Globally Convergent Modification of the Quickprop Method

A mathematical framework for the convergence analysis of the well-known Quickprop method is described. Furthermore, we propose a modification of this method that exhibits improved convergence speed and stability, and, at the same time, alleviates the use of heuristic learning parameters. Simulations are conducted to compare and evaluate the performance of the new modified Quickprop algorithm with various popular training algorithms. The results of the experiments indicate that the increased convergence rates achieved by the proposed algorithm, affect by no means its generalization capability and stability.     

Detecting objects of variable shape structure with hidden state shape models

This paper proposes a method for detecting object classes that exhibit variable shape structure in heavily cluttered images. The term "variable shape structure" is used to characterize object classes in which some shape parts can be repeated an arbitrary number of times, some parts can be optional, and some parts can have several alternative appearances. Hidden State Shape Models (HSSMs), a generalization of Hidden Markov Models (HMMs), are introduced to model object classes of variable shape structure using a probabilistic framework. A polynomial inference algorithm automatically determines object location, orientation, scale and structure by finding the globally optimal registration of model states with the image features, even in the presence of clutter. Experiments with real images demonstrate that the proposed method can localize objects of variable shape structure with high accuracy. For the task of hand shape localization and structure identification, the proposed method is significantly more accurate than previously proposed methods based on chamfer-distance matching. Furthermore, by integrating simple temporal constraints, the proposed method gains speed-ups of more than an order of magnitude, and produces highly accurate results in experiments on non-rigid hand motion tracking.     

Scanned images resolution improvement using neural networks

A novel method of improving the spatial resolution of scanned images, by means of neural networks, is presented in this paper. Images of different resolution, originating from scanner, successively train a neural network, which learns to improve resolution from 25 to 50 pixels-per-inch (ppi), then from 100 to 200 ppi and finally, from 50 to 100 ppi. Thus, the network is provided with consistent knowledge regarding the point spread function (PSF) of the scanner, whilst it gains the generalization ability to reconstruct finer resolution images unfamiliar to it. The novelty of the proposed image-resolution-enhancement technique lies in the successive training of the neural structure with images of increasing resolution. Comparisons with the image scanned at 400 ppi demonstrate the superiority of our method to conventional interpolation techniques.     

Neuro-control of unmanned underwater vehicles

Unmanned underwater vehicles (UUVs) typically operate in uncertain and changing environments. Since the dynamics of UUVs are highly nonlinear and their hydrodynamic coefficients vary with different operating conditions, a high-performance control system of a UUV is needed to have the capacities of learning and adaptation to the variations in the UUV's dynamics. This paper presents the utilization of an adaptive neuro-control scheme as a controller for controlling a UUV in six degrees of freedom. No prior offline training phase and no explicit knowledge of the structure of the vehicle are required, and the proposed scheme exploits the advantages of both neural network control and adaptive control. Asymptotic convergence of the UUV's tracking errors and stability of the presented control system is guaranteed on the basis of the Lyapunov theory. In this paper, neural network architectures based on radial basis functions and multilayer structures have been used to evaluate the performance of the adaptive controller via computer simulation.     

Perceived Autonomy Support in Physical Education and Leisure-Time Physical Activity: A Cross-Cultural Evaluation of the Trans-Contextual Model.

This study tested the replicability and cross-cultural invariance of a trans-contextual model of motivation across 4 samples from diverse cultures. The model proposes a motivational sequence in which perceived autonomy support (PAS) in physical education (PE) predicts autonomous motivation, intentions, and behavior in a leisure-time (LT) physical activity context. High-school pupils from Britain, Greece, Poland, and Singapore completed measures of PAS and autonomous motives in a PE context. Goodfitting path-analytic models supported the main hypotheses of the trans-contextual model in the British, Greek, and Singaporean samples. PAS in PE had significant total effects on autonomous motives in LT, except in the Polish sample. The effect of autonomous motives in LT on physical activity intentions and behavior was mediated by theory of planned behavior constructs in all samples. Results supported the main hypotheses of the trans-contextual model across cultures, although the effect of PAS was not pervasive in the Polish sample. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A Comparison of Word- and Sense-Based Text Categorization Using Several Classification Algorithms

Most of the text categorization algorithms in the literature represent documents as collections of words. An alternative which has not been sufficiently explored is the use of word meanings, also known as senses. In this paper, using several algorithms, we compare the categorization accuracy of classifiers based on words to that of classifiers based on senses. The document collection on which this comparison takes place is a subset of the annotated Brown Corpus semantic concordance. A series of experiments indicates that the use of senses does not result in any significant categorization improvement.     

Joining silicon nitride to itself and to metals

This article reviews the progress that has been made in developing and applying joining techniques for Si₃N₄ and discusses our understanding of the influence of process selection on the materials science of the formation and properties of joints. High-performance Si₃N₄ joints can be produced, but it is clear that much work remains to be done before the use of such joints in hot-stressed applications can be disregarded as a problem.     

Developmental trajectories of motivation in physical education: Course, demographic differences, and antecedents.

This study investigated changes in student motivation to participate in physical education and some determinants of these changes over a period of 3 years. Measures were taken twice a year, from age 13 until age 15, from a sample of Greek junior high school students. Multilevel modeling analyses showed significant decreases in task-involving teacher climate, relatedness, identified regulation, and intrinsic motivation. In contrast, there were significant increases in ego-involving climate and amotivation. For some of these variables, the observed linear decreases or increases were somewhat reversed by the beginning of the last year of junior high school. No significant changes were observed in competence need satisfaction and in extrinsic and introjected regulations. The authors found substantial between-student variability in the intercepts and growth trajectories of most variables, and therefore they tested a number of theoretical and demographic predictors to partly account for such variations. The results indicate that increases in maladaptive motivation in physical education over time are not uniform across all students and may be partly tackled by facilitating competence need satisfaction. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Aerosol lidar intercomparison in the framework of the EARLINET project. 2. Aerosol backscatter algorithms

An intercomparison of aerosol backscatter lidar algorithms was performed in 2001 within the framework of the European Aerosol Research Lidar Network to Establish an Aerosol Climatology (EARLINET). The objective of this research was to test the correctness of the algorithms and the influence of the lidar ratio used by the various lidar teams involved in the EARLINET for calculation of backscatter-coefficient profiles from the lidar signals. The exercise consisted of processing synthetic lidar signals of various degrees of difficulty. One of these profiles contained height-dependent lidar ratios to test the vertical influence of those profiles on the various retrieval algorithms. Furthermore, a realistic incomplete overlap of laser beam and receiver field of view was introduced to remind the teams to take great care in the nearest range to the lidar. The intercomparison was performed in three stages with increasing knowledge on the input parameters. First, only the lidar signals were distributed; this is the most realistic stage. Afterward the lidar ratio profiles and the reference values at calibration height were provided. The unknown height-dependent lidar ratio had the largest influence on the retrieval, whereas the unknown reference value was of minor importance. These results show the necessity of making additional independent measurements, which can provide us with a suitable approximation of the lidar ratio. The final stage proves in general, that the data evaluation schemes of the different groups of lidar systems work well.