By Topic

IEEE Transactions on Systems, Man, and Cybernetics

Issue 4 • Date April 1995

Filter Results

Displaying Results 1 - 20 of 20
  • Comments on "Noise injection into inputs in back propagation learning"

    Publication Year: 1995, Page(s):678 - 681
    Cited by:  Papers (15)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (389 KB)

    The generalization capacity of neural networks learning from examples is important. Several authors showed experimentally that training a neural network with noise injected inputs could improve its generalization abilities. In the original paper (ibid., vol. 22, no. 3. p. 436-40, 1992), Matsuoka explained this fact in a formal way, claiming that using noise injected inputs is equivalent to reduce ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Edge detection by regularized cubic B-spline fitting

    Publication Year: 1995, Page(s):636 - 643
    Cited by:  Papers (14)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (912 KB)

    In this paper, regularized cubic B-spline fitting (RCBS), a technique which combines conventional cubic B-splines with regularization techniques, is proposed for the detection of edges. In addition, a quantitative performance evaluation model, called the false-detected to correct-detected ratio (FCR) model, is proposed for the evaluation of edge detectors. The FCR model attempts to provide a commo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling uncertainty using enhanced tree structures in expert systems

    Publication Year: 1995, Page(s):592 - 604
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1132 KB)

    Network structures, called belief networks, have been shown to be effective for representing uncertainty in expert systems. A problem faced when making inferences in belief networks is that schemes to propagate beliefs are generally of exponential complexity. A special class of networks, called trees, have been shown to provide an efficient framework for propagating beliefs. In this paper, we pres... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy logic controllers are universal approximators

    Publication Year: 1995, Page(s):629 - 635
    Cited by:  Papers (326)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (456 KB)

    In this paper, we consider a fundamental theoretical question on why does fuzzy control have such a good performance for a wide variety of practical problems. We try to answer this fundamental question by proving that for each fixed fuzzy logic belonging to a wide class of fuzzy logics, and for each fixed type of membership function belonging to a wide class of membership functions, the fuzzy logi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Task planning and action coordination in integrated sensor-based robots

    Publication Year: 1995, Page(s):569 - 591
    Cited by:  Papers (15)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2148 KB)

    Intelligent robots interact with the real world by employing their advanced sensory mechanisms to perceive their environment, and using their effectors and tools to change the state of their environment. In this paper we introduce a System Architecture for Sensor-based Intelligent Robots (SASIR). The system architecture consists of perception, motor, task planner, knowledge-base, user interface an... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A heuristic algorithm for the recognition of printed Chinese characters

    Publication Year: 1995, Page(s):710 - 717
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (760 KB)

    A heuristic algorithm for the recognition of printed Chinese characters is presented. Preprocessing consists of identifying individual straight line primitive strokes of a Chinese character, and then identifying the sequence of occurrence of these primitive strokes in the course of two orthogonal and one diagonal scans. The results of the three scans are three ordered sets of primitive strokes tha... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hierarchical path planning in a multi-robot environment with a simple navigation function

    Publication Year: 1995, Page(s):651 - 654
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (376 KB)

    Considers the problem of robot motion planning using an approximate cell decomposition method for Cspace representation. By means of a hierarchical multilevel discretization the authors are able to reduce the complexity of the problem and to provide a practically feasible procedure for its solution. Hierarchical discretization is based on the use of a multisource distance field that is introduced ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Anticipation-based temporal pattern generation

    Publication Year: 1995, Page(s):615 - 628
    Cited by:  Papers (23)  |  Patents (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1380 KB)

    A neural network model of complex temporal pattern generation is proposed and investigated analytically and by computer simulation. Temporal pattern generation is based on recognition of the contexts of individual components. Based on its acquired experience, the model actively yields system anticipation, which then compares with the actual input flow. A mismatch triggers self-organization of cont... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Controlling a computer via facial aspect

    Publication Year: 1995, Page(s):669 - 677
    Cited by:  Papers (23)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (932 KB)

    Control of a computer workstation via face position and facial gesturing would be an important advance for people with hand or body disabilities as well as for all users. Steps toward realization of such a system are reported here. A computer system has been developed to track the eyes and the nose of a subject and to compute the direction of the face. Face direction and movement is then used to c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Two-level tree search in fuzzy expert systems

    Publication Year: 1995, Page(s):555 - 568
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1248 KB)

    Issues of rule search in fuzzy expert systems are investigated. Computation of overall similarity measure (OSM) is studied between a system observation and the left hand side of a rule for a class of T-similarity measure (SM) models. It is shown that for an n-antecedent system, if the connective AND in both the left hand side of a rule and a system observation is taken to be a t-norm operator whic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An implementation efficient learning algorithm for adaptive control using associative content addressable memory

    Publication Year: 1995, Page(s):704 - 709
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (520 KB)

    Three modifications to the Boxes-ASE/ACE reinforcement learning improves implementation efficiency and performance. A state history queue (SHQ) eliminates computations for temporally insignificant states. A dynamic link table only allocates control memory to states the system traverses. CMAC state association uses previous learning to decrease training time. Simulations show a 4-fold improvement i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A general computational framework for distributed sensing and fault-tolerant sensor integration

    Publication Year: 1995, Page(s):643 - 650
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (764 KB)

    Proposes an abstract framework to address the problem of fault-tolerant integration of information provided by multiple sensors. This paper presents a formal description of spatially distributed sensor networks, where i) clusters of sensors monitor (possible overlapping) regions of the environment; ii) sensors return measured values of a multidimensional parameter of interest; and iii) uncertainti... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimum shape construction of flexible manipulators with total weight constraint

    Publication Year: 1995, Page(s):605 - 614
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (892 KB)

    This paper addresses the problem of optimum shape design of flexible manipulators that maximizes the fundamental frequency of vibration under a specified total weight constraint. Successive iteration schemes are developed to solve the unconstrained optimum shape design problem analytically using the variational approach, while nonlinear programming methods are used to solve the constrained optimum... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Markov chain analysis on simple genetic algorithms

    Publication Year: 1995, Page(s):655 - 659
    Cited by:  Papers (94)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (432 KB)

    This paper addresses a Markov chain analysis of genetic algorithms (GAs), in particular for a variety called a modified elitist strategy. The modified elitist strategy generates the current population of M individuals by reserving the individual with the highest fitness value from the previous generation and generating M-1 individuals through a generation change. The author's analysis is based on ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A multi-valued Boltzmann machine

    Publication Year: 1995, Page(s):660 - 669
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (972 KB)

    The idea of a Hopfield network is based on the Ising spin glass model in which each spin has only two possible states: up and down. By introducing stochastic factors into this network and performing a simulated annealing process on it, it becomes a Boltzmann machine which can escape from local minimum states to achieve the global minimum. This paper generalizes the above ideas to multi-value case ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An O(1) time algorithms for computing histogram and Hough transform on a cross-bridge reconfigurable array of processors

    Publication Year: 1995, Page(s):681 - 687
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (640 KB)

    In this paper, instead of using the base-2 number system, we use a base-m number system to represent the numbers used in the proposed algorithms. Such a strategy can be used to design an O(T) time, T=[log mN]+1, prefix sum algorithm for a binary sequence with N-bit on a cross-bridge reconfigurable array of processors using N processors, where the data bus is m-bit wide. Then, this basic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Supporting operator problem solving through ecological interface design

    Publication Year: 1995, Page(s):529 - 545
    Cited by:  Papers (59)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1728 KB)

    This paper describes two experiments evaluating ecological interface design (EID), a novel theoretical framework for the design of interfaces for complex human-machine systems. According to EID, to properly support operator problem solving activities, an interface should display both the physical and functional properties of the work domain in the form of a multilevel representation based on the a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Designing genetic algorithms for the state assignment problem

    Publication Year: 1995, Page(s):687 - 694
    Cited by:  Papers (20)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (704 KB)

    Finding the best state assignment for implementing a synchronous sequential circuit is important for reducing silicon area or chip count in many digital designs. This state assignment problem (SAP) belongs to a broader class of combinatorial optimization problems than the well studied traveling salesman problem, which can be formulated as a special case of SAP. The search for a good solution is co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive coordination in distributed systems with delayed communication

    Publication Year: 1995, Page(s):546 - 554
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (768 KB)

    A new model for distributed decision making, distributed game automata, focuses on how communication affects the quality of decisions. The goal is to limit communication between decision makers such that overhead costs are reduced but good decisions still result. Learning automata play repeated games with payoffs quantifying the performance in a distributed application. Each automaton's view of th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Configuration space model of tightly coordinated two robot manipulators operating in 3-dimensional workspace

    Publication Year: 1995, Page(s):695 - 704
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (924 KB)

    Since the configuration space (C-space) model has been successfully used in studies of automatic off-line collision-free path planning, optimal trajectory planning, and optimal control of a single robot, there are attempts to apply the C-space model to the study of a tightly coordinated two robot manipulator (TCTR) system. A fundamental assumption used in the C-space model for a single robot is th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.