Search

Fault detection in gear train system is important in order to transmitting power effectively. The artificial intelligent such as neural network is widely used in fault diagnosis and substituted for traditional methods. In rotary machinery, the symptoms of vibration signals in frequency domain have been used as inputs to the neural network and diagnosis results are obtained by network computation. However, in gear or rolling bearing system, it is difficult to extract the symptoms from vibration signals in frequency domain which have shock vibration signals. The diagnosis results are not satisfied by using artificial neural network, if the training samples are not enough. The Bayesian networks (BN) is an effective method for uncertain knowledge and less information in faults diagnosis. In order to classify the instantaneous shock of vibration signals in gear train system, the statistical parameters of vibration signals in time-domain are used in this study. These statistical parameters include kurtosis, crest, skewness factors etc. There, based on the statistical parameters of vibration signals in time-domain, the fault diagnosis is implemented by using BN and compared with two methods back-propagation neural network (BPNN) and probabilistic neural network (PNN) in gear train system. [ABSTRACT FROM AUTHOR]

A new method for modeling and knowledge extraction at each neuron of a neural network using type-I fuzzy sets is presented. This approach of neuron modeling provides a new technique to adjust the fuzzy neural network (FNN) structure for feasible number of hidden neurons and efficient reduction in computation complexity. Through repeated simulations of a crisp neural network, we propose the idea that for each neuron in the network, we can obtain reduced model with high efficiency using wavelet based multiresolution analysis (MRA) to form wavelet based fuzzy weight sets (WBFWS). Triangular and Gaussian membership functions (MFs) are imposed on wavelet based crisp weight sets to form Wavelet Based Quasi Fuzzy Weight Sets (WBQFWS) and Wavelet Based Gaussian Fuzzy Weight Sets (WBGFWS). Such type of WBFWS provides good initial solution for training in type-I FNNs. Thus the possibility space for each synoptic connection is reduced significantly, resulting in fast and confident learning of FNNs. It is shown that propsed modeling approach hold low computational complexity as compared to existing type-I fuzzy neural network models. [ABSTRACT FROM AUTHOR]

The paper describes the application of an artificial neural network in natural language text reasoning. The task of knowledge discovery in text from a database, represented with a database file consisting of sentences with similar meanings but different lexico-grammatical patterns, was solved with the application of neural networks which recognize the meaning of the text using designed training files. We propose a new method for natural language text reasoning that utilizes three-layer neural networks. The paper deals with recognition algorithms of text meaning from a selected source using an artificial neural network. In this paper we present that new method for natural language text reasoning and also describe our research and tests performed on the neural network. [ABSTRACT FROM AUTHOR]

Systems of linear equations with elements being affine linear functions of fuzzy parameters are relevant to many practical problems. A method for solving such systems is proposed. It consists of two steps. First a finite number of parametric interval linear systems is solved using the direct method. Then membership functions of fuzzy solution elements are interpolated. Parameters are modeled by arbitrary fuzzy numbers with convex membership function and compact support. Conditions for existence of the fuzzy solution are given. The performance of the proposed method is presented using an illustrative example of truss structure. [ABSTRACT FROM AUTHOR]

Classical decision-theoretic planning methods assume that the probabilistic model of the domain is always accurate. We present two algorithms rLAO* and qLAO* in this paper. rLAO* and qLAO* can solve uncertainty Markov decision problems and qualitative Markov decision problems respectively. We prove that given an admissible heuristic function, both rLAO* and qLAO* can find an optimal solution. Experimental results also show that rLAO* and qLAO* inherit the merits of excellent performance of LAO* for solving uncertainty problems. [ABSTRACT FROM AUTHOR]

Research in educational adaptive hypermedia systems has been concerned with the generation of personalized courses, in this work we focus on a task of these kind of systems: the semi-automatic sequencing of didactic resources. Sequencing defines the order in which topics (and didactic resources) in a course will be presented to learners, considering for this, their previous knowledge and particular objectives. This task is based on subjective information, for example the learner knowledge, preferences, learning style, and even assessment results are perceived differently depending the context. In this paper we define an architecture for sequencing of didactic materials using fuzzy attributes and rules. [ABSTRACT FROM AUTHOR]

EQ-algebra is an algebra with three binary operations (meet, product, fuzzy equality) and a top element that has been introduced in [13] as an algebra of truth values for the fuzzy type theory (a higher-order fuzzy logic). Recall that till now, truth values in fuzzy type theory have been supposed to form either of IMTL, BL, MV or ŁΠ-algebra that are special residuated lattices. However, since fuzzy equality is a derived operation in residuated lattice, it is not so natural for fuzzy type theory as the EQ-algebra. In this paper, we continue the research of EQ-algebras. Namely, we have modified some axioms, show further properties of them and outline the filter theory. [ABSTRACT FROM AUTHOR]

Canonical completeness results for Ł$(\mathcal{C})$, the expansion of Łukasiewicz logic Ł with a countable set of truth-constants $\mathcal{C}$, have been recently proved in [5] for the case when the algebra of truth constants $\mathcal{C}$ is a subalgebra of the rational interval [0, 1] ∩ ℚ. The case when $C \not \subseteq [0, 1] \cap \mathbb{Q}$ was left as an open problem. In this paper we solve positively this open problem by showing that Ł$(\mathcal{C})$ is strongly canonical complete for finite theories for any countable subalgebra $\mathcal{C}$ of the standard Łukasiewicz chain [0,1]Ł. [ABSTRACT FROM AUTHOR]

We study the structures which satisfy a generalization of the Cantor-Bernstein theorem. This work is inspired by related results concerning quantum structures (orthomodular lattices). It has been proved that σ-complete MV-algebras satisfy a version of the Cantor-Bernstein theorem which assumes that the bounds of isomorphic intervals are boolean. This result has been extended to more general structures, e.g., effect algebras and pseudo-BCK-algebras. There is another direction of research which has been paid less attention. We ask which algebras satisfy the Cantor-Bernstein theorem in the same form as for σ-complete boolean algebras (due to Sikorski and Tarski) without any additional assumption. In the case of orthomodular lattices, it has been proved that this class is rather large. E.g., every orthomodular lattice can be embedded as a subalgebra or expressed as an epimorphic image of a member of this class. On the other hand, also the complement of this class is large in the same sense. We study the analogous question for MV-algebras and we find out interesting examples of MV-algebras which possess or do not possess this property. This contributes to the mathematical foundations by showing the scope of validity of the Cantor-Bernstein theorem in its original form. [ABSTRACT FROM AUTHOR]

Proof systems based on rules with the property that all formulas contained in the assumptions are contained as subformulas in the conclusion as well, are particularly suitable for automated proof search. Systems of this kind were found for several well-known fuzzy logics. However, for BL (Basic Logic), the logic of continuous t-norms and their residua, the situation is less satisfactory. We consider two proof systems for BL which fulfill the desired property in quite contrasting ways. [ABSTRACT FROM AUTHOR]

The problem of solvability of a system of fuzzy relation equations with sup− *-composition is considered in a finite semilinear space over a residuated lattice. In this setting the problem of solvability given above is similar to the problem of solvability of a system of linear equations in the form Ax = b. We put emphasis on a right-hand side vector b and consider the problem of solvability as a problem of characterization of all vectors b for which the original system of (fuzzy relation) equations is solvable. We prove that a system of equations with sup− *-composition is solvable if and only if b is a fixed point of the shrivel operator (introduced in this paper). Moreover, a set of all fixed points is a semi-linear subspace of an original space. Some other results are presented as well. [ABSTRACT FROM AUTHOR]

Let Ω be a complete residuated lattice. By SetF(Ω) we denote a category of sets with similarity relations (A,δ) with values in Ω. We investigate an interpretation of a first order predicate fuzzy logic in a model based on objects of this category SetF(Ω). A notion of a fuzzy set in this category is introduced and interpretation of formulas as fuzzy sets are defined. Characteristic morphisms are defined for such fuzzy sets and relationship between interpretation by fuzzy sets and interpretation defined by characteristic morphisms are investigated. [ABSTRACT FROM AUTHOR]

After generating simple evaluating syntagms which are constructed by linguistic hedges and atomic evaluating syntagms, a voting mechanism is adopted for truth values of evaluating syntagms propositions on universe D. Then, a formal context of voting mechanism about evaluating syntagms is proposed. Based on the formal context, formal concepts of evaluating syntagms are obtained, and these formal concepts are used to semantics of simple evaluating syntagms and compound evaluating syntagms which are generated by simple evaluating syntagms and the connectives ∧ , ∨ , →, ¬. [ABSTRACT FROM AUTHOR]

As a kind of logical algebra, lattice implication algebra has been applied in lattice-valued logic. Study in algebraic structure of sub-algebra of lattice implication algebra can help to construct and apply lattice implication algebra to real applications. In this paper, we studied the structural properties of sub-algebra of a finite lattice implication algebra and proposed a method for extracting a sub-algebra from it. [ABSTRACT FROM AUTHOR]

It is difficult to define a comfortable space for people. It is partly because comfortness relates to many attributes specify a space, partly because all people have different preferences, and also because even the same person changes his/her preference according the state of their health, body conditions, working states and so on. Various parameters and attributes should be controlled to realize such a comfortable space according the data-base of past usages. Information obtained from human bodies such as temperature, blood pressure, α brainwave, heart beats and etc. can be employed to adjust the space to the best condition. In order to realize a comfortable space, first we recognize human states and behabiors, and second we provide an apporpriate environment for a focal person according to his/her state. The objective of this paper is to achieve a comfortable space in terms of affectie behaviors or actions. We deal with such techneaques as KANSEI engineering. In other words, it is required to realize our comfortable environment suitable to feelings. Kansei Engineering is one to offer better products to the customers by employing human sensitivity. [ABSTRACT FROM AUTHOR]

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]

Texture is a visual feature frequently used in image analysis that has associated certain vagueness. However, the majority of the approaches found in the literature do not either consider such vagueness or they do not take into account human perception to model the related uncertainty. In this paper we model the concept of "coarseness", one of the most important textural features, by means of fuzzy sets and considering the way humans perceive this kind of texture. Specifically, we relate representative measures of coarseness with its presence degree. To obtain these "presence degrees", we collect assessments from polls filled by human subjects, performing an aggregation of such assessments. Thus, the membership function corresponding to the fuzzy set "coarseness" is modelled by using as reference set the representative measures and the aggregated data. [ABSTRACT FROM AUTHOR]

Ensemble Neural Networks are a learning paradigm where many neural networks are used together to solve a particular problem. In this paper, the relationship between the ensemble and its component neural networks is analyzed with the goal of creating of a set of nets for an ensemble with the use of a sampling-technique. This technique is such that each net in the ensemble is trained on a different sub-sample of the training data. [ABSTRACT FROM AUTHOR]

A Recurrent Trainable Neural Network (RTNN) with a two layer canonical architecture learned by a dynamic Backpropagation learning algorithm is incorporated in a Hierarchical Fuzzy-Neural Multi-Model (HFNMM) identifier, combining the fuzzy model flexibility with the learning abilities of the RTNNs. The local and global features of the proposed HFNMM identifier are implemented by a Hierarchical Sliding Mode Controller (HSMC). The proposed HSMC scheme is applied for 1-DOF mechanical plant with friction control, where the obtained comparative results show that the HSMC with a HFNMM identifier outperforms the SMC with a single RTNN identifier. [ABSTRACT FROM AUTHOR]

An improvement of a fuzzy Artificial Neural Network model based on correlation coefficients is presented. As aggregation operator to compute the net input to target neuron a uninorm is used, instead of the sum of all the influences that the neuron receives usually used in typical artificial neurons. Such combination allows increasing the model performance in problem solving. While the natural framework and the interpretability presented in the former model are preserved by using fuzzy sets, experimental results show the improvement can be accomplished by using the proposed model. Significant differences of performance with the previous model in favor of the new one, and comparable results with a traditional classifier were statistically demonstrated. It is also remarkable that the model proposed shows a better behavior in presence of irrelevant attributes than the rest of tested classifiers. [ABSTRACT FROM AUTHOR]

In this paper, we present a sufficient and necessary condition to decide whether a weakly implicative logic has the proof by cases property (PCP for short). This result gives a general method for constructing a weakly implicative fuzzy logic from any given weakly implicative logic. [ABSTRACT FROM AUTHOR]

In this paper, two new notions called core-concept and core-concept lattice are proposed and applied to collaborative recommendation system. The core-concept lattice is constructed based on the core-concept, which is extracted from rating matrix between users and items in collaborative recommendation systems. Compared with traditional FCA, it is obviously that the extraction of core-concept very easy and fast. We present the improved nearest neighbors algorithm, it use core-concept lattice as an index to the recommendation's ratings matrix. The improved nearest neighbors algorithm could remarkably accelerate finding the nearest neighbors. Therefore, it could evidently improve efficiency of recommendation. [ABSTRACT FROM AUTHOR]

This paper presents a Fuzzy-Lyapunov approach to design trajectory tracking controllers. This methodology uses a Lyapunov function candidate to obtain the rules of the Mamdani-type fuzzy controllers which are implemented to track a desired trajectory. Two fuzzy controllers are implemented to control the position and velocity of a servo trainer and real time results are presented to evaluate the performance of designed controllers against the performance of classical controller. [ABSTRACT FROM AUTHOR]

Temperature control system (TCS) of texturing machine (TM) has many control channels, requires high control precision, and it is prone to be influenced by peripheral environmental factors. Since traditional temperature control method hardly realize ideal control effect, a kind of TCS realization method based on self-turning PID technology for constant temperature box (CTB) of TM was put forward based on the wide analysis of characteristics and methods of TCS. According to structure characteristic and working environment of TM-CTB, its discrete mathematics model was established by thermodynamics principle. The self-turning PID minimum phase control system for TM temperature controller was designed using pole points placement method, and its application instance was established by embedded system technology. System parameters were identified by recursion least square method, and forgetting factor was introduced to improve the model tracing ability of TCS. Experiments results showed that the method can satisfy the multi-channel requirement of texturing machine TCS, and its temperature control error can be limited under one percent. [ABSTRACT FROM AUTHOR]

The work describes an automatically on-line Self-Tunable Fuzzy Inference System (STFIS) of a mini-flying called XSF drone. A Fuzzy controller based on an on-line optimization of a zero order Takagi-Sugeno fuzzy inference system (FIS) by a back propagation-like algorithm is successfully applied. It is used to minimize a cost function that is made up of a quadratic error term and a weight decay term that prevents an excessive growth of parameters. Simulation results and a comparison with a Static Feedback Linearization controller (SFL) are presented and discussed. A path-like flying road, described as straight-lines with rounded corners permits to prove the effectiveness of the proposed control law. [ABSTRACT FROM AUTHOR]

Location services are used in mobile ad hoc and hybrid networks either to locate the geographic position of a given node in the network or for locating a data item. One of the main usages of position location services is in location based routing algorithms. In particular, geographic routing protocols can route messages more efficiently to their destinations based on the destination node's geographic position, which is provided by a location service. In this paper, we propose an adaptive location service on the basis of fuzzy logic called FHLS (Fuzzy Hierarchical Location Service) for mobile ad hoc networks. The FHLS uses the adaptive location update scheme using the fuzzy logic on the basis of the mobility and the call preference of mobile nodes. The performance of the FHLS is to be evaluated by using a simulation, and compared with that of existing HLS scheme. [ABSTRACT FROM AUTHOR]

In this paper, the robust stability analysis of a fuzzy vehicle lateral system with perturbed parameters is presented. Firstly, the fuzzy controller can be linearized by utilizing the describing function method with experiments. After the describing function is obtained, the stability analysis of the vehicle lateral control system with the variations of velocity and friction is then carried out by the use of parameter plane method. Afterward some limit cycle loci caused by the fuzzy controller can be easily pointed out in the parameter plane. Computer simulation shows the efficiency of this approach. [ABSTRACT FROM AUTHOR]

Bio-signal/behavior pattern acquisition and its use are essential in human-friendly human-robot interaction to recognize human intention. However, it is usually difficult to model and handle such interaction due to variability of the user's behavior and uncertainty of the environment in human-in-the-loop system. In this paper, we shall show the benefits of a PFR (probabilistic fuzzy rule)-based learning system to handle inconsistent data pattern in view of combining fuzzy logic, fuzzy clustering, and probabilistic reasoning in a single system as an effective engineering solution to resolve inconsistency of the complicated human behavioral characteristics. Moreover, we introduce a PFR-based inductive life-long learning structure for continual adaptation throughout incessant learning and control. The learning system gradually extracts more meaningful/reliable rule-based knowledge in incorporation of learning processes in short-term memory, interim transition memory and long-term memory. To show the effectiveness of the proposed system, we introduce a successful example as a case study in view of probabilistic fuzzy rule-based knowledge discovery to handle TV watching behavior data pattern learning. [ABSTRACT FROM AUTHOR]

We introduce an alternative method to approach the addition of discrete fuzzy numbers when the application of the Zadeh's extension principle does not obtain a convex membership function. [ABSTRACT FROM AUTHOR]

Although search engines represent the main means to access on-line data, the increasing demand in terms of performance, precision and relevance in the information retrieval is too far from to being acceptable. The gap existing between the wanted information and the gathered information is often bound to hindrances of semantic rather than syntactic nature. The continuing growth of the Internet usage and contents makes difficult the information access, making the task of information retrieval highly critical. The paper introduces a system for supporting the Web search activity: on the basis of the interpretation of input query, a suitable list of links to relevant web pages is presented to the user. In fact, the system builds additional queries whose content is similar to the initial one and returns a refined list, resulting from the "multiple" query submissions. [ABSTRACT FROM AUTHOR]

J-K flip-flops are elementary digital units providing sequential features/memory functions. Their definitive equation is used both in the minimal disjunctive and conjunctive forms. Fuzzy connectives do not satisfy all Boolean axioms, thus the fuzzy equivalents of these equations result in two non-equivalent definitions, "reset and set type" fuzzy flip-flops (F3) by Hirota & al. when introducing the concept of F3. There are many alternatives for "fuzzifying" digital flip-flops, using standard, algebraic or other connectives. The paper gives an overview of some of the most famous F3-s by presenting their definitions and presenting graphs of the inner state for a typical state value situation. Then a pair of non-associative operators is introduced, and the properties of the respective F3 are discussed. The investigation of possible fuzzy flip-flops is continued by examining Türkşen's IVFS, its midpoint values, and by introducing "minimized IVFS" (MIVFS), along with the MIVFS midpoints. [ABSTRACT FROM AUTHOR]

In this paper, we focus on the linguistic-valued logic system with truth-values in the lattice-ordered linguistic truth-valued algebra, then investigate its satisfiability problem and its corresponding Quasi-Horn-clause logic framework, while their soundness and completeness theorems are provided. The present framework reflects the symbolic approach acts by direct reasoning on linguistic truth values, i.e., reasoning with words, and provides a theoretical support for natural-language based reasoning and decision making system. [ABSTRACT FROM AUTHOR]

Defining the standard Boolean operations on fuzzy Booleans with the compositional rule of inference (CRI) or Zadeh's extension principle gives counter-intuitive results. We introduce and motivate a slight adaptation of the CRI, which only effects the results for non-normal fuzzy sets. It is shown that the adapted CRI gives the expected results for the standard Boolean operations on fuzzy Booleans. As a second application, we show that the adapted CRI enables a don't-care value in approximate reasoning. From the close connection between the CRI and Zadeh's extension principle, we derive an adaptation of the extension principle, which, like the modified CRI, also gives the expected Boolean operations on fuzzy Booleans. [ABSTRACT FROM AUTHOR]

The proposition about generalization of the existence of the residuum for left continuous uninorm U on a commutative, residuated l-monoid, with a neutral element is proved. The question raised previously was whether there are general operation groups which satisfy the residuum-based approximate reasoning, but at the same time are easily comprehensible and acceptable to application-oriented experts. The basic backgrounds of this research are the distance-based operators. [ABSTRACT FROM AUTHOR]

Fuzzy quantifiers have important applications in a great variety of fields such as database querying, data mining and knowledge discovering, inductive learning and so on. Recently, M.S.Ying introduces a novel fuzzy framework for linguistic quantifiers which are modeled by Sugeno integrals. Essentially, the conjunction and disjunction in Ying's framework are interpreted as the "min" and "max" operations, which restricts the application of this theory in some sense. In this paper, we extended Ying's framework by interpreting the conjunction and disjunction as t-norm and t-conorm respectively. And some elegant logical results for our framework have been obtained. [ABSTRACT FROM AUTHOR]

Probability and possibility are both convenient scales of uncertainty, because they are defined by a distribution function. They also have complementary properties in the sense that probability is a quantitative and objective ratio scale, while possibility is a qualitative and subjective ordinal scale. The paper discusses probabilistic and possibilistic causal models with a time-series effect from the viewpoint of Evidence theory, and shows that they can be defined by a single equation with different conditions of focal elements using the basic probability assignments. The equation could be recognized as a causal model with a general representation of uncertainty in the form of Evidence theory. The paper finalizes the discussion with the properties of the generalized uncertain causal model. [ABSTRACT FROM AUTHOR]

With the rapid growth of web services on the Internet, users are experiencing access delays more often than ever. Recent studies showed that web prefetching could alleviate the WWW latency to a larger extent than the traditional caching. Web prefetching is one of the most popular strategies in web mining research domain, which are proposed for reducing the perceived access delay, improving the service quality of web site and mining the user requirement information in advance. In this paper, we introduce the features of the web site model named web ontology, and build a web prefetching agent-WebAGENT based on the web ontology and the hidden Markov model. With the agent, we analyze the user access path and how to mine the latent information requirement concepts, then we could make semantic-based prefetching decisions. Experimental results show that the web prefetching scheme of the WebAGENT has better predictive mining effect and prefetching precision. [ABSTRACT FROM AUTHOR]

Spam is in spate, which accounts for over 60 percent of all emails in the world recently. Researchers are trying to develop ways to fight it but few are effective. The paper put forward a new filtering scheme based on grid technology and statistical method, which regards the user computers and email servers as nodes of the grid. They contribute and consume statistics information on the grid platform. If the number of copies of an email is obviously err from normal value, to flag it as a spam then can be a reasonable operation. As more and more nodes join the platform, the filtering precision can be further improved, just as the simulation study shows. [ABSTRACT FROM AUTHOR]

For graphs of various local complex degrees, this paper will investigate their fitting approach and conduct experiments by using the mixture processing method which is a combination of the Box dimension's pretreatment with self-affine fractal interpolation function (AFIF). [ABSTRACT FROM AUTHOR]

The paper explores some crucial technologies of Distributed Database in University MIS, such as the distribution and replication of data, and studies its feasibility on the basis of campus networks. [ABSTRACT FROM AUTHOR]

Fractal image coding is a novel technique for still image compression. Compared with the distance between the range block and the matching domain block, setting of the initial threshold value is one of the most difficult problems in Fisher Quadtree-based fractal image coding. In this paper, a novel fractal image coding based on Quadtree partition of the adaptive threshold value is proposed. Considering the input image feature fully, we put forward the computation derivation process of the adaptive threshold value progressively and declare that the adaptive threshold value has the direct proportion with the variance of the current range block. Experimental results show that compared with Fisher Quadtree-based fractal coding for the same image, the proposed coding scheme obtains better performance including the improved quality of the decoded image, shorter compression time and higher compression ratio. [ABSTRACT FROM AUTHOR]

Bucket sort algorithm is an effective approach to sort very large files, whereas the probability of bucket overflow hinders its efficiency. The paper puts forward a more effective bucket sort algorithm, THShort2, which subtly handles the overflowed buckets. For a different degree of bucket overflow, we propose a corresponding processing scheme. The correctness and efficiency of THShort2 is proofed theoretically. The experiment results show that the performance of THSort2 is about triple times of NTSort, and 50% faster than THSort. [ABSTRACT FROM AUTHOR]

In the present paper, the weak completeness of a-resolution principle for a lattice-valued logic (Ln ×L2)P(X) with truth value in a logical algebra ( lattice implication algebra Ln ×L2, is established. Accordingly, the weak completeness of (Exactly, True)-resolution principle for a linguistic truth-valued propositional logic ℓ based on the linguistic truth-valued lattice implication algebra L-LIA is derived. [ABSTRACT FROM AUTHOR]

In many applications fields, we can obtain benefits from analyzing large distributed data sets by using the high performance computational power. The Grid provides an unrivalled technology for large scale distributed computing as it enables collaboration over the global and the use of distributed computing resources, while also facilitating access to geographically distributed data sets. In this paper, we present a framework for high performance DDM applications in Computational Grid environments called DMGrid, which is based on Grid mechanisms and implemented on top of the Globus 4.0 toolkit. [ABSTRACT FROM AUTHOR]

In this paper, we develop a decision-based questionnaire system. Toward this end, we use evolutionary computation techniques. Initially, we work on a first order aggregation model and performed its learning using genetic algorithms, in which these preferences will be represented by a weighting vector associated with the variables involved in the aggregation process. In this model tree nodes represent aggregators, terminals or leaves correspond to variables, and weight values are added to the children branches for each aggregator. The parameters characterizing this multi-aggregation model are aggregators, weights and their combination in form of a tree structure. In this case, the learning process has to find the optimal combination of these parameters based on training data. In this learning process, the evolution principle remains the same as in a conventional GP but the DNA encoding needs to be defined according to the considered problem [ABSTRACT FROM AUTHOR]

Disruption on a supply chain provokes lost that can be minimized through an alternative solution. This solution involves a strategy to manage the impact of the disruption and thus to recuperate the supply chain. Difficulty of this management is the diversity of factors such that becomes complex to provide or choice a solution among the possible ones. Depending on the objective(s) to optimize are the strategy to follow and the solution to choice. In this work the Fast Elitist Non-Dominated Sorting Genetic Algorithm for Multi-Objective Optimization NSGA-II is used as the strategy to generate and optimize (minimize) solutions (lost) in front of a disruption. The included objectives are cost, risk and the place of facilities supporting the supply chain recuperation. These objectives are combined to generate possible solutions and to choice one such that it provides a proposal to minimize the disruption impact on a delimited period of time. Advantage of NSGA-II utilization is the provision of a practical formal and computational tool to analyze different scenarios without simplifies the complexity of a standard real supply chain. The illustrative exercise presents recovery scenarios for a crude oil refinery supply chain. [ABSTRACT FROM AUTHOR]