Studies on the generalisation of Gaussian processes and Bayesian neural networks

The assessment of the reliability of systems which learn from data is a key issue to investigate thoroughly before the actual application of information processing techniques to real-world problems. Over the recent years Gaussian processes and Bayesian neural networks have come to the fore and in this thesis their generalisation capabilities are analysed from theoretical and empirical perspectives. Upper and lower bounds on the learning curve of Gaussian processes are investigated in order to estimate the amount of data required to guarantee a certain level of generalisation performance. In this thesis we analyse the effects on the bounds and the learning curve induced by the smoothness of stochastic processes described by four different covariance functions. We also explain the early, linearly-decreasing behaviour of the curves and we investigate the asymptotic behaviour of the upper bounds. The effect of the noise and the characteristic lengthscale of the stochastic process on the tightness of the bounds are also discussed. The analysis is supported by several numerical simulations. The generalisation error of a Gaussian process is affected by the dimension of the input vector and may be decreased by input-variable reduction techniques. In conventional approaches to Gaussian process regression, the positive definite matrix estimating the distance between input points is often taken diagonal. In this thesis we show that a general distance matrix is able to estimate the effective dimensionality of the regression problem as well as to discover the linear transformation from the manifest variables to the hidden-feature space, with a significant reduction of the input dimension. Numerical simulations confirm the significant superiority of the general distance matrix with respect to the diagonal one.In the thesis we also present an empirical investigation of the generalisation errors of neural networks trained by two Bayesian algorithms, the Markov Chain Monte Carlo method and the evidence framework; the neural networks have been trained on the task of labelling segmented outdoor images.

A study of the problem solving strategies used by expert and novice designers

This research project focused upon the design strategies adopted by expert and novice designers. It was based upon a desire to compare the design problem solving strategies of novices, in this case key stage three pupils studying technolgy within the United Kingdom National Curriculum, with designers who could be considered to have developed expertise. The findings helped to provide insights into potential teaching strategies to suit novice designers. Verbal protocols were made as samples of expert and novice designers solved a design problem and talked aloud as they worked. The verbalisations were recorded on video tape. The protocols were transcribed and segmented, with each segment being assigned to a predetermined coding system which represented a model of design problem solving. The results of the encoding were analysed and consideration was also given to the general design strategy and heuristics used by the expert and novice designers. The drawings and models produced during the generation of the protocols were also analysed and considered. A number of significant differences between the problem solving strategies adopted by the expert and novice designers were identified. First of all, differences were observed in the way expert and novice designers used the problem statement and solution validation during the process. Differences were also identified in the way holistic solutions were generated near the start of the process, and also in the cycles of exploration and the processes of integration. The way design and technological knowledge was used provided further insights into the differences between experts and novices, as did the role of drawing and modelling during the process. In more general terms, differences were identified in the heuristics and overall design strategies adopted by the expert and novice designers. The above findings provided a basis for discussing teaching strategies appropriate for novice designers. Finally, opportunities for future research were discussed.

Application of the finite element method to problems in fracture mechanics

Numerical techniques have been finding increasing use in all aspects of fracture mechanics, and often provide the only means for analyzing fracture problems. The work presented here, is concerned with the application of the finite element method to cracked structures. The present work was directed towards the establishment of a comprehensive two-dimensional finite element, linear elastic, fracture analysis package. Significant progress has been made to this end, and features which can now be studied include multi-crack tip mixed-mode problems, involving partial crack closure. The crack tip core element was refined and special local crack tip elements were employed to reduce the element density in the neighbourhood of the core region. The work builds upon experience gained by previous research workers and, as part of the general development, the program was modified to incorporate the eight-node isoparametric quadrilateral element. Also. a more flexible solving routine was developed, and provided a very compact method of solving large sets of simultaneous equations, stored in a segmented form. To complement the finite element analysis programs, an automatic mesh generation program has been developed, which enables complex problems. involving fine element detail, to be investigated with a minimum of input data. The scheme has proven to be versati Ie and reasonably easy to implement. Numerous examples are given to demonstrate the accuracy and flexibility of the finite element technique.

Automatic object segmentation from calibrated images

This paper addresses the problem of automatically obtaining the object/background segmentation of a rigid 3D object observed in a set of images that have been calibrated for camera pose and intrinsics. Such segmentations can be used to obtain a shape representation of a potentially texture-less object by computing a visual hull. We propose an automatic approach where the object to be segmented is identified by the pose of the cameras instead of user input such as 2D bounding rectangles or brush-strokes. The key behind our method is a pairwise MRF framework that combines (a) foreground/background appearance models, (b) epipolar constraints and (c) weak stereo correspondence into a single segmentation cost function that can be efficiently solved by Graph-cuts. The segmentation thus obtained is further improved using silhouette coherency and then used to update the foreground/background appearance models which are fed into the next Graph-cut computation. These two steps are iterated until segmentation convergences. Our method can automatically provide a 3D surface representation even in texture-less scenes where MVS methods might fail. Furthermore, it confers improved performance in images where the object is not readily separable from the background in colour space, an area that previous segmentation approaches have found challenging. © 2011 IEEE.

Waveform type evaluation in congenital nystagmus

Congenital nystagmus is an ocular-motor disorder characterised by involuntary, conjugated and bilateral to and fro ocular oscillations. In this study a method to recognise automatically jerk waveform inside a congenital nystagmus recording and to compute foveation time and foveation position variability is presented. The recordings were performed with subjects looking at visual targets, presented in nine eye gaze positions; data were segmented into blocks corresponding to each gaze position. The nystagmus cycles were identified searching for local minima and maxima (SpEp sequence) in intervals centred on each slope change of the eye position signal (position criterion). The SpEp sequence was then refined using an adaptive threshold applied to the eye velocity signal; the outcome is a robust detection of each slow phase start point, fundamental to accurately compute some nystagmus parameters. A total of 1206 slow phases was used to compute the specificity in waveform recognition applying only the position criterion or adding the adaptive threshold; results showed an increase in negative predictive value of 25.1% using both features. The duration of each foveation window was measured on raw data or using an interpolating function of the congenital nystagmus slow phases; foveation time estimation less sensitive to noise was obtained in the second case. © 2010.

What drives the prediction of early reading? An analysis of stimulus and response-type

Purpose: Phonological accounts of reading implicate three aspects of phonological awareness tasks that underlie the relationship with reading; a) the language-based nature of the stimuli (words or nonwords), b) the verbal nature of the response, and c) the complexity of the stimuli (words can be segmented into units of speech). Yet, it is uncertain which task characteristics are most important as they are typically confounded. By systematically varying response-type and stimulus complexity across speech and non-speech stimuli, the current study seeks to isolate the characteristics of phonological awareness tasks that drive the prediction of early reading. Method: Four sets of tasks were created; tone stimuli (simple non-speech) requiring a non-verbal response, phonemes (simple speech) requiring a non-verbal response, phonemes requiring a verbal response, and nonwords (complex speech) requiring a verbal response. Tasks were administered to 570 2nd grade children along with standardized tests of reading and non-verbal IQ. Results: Three structural equation models comparing matched sets of tasks were built. Each model consisted of two 'task' factors with a direct link to a reading factor. The following factors predicted unique variance in reading: a) simple speech and non-speech stimuli, b) simple speech requiring a verbal response but not simple speech requiring a non-verbal-response, and c) complex and simple speech stimuli. Conclusions: Results suggest that the prediction of reading by phonological tasks is driven by the verbal nature of the response and not the complexity or 'speechness' of the stimuli. Findings highlight the importance of phonological output processes to early reading.

Service employee clusters in banking:exploring Ind's typology considering behaviour, commitment and attitude about leadership

Purpose: Ind suggests front line employees can be segmented according to their level of brand-supporting performance. His employee typology has not been empirically tested. The paper aims to explore front line employee performance in retail banking, and profile employee types. Design/methodology/approach: Attitudinal and demographic data from a sample of 404 front line service employees in a leading Irish bank informs a typology of service employees. Findings: Champions, Outsiders and Disruptors exist within retail banking. The authors provide an employee profile for each employee type. They found Champions amongst males, and older employees. The highest proportion of female employees surveyed were Outsiders. Disruptors were more likely to complain, and rated their performance lower than any other employee type. Contrary to extant literature, Disruptors were more likely to hold a permanent contract than other employee types. Originality/value: The authors augment the literature by providing insights about the profile of three employee types: Brand Champions, Outsiders and Disruptors. Moreover, the authors postulate the influence of leadership and commitment on each employee type. The cluster profiles raise important questions for hiring, training and rewarding front line banking employees. The authors also provide guidelines for managers to encourage Champions, and curtail Disruptors. © Emerald Group Publishing Limited.

Image Quotient Set Transforms in Segmentation Problems

Image content interpretation is much dependent on segmentations efficiency. Requirements for the image recognition applications lead to a nessesity to create models of new type, which will provide some adaptation between law-level image processing, when images are segmented into disjoint regions and features are extracted from each region, and high-level analysis, using obtained set of all features for making decisions. Such analysis requires some a priori information, measurable region properties, heuristics, and plausibility of computational inference. Sometimes to produce reliable true conclusion simultaneous processing of several partitions is desired. In this paper a set of operations with obtained image segmentation and a nested partitions metric are introduced.

Exploring the optimum step size for defocus curves

Purpose: To evaluate the effect of reducing the number of visual acuity measurements made in a defocus curve on the quality of data quantified. Setting: Midland Eye, Solihull, United Kingdom. Design: Evaluation of a technique. Methods: Defocus curves were constructed by measuring visual acuity on a distance logMAR letter chart, randomizing the test letters between lens presentations. The lens powers evaluated ranged between +1.50 diopters (D) and -5.00 D in 0.50 D steps, which were also presented in a randomized order. Defocus curves were measured binocularly with the Tecnis diffractive, Rezoom refractive, Lentis rotationally asymmetric segmented (+3.00 D addition [add]), and Finevision trifocal multifocal intraocular lenses (IOLs) implanted bilaterally, and also for the diffractive IOL and refractive or rotationally asymmetric segmented (+3.00 D and +1.50 D adds) multifocal IOLs implanted contralaterally. Relative and absolute range of clear-focus metrics and area metrics were calculated for curves fitted using 0.50 D, 1.00 D, and 1.50 D steps and a near add-specific profile (ie, distance, half the near add, and the full near-add powers). Results: A significant difference in simulated results was found in at least 1 of the relative or absolute range of clear-focus or area metrics for each of the multifocal designs examined when the defocus-curve step size was increased (P<.05). Conclusion: Faster methods of capturing defocus curves from multifocal IOL designs appear to distort the metric results and are therefore not valid. Financial Disclosure: No author has a financial or proprietary interest in any material or method mentioned. © 2013 ASCRS and ESCRS.

Offline Handwriting Recognition Using Genetic Algorithm

In this paper, a new method for offline handwriting recognition is presented. A robust algorithm for handwriting segmentation has been described here with the help of which individual characters can be segmented from a word selected from a paragraph of handwritten text image which is given as input to the module. Then each of the segmented characters are converted into column vectors of 625 values that are later fed into the advanced neural network setup that has been designed in the form of text files. The networks has been designed with quadruple layered neural network with 625 input and 26 output neurons each corresponding to a character from a-z, the outputs of all the four networks is fed into the genetic algorithm which has been developed using the concepts of correlation, with the help of this the overall network is optimized with the help of genetic algorithm thus providing us with recognized outputs with great efficiency of 71%.

Application of ensemble averaging to the analysis of electromyography recordings under whole body vibratory stimulation

The aim of this study is to evaluate the application of ensemble averaging to the analysis of electromyography recordings under whole body vibratory stimulation. Recordings from Rectus Femoris, collected during vibratory stimulation at different frequencies, are used. Each signal is subdivided in intervals, which time duration is related to the vibration frequency. Finally the average of the segmented intervals is performed. By using this method for the majority of the recordings the periodic components emerge. The autocorrelation of few seconds of signals confirms the presence of a pseudosinusoidal components strictly related to the soft tissues oscillations caused by the mechanical waves. © 2014 IEEE.

A laser induced breakdown spectroscopy quantitative analysis method based on the robust least squares support vector machine regression model

Data fluctuation in multiple measurements of Laser Induced Breakdown Spectroscopy (LIBS) greatly affects the accuracy of quantitative analysis. A new LIBS quantitative analysis method based on the Robust Least Squares Support Vector Machine (RLS-SVM) regression model is proposed. The usual way to enhance the analysis accuracy is to improve the quality and consistency of the emission signal, such as by averaging the spectral signals or spectrum standardization over a number of laser shots. The proposed method focuses more on how to enhance the robustness of the quantitative analysis regression model. The proposed RLS-SVM regression model originates from the Weighted Least Squares Support Vector Machine (WLS-SVM) but has an improved segmented weighting function and residual error calculation according to the statistical distribution of measured spectral data. Through the improved segmented weighting function, the information on the spectral data in the normal distribution will be retained in the regression model while the information on the outliers will be restrained or removed. Copper elemental concentration analysis experiments of 16 certified standard brass samples were carried out. The average value of relative standard deviation obtained from the RLS-SVM model was 3.06% and the root mean square error was 1.537%. The experimental results showed that the proposed method achieved better prediction accuracy and better modeling robustness compared with the quantitative analysis methods based on Partial Least Squares (PLS) regression, standard Support Vector Machine (SVM) and WLS-SVM. It was also demonstrated that the improved weighting function had better comprehensive performance in model robustness and convergence speed, compared with the four known weighting functions.

Handwritten and machine-printed text discrimination using a template matching approach

We propose a novel template matching approach for the discrimination of handwritten and machine-printed text. We first pre-process the scanned document images by performing denoising, circles/lines exclusion and word-block level segmentation. We then align and match characters in a flexible sized gallery with the segmented regions, using parallelised normalised cross-correlation. The experimental results over the Pattern Recognition & Image Analysis Research Lab-Natural History Museum (PRImA-NHM) dataset show remarkably high robustness of the algorithm in classifying cluttered, occluded and noisy samples, in addition to those with significant high missing data. The algorithm, which gives 84.0% classification rate with false positive rate 0.16 over the dataset, does not require training samples and generates compelling results as opposed to the training-based approaches, which have used the same benchmark.

Heterogeneous labour and the determination of value

Heterogeneity of labour and its implications for the Marxian theory of value has been one of the most controversial issues in the literature of the Marxist political economy. The adoption of Marx's conjecture about a uniform rate of surplus value leads to a simultaneous determination of the values of common and labour commodities of different types and the uniform rate of surplus value. Determination of these variables can be formally represented as a parametric cigenvalue problem. Morishima's and Bródy's earlier results are analysed and given new interpretations in the light of the suggested procedure. The main questions are addressed in a more general context too. The analysis is extended to the problem of segmented labour market, as well.

An indexing structure and application model for vehicles moving on road networks

Moving objects database systems are the most challenging sub-category among Spatio-Temporal database systems. A database system that updates in real-time the location information of GPS-equipped moving vehicles has to meet even stricter requirements. Currently existing data storage models and indexing mechanisms work well only when the number of moving objects in the system is relatively small. This dissertation research aimed at the real-time tracking and history retrieval of massive numbers of vehicles moving on road networks. A total solution has been provided for the real-time update of the vehicles' location and motion information, range queries on current and history data, and prediction of vehicles' movement in the near future. ^ To achieve these goals, a new approach called Segmented Time Associated to Partitioned Space (STAPS) was first proposed in this dissertation for building and manipulating the indexing structures for moving objects databases. ^ Applying the STAPS approach, an indexing structure of associating a time interval tree to each road segment was developed for real-time database systems of vehicles moving on road networks. The indexing structure uses affordable storage to support real-time data updates and efficient query processing. The data update and query processing performance it provides is consistent without restrictions such as a time window or assuming linear moving trajectories. ^ An application system design based on distributed system architecture with centralized organization was developed to maximally support the proposed data and indexing structures. The suggested system architecture is highly scalable and flexible. Finally, based on a real-world application model of vehicles moving in region-wide, main issues on the implementation of such a system were addressed. ^