Showing papers on "Neuro-fuzzy published in 1983"
TL;DR: A realistic fuzzy reasoning algorithm and a method to identify control rules from human operators actual control actions and the performance of the proposed algorithm is examined by applying it to water cleaning process control.
821 citations
TL;DR: Numerical methods leading to a resolution of fuzzy relational equations which create a formal description of ill-defined systems are discussed and an applicability of the numerical approach is shown in solving some problems in fuzzy systems such as identification and control.
176 citations
TL;DR: This paper may be considered as a primer for applications in structural engineering by providing a justification for the fuzzy set theory and then simple fuzzy operations are developed and contrasted with those of conventional set theory.
Abstract: The process of accounting for subjective information, insight, and wisdom in structural engineering decision making is a matter of debate. One effort to include verbal ideas involves the use of the fuzzy set theory. This paper may be considered as a primer for applications in structural engineering. The first part provides a justification for the theory and then simple fuzzy operations are developed and contrasted with those of conventional set theory. Two applications are then developed. The first considers the fuzzification of objective information where cylinder test results on concrete are used as a basis for the evaluation of the actual strength in a structural member. The two may not be the same and the subjective argument to assess the concrete strength of the beam is treated by fuzzy logic. The second concerns an engineer's assessment of the damage to a structure and subsequent repairs. Here a plan for starting such a problem is provided within a rule‐based assessment system called SPERIL version ...
162 citations
TL;DR: The idea of fuzzy relational equation with generalized connectives is introduced and algorithms of resolution of this class equations are presented in details, showing some types of well-known fuzzy relational equations can be treated as special cases of a wise class of equations under discussion.
134 citations
TL;DR: This paper suggests a method of multi-dimensional fuzzy reasoning concerned with both modus ponens and modus tollens, and discusses an example to show how the method works.
117 citations
01 Jan 1983
TL;DR: This chapter discusses the application of Fuzzy Set Theory to a Risk Analysis Model of Computer Security, and a concept of A FuzzY Ideal for Multicriteria Conflict Resolution is proposed.
Abstract: Fuzzy Set Theory: Past, Present and Future.- Advances in Fuzzy Sets - An Overview.- A Survey of Some Aspects on the Research Work of Fuzzy Topology in China.- Some Properties of Fuzzy Convex Sets.- "Non-standard" Concepts in Fuzzy Topology.- The Spaces of Fuzzy Probability and Possibility.- An Algebraic System Generalizing the Fuzzy Subsets of a Set.- From the Fuzzy Statistics to the Falling Random Subsets.- On Fuzzy Relations and Partitions.- Fuzzy Set Structure with Strong Implication.- Inference Regions for Fuzzy Propositions.- Fuzzy Tree Grammar and Fuzzy Forest Grammar.- Fuzzy Production Rules: A Learning Methodology.- Decision Support with Fuzzy Production Systems.- Imprecision in Computer Vision.- Fuzzy Programming: Why and How? - Some Hints and Examples.- A Fuzzy, Heuristic, Interactive Approach to the Optimal Network Problem.- Application of Fuzzy Set Theory to Economics.- Use of Fuzzy Logic for Implementing Rule-Based Control of Industrial Processes.- A New Approach to Design of Fuzzy Controller.- Advanced Results on Applications of Fuzzy Switching Functions to Hazard Detection.- The Application of Fuzzy Set Theory to a Risk Analysis Model of Computer Security.- Fuzzy Models of Human Problem Solving.- A Concept of A Fuzzy Ideal for Multicriteria Conflict Resolution.- Appendix I: Fuzzy Set Research in People's Republic of China.- Author Index.
79 citations
01 Jan 1983
TL;DR: The authors have recently developed a method of multi-dimensional fuzzy reasoning that enables one to build a dynamic model of a system just as the authors do in terms of differential equations.
Abstract: We have heuristically designed fuzzy controllers so far since we have lacked a fuzzy model of a system. The authors have recently developed a method of multi-dimensional fuzzy reasoning that enables one to build a dynamic model of a system just as we do in terms of differential equations. This paper presents a new idea of designing a fuzzy controller based on a fuzzy model of a system.
63 citations
01 Feb 1983
TL;DR: The analytical approaches outlined here enable the analyst to use the information in a fuzzy form for narrowing down the scope of alternative decisions, by discarding those of them for which better alternatives can be found.
Abstract: A fuzzy set is a mathematical model of a collection of elements (objects) with fuzzy boundaries, which involves the possibility of gradual transition from complete belongness to nonbelongness of an element to a collection. This concept is introduced in the Fuzzy Sets Theory as the means to model mathematically fuzzy notions that are used by human beings in describing their understanding of real systems, their preferences, goals, etc. This introductory paper outlines various classes of problems of decision-making in a fuzzy environment, that is, in which information is modeled in terms of fuzzy sets and relations. The analytical approaches outlined here enable the analyst to use the information in a fuzzy form for narrowing down the scope of alternative decisions, by discarding those of them for which better alternatives can be found. A number of illustrative examples are discussed.
48 citations
01 Jan 1983
TL;DR: In many research fields it is possible to obtain good scientific results only after large amounts of data have been collected and analyzed; the analysis allows the researcher to detect regularities, similarities and discriminant features which may be useful to characterize different classes of objects.
Abstract: In many research fields it is possible to obtain good scientific results only after large amounts of data have been collected and analyzed; the analysis allows the researcher to detect regularities, similarities and discriminant features which may be useful to characterize different classes of objects. On the other hand, the manual examination of a large set of data is slow and error prone, so that many techniques have been proposed and are actually used to perform that analysis automatically (e.g. discriminant analysis); unfortunately, most of those techniques are based on mathematical methodologies which impose strong constraints on the kinds of data that can be analyzed.
28 citations
TL;DR: The relation between fuzzy information and fuzzy time is important in socioeconomic data processing and control and a measurement of fuzzy time by the volume of approximative knowledge is studied.
01 Jan 1983
TL;DR: It is argued that the use of fuzzy set theory will generally provide models of better proximity to the systems modeled than the traditional deterministic and stochastic approaches.
Abstract: The application of dynamic programming to the modeling of decision control problems arising in research and development systems management is discussed. Probabilistic models for treating an allocation problem in the context of an antiballistic missile system are first reviewed in order to set the background for the use of fuzzy sets. Fuzzy research and development (R&D) systems are exemplified in the context of allocation problems occurring in cancer research appropriation. By recourse to fuzzy set theory, fuzzy dynamic programming models with their corresponding flow charts are then developed for an allocation problem arising in R&D systems. It is argued that the use of fuzzy set theory will generally provide models of better proximity to the systems modeled than the traditional deterministic and stochastic approaches. The computational problems in fuzzy algorithms are discussed. A method for deriving the membership function values is also presented. An example of the use of the digital computer to derive computational results from the models is presented.
TL;DR: It is shown that a fuzzy system can be represented by a flow, describing the evolution of this fuzzy system in the space of fuzzy subsets of the state-space.
TL;DR: The main ideas of a work in progress concerning a very general approach to the management of relational databases with fuzzy attribute values are presented, which makes an extensive use of the dual concepts of possibility and necessity measures.
TL;DR: Some fundamental pro Menu concerned with identification and control arc formulated and several algorithms are provided and an applicability of a concept of fuzzy discretization in system analysis is pointed out.
Abstract: The paper deals with the notion of fuzzy systems described by means or fuzzy relational equations with triangular norms. Some fundamental pro Menu concerned with identification and control arc formulated and several algorithms are provided. An applicability of a concept of fuzzy discretization in system analysis is pointed out. Numerical results obtained form an illustration of theoretical background considered.
TL;DR: A framework for implementing this procedure with the aid of fuzzy subsets is developed and extended to allow for a fuzzy set type description via linguistic values and also for the inclusion of the consideration of the implementation phase.
Abstract: INTRODUCTION The ability to provide a structure for the intelligent achievement of actions by robots is becoming a very important problem. The achievement of a goal by a robot, or for that matter, any organization, is a two step operation. The first phase consists of a plan of action, and the second phase consists of an implementation of this plan to achieve the desired goals. Nilsson has suggested an approach to the problem of having a robot plan the sequence of actions necessary to achieve a goal. The structure suggested by Nilsson provides a useful one for investigating both the planning and implementation portion. Nilsson's approach uses production rules based upon a state description involving predicate calculus. We shall extend this approach to allow for a fuzzy set type description via linguistic values\" and also for the inclusion of the consideration of the implementation phase. The robot starts off with information about the current state of the environment called the initial state. He is also given information as to a desired state of the environment called the goal state. For example, a box may be located at a particular point in a room and it may be desired for him to move the box to a different location. The robot is also provided with a set of production rules describing the actions available to it for going from the initial state to the goal state. Each production rule consists of two components. The first component, called the antecedent, consists of a set of necessary conditions in the environment that are required if it is to apply or fire this production rule. That is, if these conditions are met by the present state of the environment then it can, if it desires', fire this production rule. The second component of the production, called the consequent, consists of the possible modifications to the environment as a result of implementing this production rule. Thus the effect of the firing of a production rule is the modification of the environment resulting in a new state. The overall planning phase involves the use of a search tree. We start with initial state as the root node. Each production rule whose antecedent is matched by the current state then generates a branch, a possible course of action, whose destination node is a new state determined by the current state and the consequent of the production rule. We continue expanding in tree in this manner until a state is reached that matches the goal conditions. This searching procedure results in a plan of action, the path from the initial node to the node satisfying the goal, used by the robot to achieve its desired goal. The next phase involves the actual implementation of this plan by the robot's implementation of the production rules on this path. However, since there exists some uncertainty in the consequence of each production rule the robot must check after each firing that the antecedents necessary for the next firing are there. If at some point the robot finds that he can't implement the prescribed firing rule he must now replan starting at this point. It is our purpose here to develop a framework for implementing this procedure with the aid of fuzzy subsets.
TL;DR: A fuzzy control algorithm for regulator control of multivariable systems based on a state space model of the system is introduced and its application to several linear systems is illustrated and compared with systems controlled by means of linear feedback laws as obtained via an INA-design or linear output feedback.
TL;DR: It is shown that the inference results for various fuzzy inputs A' are better than those under the ordinal compositional rule of inference which uses “max-min composition.”
01 Jan 1983
TL;DR: As the routine operations of many technical systems become increasingly automated, the roles of the human operators in these systems are becoming more and more oriented towards problem solving.
Abstract: As the routine operations of many technical systems become increasingly automated, the roles of the human operators in these systems are becoming more and more oriented towards problem solving. The human operator is required to engage in problem solving when the automation encounters a situation for which it was not designed or, when the automation fails due to hardware and/or software problems.
TL;DR: The concept of fuzziness, while interesting, points to few distinctive benefits and the need for understanding remains the need.
Abstract: Artificial intelligence has become all the rage, often by government sponsorship The concept of fuzziness, while interesting, points to few distinctive benefits Understanding remains the need
TL;DR: The scheme of fuzzy control for large scale systems - " Multilevel Fuzzy Control " (MFC) is proposed, and the methods to design the " Local FuzzY Controller " (LFC) and the Whole F fuzzy Coordinator (WFC) are given.
TL;DR: Multistage control of a stochastic system (Markov chain) in a fuzzy environment is considered and an optimal sequence of controls is sought which maximizes the probability of attainment of the fuzzy goal subject to the fuzzy constraints.
TL;DR: An essential problem of contemporary architecture, namely, that of complexity and contradiction, is examined, and it is shown in passing that the fuzzy algebra of Kandel and the fuzzy system of Zimmermann are ‘components’ — and hence special interpretative realizations — of the fuzzy structure.
22 Jun 1983
TL;DR: In this article, the applicability of fuzzy set theory to decision analysis in uncertain environments is examined by using the axiomatic system of "fuzzy statistics" and fuzzy expectation can be used as a solution to imprecise dynamical processes.
Abstract: This paper focuses on the results indicating that fuzzy expectation can be used as a solution to imprecise dynamical processes The applicability of fuzzy set theory to decision analysis in uncertain environments is examined by using the axiomatic system of "fuzzy statistics"
TL;DR: Polysymptomatic time series are transformed to an one-dimensional interpretation space by a structured fuzzy model based on vague psychological statements that results in the preference of one of them.
TL;DR: A net-making method for fuzzy clustering analysis is obtained and a method for clinical data reduction is considered that uses the concept of fuzzy clustered.
TL;DR: The general fuzzy model of the innovation is proposed and shortly discussed and the possibilities of modelling under uncertainty and the applications of fuzzy sets theory are analysed.
TL;DR: An identification method is proposed that enables one to estimate the parameters and also to evaluate the model performance and is based on fuzzy-set theory.
Abstract: An identification method is proposed that enables one to estimate the parameters and also to evaluate the model performance. The method is based on fuzzy-set theory.
TL;DR: The generalized fuzzy number -- LFN (longitudinal fuzzy number) discussed and its E-operation (extension operation) ⊕, P- operation (point by point operation) P-operation C-operation, S-operation ∪, n and - are defined.
22 Jun 1983
TL;DR: Fuzzy set theory has been extensively applied in the area of process control, from the first papers by Zadeh to the current efforts in both theory and practice.
Abstract: One of the most active areas for the application of fuzzy set theory has been in process control. We trace the development of this research, from the first papers by Zadeh to current efforts in both theory and practice. We review some themes that appear in this corpus and suggest some directions for future work. In particular, we suggest that by adopting some concepts from artificial intelligence, existing approaches to fuzzy control system design could be significantly enhanced.