Neural network payload estimation for adaptive robot control

A concept is proposed for utilizing artificial neural networks to enhance the high-speed tracking accuracy of robotic manipulators. Tracking accuracy is a function of the controller's ability to compensate for disturbances produced by dynamical interactions between the links. A model-based control algorithm uses a nominal model of those dynamical interactions to reduce the disturbances. The problem is how to provide accurate dynamics information to the controller in the presence of payload uncertainty and modeling error. Neural network payload estimation uses a series of artificial neural networks to recognize the payload variation associated with a degradation in tracking performance. The network outputs are combined with a knowledge of nominal dynamics to produce a computationally efficient direct form of adaptive control. The concept is validated through experimentation and analysis on the first three links of a PUMA-560 manipulator. A multilayer perceptron architecture with two hidden layers is used. Integration of the principles of neural network pattern recognition and model-based control produces a tracking algorithm with enhanced robustness to incomplete dynamic information. Tracking efficacy and applicability to robust control algorithms are discussed.     

A generalized EM algorithm for 3-D Bayesian reconstruction from Poisson data using Gibbs priors

A generalized expectation-maximization (GEM) algorithm is developed for Bayesian reconstruction, based on locally correlated Markov random-field priors in the form of Gibbs functions and on the Poisson data model. For the M-step of the algorithm, a form of coordinate gradient ascent is derived. The algorithm reduces to the EM maximum-likelihood algorithm as the Markov random-field prior tends towards a uniform distribution. Three different Gibbs function priors are examined. Reconstructions of 3-D images obtained from the Poisson model of single-photon-emission computed tomography are presented.     

Computation of 3-D velocity fields from 3-D cine CT images of a human heart

A method of computing the three-dimensional (3-D) velocity field from 3-D cine computer tomographs (CTs) of a beating heart is proposed. Using continuum theory, the authors develop two constraints on the 3-D velocity field generated by a beating heart. With these constraints, the computation of the 3-D velocity field is formulated as an optimization problem and a solution to the optimization problem is developed using the Euler-Lagrange method. The solution is then discretized for computer implementation. The authors present the results for both simulated images and clinical cine CT images of a beating heart.     

Derivation and analysis of a filtered backprojection algorithm for cone beam projection data

The authors address the problem of three-dimensional image reconstruction from cone beam projections. Modifying a result due to A.A. Kirillov (Soviet Math. Dokl., vol. 2, p.268-9, 1961), the authors derive an inversion formula for the case where the cone vertices form an unbounded curve. For the special case in which the cone vertices form a circle, an approximate reconstruction formula is developed and shown to be essentially equivalent to the practical cone-beam algorithm of L.A. Feldkamp et al. (1984). For this approximate inverse, the authors derive the resulting spatially varying point spread function, examine the effect of bandlimiting due to sampling, and compare the resulting image quality as a function of the radius of the circle formed by the cone vertices.     

Cumulating Retrieval Inhibition in Semantic and Lexical Domains.

In 3 experiments the authors examined changes in successive exemplar generation percentages within categories defined semantically (e.g., fruit-P, fruit-A, fruit-M) and by 1st letter (e.g., insect-C, sport-C, car-C), with a mixed control condition (e.g., fruit-P, insect-C, disease-M). Retrieval success declined across 12 successive items in both semantic and letter categories, with no change for the mixed condition. This retrieval inhibition is unrelated to taxonomic frequency of exemplars within either letter or semantic categorical structures. Furthermore, semantic retrieval inhibition appears to be long lasting, suggested by the decline in retrieval percentage across successive 12-item blocks in both the mixed and letter conditions. The authors suggest that different mechanisms underlie the inhibition found in the semantic (suppression) and letter (interference) conditions. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Analysis of Resolution and Noise Properties of Nonquadratically Regularized Image Reconstruction Methods for PET

We present accurate and efficient methods for estimating the spatial resolution and noise properties of nonquadratically regularized image reconstruction for positron emission tomography (PET). It is well known that quadratic regularization tends to over-smooth sharp edges. Many types of edge-preserving nonquadratic penalties have been proposed to overcome this problem. However, there has been little research on the quantitative analysis of nonquadratic regularization due to its nonlinearity. In contrast, quadratically regularized estimators are approximately linear and are well understood in terms of resolution and variance properties. We derive new approximate expressions for the linearized local perturbation response (LLPR) and variance using the Taylor expansion with the remainder term. Although the expressions are implicit, we can use them to accurately predict resolution and variance for nonquadratic regularization where the conventional expressions based on the first-order Taylor truncation fail. They also motivate us to extend the use of a certainty-based modified penalty to nonquadratic regularization cases in order to achieve spatially uniform perturbation responses, analogous to uniform spatial resolution in quadratic regularization. Finally, we develop computationally efficient methods for predicting resolution and variance of nonquadratically regularized reconstruction and present simulations that illustrate the validity of these methods.     

Improving the effectiveness of computer-delivered personalized drinking feedback interventions for college students.

This study evaluated methods of enhancing college students' retention of information provided to them in a computer-delivered personalized drinking feedback intervention and whether enhanced retention reduced alcohol consumption during the two-week period following the intervention. Participants were 98 college students who reported at least one heavy drinking episode in the past two weeks. After participating in an online, personalized drinking feedback intervention, students were randomly assigned to one of three experimental conditions: 1) typical, in which they were simply sent home, 2) reading, in which they were asked to spend the next 20 minutes re-reading the feedback, and 3) recall, in which they were asked to spend the next 20 minutes writing down as much of the information from the feedback as they could remember. Two weeks following the intervention, participants completed a recall test and provided information on their alcohol use during the previous two weeks. Results indicated that participants in the reading and recall conditions retained more of the feedback information than did participants in the typical condition. In addition, participants in the reading and recall conditions reported reduced alcohol consumption in the two-week period following the intervention, compared to those in the typical condition. Information retention partially mediated the effects of the reading and recall conditions on drinking outcomes. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Peer reviewed: environmental sleuth at work

A combination of technical approaches and forensic tools can determine historic causes, timing, and impacts of site contamination.