme based on well-known Takagi–Sugeno (T–S) fuzzy models for the MIMO plants is constructed. The developed control law and adaptive law guarantee the boundedness of all signals in the closed-loop system. In addition, the chaotic state tracks the state of the stable reference model (SRM) asymptotically with time for any bounded reference input signal. The proposed control is applied to control of an uncertain Lorenz system such as stabilization, synchronization and chaotic model following control (CMFC). [Copyright &y& Elsevier]

In this paper, we generalize results of Wang and Li [Fuzzy Sets and Systems 98 (1998) 331] on interval-valued fuzzy numbers and extend their operations with simple proofs. We also consider some algebraic properties and a distance measure for interval-valued fuzzy numbers. [Copyright &y& Elsevier]

A LR parsing table is generally made use of the parsing process based on the context free grammar for natural languages. Besides the parsing process, it can be used as the index of approximate pattern matching and error correction, because it has the characteristic to be able to predict the next character in the sentence. As for the issue of the traditional LR parsing table, however we can mention if the number of sequences to be processed becomes large, many reduce actions will be created in the parsing table, as a result, it takes a great deal of time to parse the sentence. In this paper, we propose the method to construct a new LR parsing table without reduce actions from the generalized context free grammar. This new parsing table denotes the states to be transited after accepting each symbol. Moreover, we applied this new parsing table to detect and correct erroneous sentences which include the syntax errors, unknown words and misspelling. By using this table, the symbol which is allocated just after the error position can be utilized for selecting correction symbols, as a result, the number of candidates produced on the correction process is reduced, and fast system can be realized. The experiment results, using 1050 sentences including error characters, show that this method can correct error points 69 times faster than the traditional method, also keep the almost same correction accuracy as the traditional method. [Copyright &y& Elsevier]

This paper shows that each rough set can be evaluated from two different aspects which may be considered as two facets of rough sets. One refers to the conceptual meaning of each rough set, e.g., we say that the concept of lion is included in the concept of animal and the concept of animal has a higher order of inclusion than the concept of lion. The second one refers to the amount of knowledge that each rough set exhibits, e.g., a zoologist may consider a more informative rough set for the concept of lion (he considers more kinds of lions in his set) than a rough set which proposed by a nonspecialist person. So, the first facet views the theory of rough set as an extension of the classical set theory in terms of the three-valued logic which is a proper tool of reasoning and decision making based on a solitary source of information. The second facet concerns the ability of rough set theory to knowledge manipulation and reduction among several information sources such that we do not care the soundness or falsity of the available information. We show that the second facet is the salient characteristic of rough sets which has the capability of being extended more in new application areas. As a result, we present a new extension of rough sets called rough communication as a proper tool of dealing with several information sources. At the end, we refer to some interesting mathematical symmetries between two facets which may be used to propose new extensions. [Copyright &y& Elsevier]

In general, developing countries lack capital and human resources to develop all industrial sectors of their countries. Therefore, they will select some of the industrial sectors concerned and invest all the money to those sectors to make unbalanced economic progress. In making economic policies, they have to use imprecise [fuzzy] information to consider many development goals. This paper applies a fuzzy goal programming approach for the optimal planning of an unbalanced development policy for developing (or underdeveloped) countries. In particular, it presents how fuzzy objectives of economic planners can be quantified through the use of specific tolerance operators in various economic growth alternatives. [Copyright &y& Elsevier]

There have been a number of previous successful efforts that show how fuzzy logic concepts have homomorphic-like stochastic correspondences, utilizing one-point coverages of appropriately constructed random sets. Independent of this and fuzzy logic considerations in general, boolean relational event algebra (BREA) has been introduced within a stochastic setting for representing prescribed compositional functions of event probabilities by single compounded event probabilities. In the special case of the functions being restricted to division corresponding to pairs of nested sets, BREA reduced to boolean conditional event algebra (BCEA). BCEA has been successfully applied to issues involving comparing, contrasting and combining rules of inference, especially for those having differing antecedents. In this paper we show how, in a new way, not only BCEA, but also more generally, RCEA, can be applied to provide homomorphic-like connections between fuzzy logic quantifiers and classical logic relations applied to random sets. This also leads to an improved consistency criterion for these connections. Finally, when the above is specialized to BCEA, a novel extension of crisp boolean conditional events is obtained, compatible with the above improved consistency criterion. [Copyright &y& Elsevier]

This paper presents FC networks which are instantaneously trained neural networks that allow rapid learning of non-binary data. These networks, which generalize the earlier corner classification (CC) networks, have been compared against Backpropagation (BP) and Radial Basis Function (RBF) networks and are seen to have excellent performance for prediction of time-series and pattern recognition. The networks can generalize using soft or hard decisions. [Copyright &y& Elsevier]

Various relevance feedback algorithms have been proposed in recent years in the area of content-based image retrieval. This paper presents some recent advances: first, the linear and kernel-based biased discriminant analysis, BiasMap, is proposed to fit the unique nature of relevance feedback as a small sample biased classification problem. As a novel variant of traditional discriminant analysis, the proposed algorithm provides a trade-off between discriminant transform and density modeling. Experimental results indicate that significant improvement in retrieval performance is achieved by the new scheme. Secondly, a word association via relevance feedback (WARF) formula is presented and tested for unification of low-level visual features and high-level semantic annotations during the process of relevance feedback. [Copyright &y& Elsevier]

Many multivariable (systems with many inputs/outputs) industrial processes can, to a good degree of approximation, be modelled by a transfer function matrix, where all of the interaction occurs in a matrix of constant coefficients. This reflects the fact that the dynamics of the section in which the interaction occurs are very fast compared with the other dynamics in the system. Examples of such systems include steel rolling mills and boiler systems.Such multivariable systems are relatively easy to design controllers for, since the system may be diagonalised by an inverse of the constant gain matrix, followed by suitable single-loop dynamic compensation. However, this approach depends on the linearity of the dynamical elements in the system. Such a condition is voilated by the presence of non-linear actuators, which are a feature of many industrial systems. The presence of such actuators within a multivariable control system as described above can cause very significant interaction problems, with associated degradation in performance, particularly during transients.This paper describes a straightforward technique, which is effective in linearising typical non-linear industrial actuators, allowing diagonalisation to be effectively achieved at all frequencies. The technique relies on a simple describing function analysis and manifests itself as a time-varying linearising precompensator for each non-linear actuator. A simple example is used to demonstrate the effectiveness of the method and it is then shown in application with multivariable boiler and steel mill models. [Copyright &y& Elsevier]