By Topic

Systems, Man and Cybernetics, IEEE Transactions on

Issue 2 • Date Mar/Apr 1991

Filter Results

Displaying Results 1 - 21 of 21
  • Plan recognition and generalization in command languages with application to telerobotics

    Page(s): 327 - 338
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1180 KB)  

    A method for pragmatic inference as a necessary accompaniment to command languages is proposed. The approach taken focuses on the modeling and recognition of the human operator's intent, which relates sequences of domain actions (`plans') to changes in some model of the task environment. The salient feature of this module is that it captures some of the physical and linguistic contextual aspects of an instruction. This provides a basis for generalization and reinterpretation of the instruction in different task environments. The theoretical development is founded on previous work in computational linguistics and some models in the theory of action and intention. To illustrate these ideas, an experimental command language to a telerobot is implemented. The program consists of three different components: a robot graphic simulation, the command language itself, and the domain-independent pragmatic inference module. Examples of task instruction processes are provided to demonstrate the benefits of this approach View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A general organizer model for robotic assemblies and intelligent robotic systems

    Page(s): 302 - 317
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1480 KB)  

    A general purpose organization level model for robotic assemblies and intelligent robotic systems is proposed. The methodology and algorithm described consider both well-defined and fuzzy/imprecise environments. The user input commands to the system organizer, an IKBS, are linguistic in general and the primitive events-tasks from the task domain are in general interpreted via fuzzy sets. The constraint of task precedence and the concepts of criticality of tasks-events and valid repetitive orderings are introduced to facilitate and optimize the formulation of every complete plan capable of executing a user-requested job. An example demonstrates the applicability of the proposed algorithm to robotic assemblies View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Use of concurrent processing with the adaptive complex method for global optimization of large dynamic systems

    Page(s): 442 - 445
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (364 KB)  

    A modified version of the adaptive complex method for global optimization is described that parallelizes a procedure that is computationally serial in nature. The modified method assigns n p processors for parallel execution. Simulation tests and an implementation with parallel hardware indicate that speed-up factors with the modified method are nearly linear with np up to about 0.1k where k is the number of vertices in the optimizing complex. Since k increases linearly with problem size, the modified method can significantly reduce computation times for large optimization problems View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Information flow evaluation in autonomous groups functioning

    Page(s): 402 - 408
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (524 KB)  

    An attempt is made to show how mathematical tools can be used in the analysis of an information flow in autonomous group functioning. The analysis is descriptive in nature and provides useful IF-THEN rules that can be used to support the process of structuring an information flow between a group and its external environment as well as information exchange within a group View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A less arbitrary method for inferring cause and effect: Generalization of a medical model

    Page(s): 339 - 346
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (668 KB)  

    A method is introduced that was developed for medical research in order to distinguish between random changes and changes with reproducible causes in the natural state of an empirical system. The method differs from statistical inference in that probability is associated with relative frequency only when characterizing the natural state of a system. More generally, it is used to distinguish signal from noise. For the latter purpose, probability is scaled for the actual boundary conditions imposed by a system, and a nonlinear spectrum-like function is used to relate low probability to signal (equivalently, high probability to noise) View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Minimum inertial parameters of robots with parallelogram closed loops

    Page(s): 318 - 326
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (584 KB)  

    A symbolic method to determine the minimum set of inertial parameters of robots containing parallelogram closed loops is presented. The solution is obtained by determining the minimum inertial parameters of an equivalent tree structure. Then, the constraint equations of the closed loops are taken into account to get the global minimum inertial parameters. Direct general relations are obtained for the two steps View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A knowledge-based methodology for tuning analytical models

    Page(s): 347 - 358
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1212 KB)  

    A description is presented of a methodology, called knowledge-based tuning, that allows a human analyst and a knowledge-based system to collaborate in adjusting an analytic model. Such a methodology makes the model more acceptable to a decision-maker, and offers the potential for making better decisions than either an analyst or a model can make alone. In knowledge-base tuning, subjective judgments about missing factors are specified by the analyst in terms of linguistic variables. These linguistic variables and knowledge of the model error history are used by the tuning system to infer a specific model adjustment. A logic programming system was developed that illustrates the tuning methodology for a macroeconometric forecasting model. It empirically demonstrates how the predictability of the model can be improved View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An analysis of the effects of jitter in data acquisition on synchronous averaging

    Page(s): 456 - 463
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (572 KB)  

    A synchronously averaged signal, acquired in real time using an A/D converter, a package of service routines and a computer, can be corrupted if precautions are not taken to minimize imprecise timing (jitter). The effects of jitter on the recovery of a signal from noise by averaging is discussed. Two cases are examined. In the first case, the jitter is the result of frequency mismatch between the acquisition repetition frequency and the signal frequency. In the second case, the jitter is due to a random phase shift present in each of the acquired waveforms. Both cases result in a reduction in magnitude and a variation in latency. A detailed analysis is given deriving several statistical descriptors. It is established that these descriptors are closely related to the characteristic function of jitter. Special cases where jitter obeys the Gaussian and uniform distributions are examined. A simple technique for determining the mean and standard deviation of the jitter is also given by example View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A genetic algorithm for the linear transportation problem

    Page(s): 445 - 452
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (744 KB)  

    Genetic algorithms are adaptive procedures that find solutions to problems by an evolutionary process based on natural selection. The use of alternative genetic algorithms for solving the linear transportation problem is discussed. Using it as an example the relationship between representation structures and genetic operators is investigated for constrained problems, and the value of structures richer than bitstrings is demonstrated View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • VLSI architectures for image transformation

    Page(s): 409 - 413
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (540 KB)  

    An image transformation method that performs mapping and filling at the same time, while respecting the connectivity of the original image, is proposed. As a result, the transformations become more consistent and accurate. Its VLSI implementation can reduce the time complexity to O(N2) using a uniprocessor, where N is the dimension of the image plane. The algorithms can handle all kinds of images including those of long narrow objects that present problems to other algorithms They also reduce the errors introduced by the order in which rotation and scaling are applied. Their application to gray level images is studied. A series of experiments has been conducted to verify the performance of the proposed algorithms View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Experiments, quasi-experiments, and case studies: A review of empirical methods for evaluating decision support systems

    Page(s): 293 - 301
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1068 KB)  

    Developers of decision support systems (DSS) often fail to present empirical data supporting the claimed merits of their systems. Discussions with developers indicate that they often do not consider or know how to perform the required empirical evaluations. That problem is addressed by reviewing the issues inherent in using experiments, quasi-experiments, and case studies to evaluate DSSs. The discussion revolves around the issues of reliability and four types of validity: internal, construct, statistical conclusion, and external. The discussion is focused upon but not restricted to expert systems View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A measure of the information gain attributable to cueing

    Page(s): 434 - 442
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (924 KB)  

    The high false alarm rate of automatic target recognition systems used in conjunction with imaging systems has precluded their use as completely autonomous devices for the targeting and launching of weapons in military systems and has prompted their use primarily as an aid to final target recognition by a trained observer. Automatic target recognition systems used in this manner are termed cuers and are assumed by many to improve the probability of detection and recognition of a target by an observer searching an image. The efficacy of these cuers and methods of evaluating their performance are under investigation since no quantifiable measure exists. The author addresses the automated part of the problem and presents a proposed objective measure of cuer effectiveness based on an information measure. The usefulness of this measure is in discriminating among competing cuer designs. Cuers are classified according to the type of information that they extract from the image and a measure of information for each type of cuer is proposed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improved posterior probability estimates from prior and conditional linear constraint systems

    Page(s): 464 - 469
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (500 KB)  

    C. C. White (1986) presented a method for computing interval bounds on posterior probabilities when the priors and conditionals are described by linear constraint systems. It is shown that White's method gives an exact description of the possible posteriors in the special case where conditionals are precise and uniformity positive. A simple method for extending this result to precise zero conditionals is developed. Then, a method for computing interval ends on the posteriors is presented for the case of imprecise conditionals. These bounds are tight for interval and bounds are at least as tight as, and often tighter than, those found by White, and require little additional computational effort View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the synthesis of nonlinear continuous neural networks

    Page(s): 413 - 418
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (508 KB)  

    A synthesis technique for a class of nonlinear neural networks that subsumes J.J. Hopfield's network with graded response (1984) is presented. The network is synthesized by designing its energy function E such that the function has local minima at the prescribed attractor points. Implementation of the synthesis technique as a nonlinear programming problem is also suggested View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Θ(1) algorithm for image component labeling in a mesh connected computer

    Page(s): 427 - 433
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (556 KB)  

    A labeling algorithm for the components of a multicolored image is proposed. This image is registered in a size n×n mesh-connected computer. Each pixel is associated with a processing element. The number of operations necessary for component labeling is fixed independently of the value of n View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimation of prior and transition probabilities in multiclass finite Markov mixtures

    Page(s): 418 - 426
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (660 KB)  

    Techniques for simultaneous estimation of prior probabilities of class labels of individual pattern samples and transition probabilities between class labels of successive samples from stationary unsupervised data are presented. The prior probability estimators derived by G. R. Dattatreya and L. N. Kanal (1990) are shown to be valid convergent estimators even when the class labels of successive pattern samples are Markov dependent. A simple class of convergent estimators for the joint probabilities of class labels of successive samples is derived by constructing M2 linear equations involving 2M functions of observations, and their class conditional moments are derived. By using the properties of the tensor product of invertible matrices, it is shown that the same M functions required to estimate the prior probabilities are sufficient to ensure the uniqueness of the solution of the linear equations. Expressions for the variances and asymptotic variances of the estimates of joint class probabilities are worked out. Application areas are mentioned. Simulation results on a three class Markov problem are included View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dimensionality reduction and feature extraction applications in identifying computer users

    Page(s): 452 - 456
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (504 KB)  

    Algorithms for dimensionality reduction and feature extraction and their applications as effective pattern recognizers in identifying computer users are presented. Fisher's linear discriminant technique was used for the reduction of dimensionality of the patterns. An approach for the extraction of physical features from pattern vectors is developed. This approach relies on shuffling two pattern vectors. The shuffling approach is competitive with the use of Fisher's technique in terms of speed and results. An online identification system was developed. The system was tested over a period of five weeks, used by ten participants, and in 1.17% of cases gave the error of being unable to decide. The applications of these algorithms in identifying computer users could lead to better results in securing access to computer systems. The user types a password and the system identifies not only the word but the time between each keystroke and the next View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Expert assistance for the decision support process using hierarchical planning

    Page(s): 390 - 401
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1036 KB)  

    A decision support process (DSP), defined as an approach to decision support, uses a programming environment to aid the decision-maker. The DSP is discussed and a system architecture using a hierarchical planning approach to support DSP activities is proposed. These stages include problem solving, solution planning, tools integration, and model execution. A comparative study of DSP research with respect to these stages is made. Using a conceptual framework for DSP as the basis for proposing a system architecture for assisting DSP, the design and development concerns based on hierarchical planning and an attribute-based approach are outlined, and the system, called XDSP (expert decision support process), is described View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic assembly sequences generation by pattern matching

    Page(s): 376 - 389
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1100 KB)  

    The problem of generating all the feasible assembly sequences of a set of n parts to construct a mechanical object is formulated as a state-constrained travelling salesman problem. In generating all the assembly sequences presented, the precedence-logic relations among parts to assemble an object are transformed into a pattern-matching problem. The concept of the pattern-matching algorithm is to match liaisons or parts with one of the answers to obtain the currently last assembly operation. Equivalency between the proposed knowledge acquisition and general AND/OR precedence nominal precedence forms is also discussed. The algorithms presented are able to reduce the number of questions asked in generating the assembly sequences View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design of a knowledge-based controller for intelligent control systems

    Page(s): 368 - 375
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (680 KB)  

    A hierarchical knowledge-based controller is proposed to improve the performance of complex control systems such as robots. This controller is designed only to modify the reference input of a lower-level servo controller. Because the internal parameters and structure of the lower-level controller are not affected, commercial servo controllers can be made to perform more sophisticated tasks than originally intended. The principle of the knowledge-based controller, modification of the reference input, knowledge representation, existence of the solution, and analyses of the controller's stability and tracking error are described in detail. A self-tuning multiple-step predictor is designed as part of the controller to eliminate the undesirable effects of system time delay. Both linear and nonlinear example control systems are tested via extensive simulations and have all shown promising performances View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning in parallel distributed processing networks: Computational complexity and information content

    Page(s): 359 - 367
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (904 KB)  

    A set of experiments that precisely identify the power and limitations of the method of back-propagation is reported. The experiment on learning to compute the exclusive-OR function suggests that the computational efficiency of learning by the method of back-propagation depends on the initial weights in the network. The experiment on learning to play tic-tac-toe suggests that the information content of what is learned by the back-propagation method is dependent on the initial abstractions in the network. It also suggests that these abstractions are a major source of power for learning in parallel distributed processing networks. In addition, it is shown that the learning task addressed by connectionist methods, including the back-propagation method, is computationally intractable. These experimental and theoretical results strongly indicate that current connectionist methods may be too limited for the complex task of learning they seek to solve. It is proposed that the power of neural networks may be enhanced by developing task-specific connectionist methods View full abstract»

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