Developing a probabilistic graphical structure from a model of mental-health clinical risk expertise

This paper explores the process of developing a principled approach for translating a model of mental-health risk expertise into a probabilistic graphical structure. The Galatean Risk Screening Tool [1] is a psychological model for mental health risk assessment based on fuzzy sets. This paper details how the knowledge encapsulated in the psychological model was used to develop the structure of the probability graph by exploiting the semantics of the clinical expertise. These semantics are formalised by a detailed specification for an XML structure used to represent the expertise. The component parts were then mapped to equivalent probabilistic graphical structures such as Bayesian Belief Nets and Markov Random Fields to produce a composite chain graph that provides a probabilistic classification of risk expertise to complement the expert clinical judgements. © Springer-Verlag 2010.

Variational mean-field algorithm for efficient inference in large systems of stochastic differential equations

This work introduces a Gaussian variational mean-field approximation for inference in dynamical systems which can be modeled by ordinary stochastic differential equations. This new approach allows one to express the variational free energy as a functional of the marginal moments of the approximating Gaussian process. A restriction of the moment equations to piecewise polynomial functions, over time, dramatically reduces the complexity of approximate inference for stochastic differential equation models and makes it comparable to that of discrete time hidden Markov models. The algorithm is demonstrated on state and parameter estimation for nonlinear problems with up to 1000 dimensional state vectors and compares the results empirically with various well-known inference methodologies.

O paradoxo da superdifusão de uma caminhada aleatória com memória exponencial

The random walk models with temporal correlation (i.e. memory) are of interest in the study of anomalous diffusion phenomena. The random walk and its generalizations are of prominent place in the characterization of various physical, chemical and biological phenomena. The temporal correlation is an essential feature in anomalous diffusion models. These temporal long-range correlation models can be called non-Markovian models, otherwise, the short-range time correlation counterparts are Markovian ones. Within this context, we reviewed the existing models with temporal correlation, i.e. entire memory, the elephant walk model, or partial memory, alzheimer walk model and walk model with a gaussian memory with profile. It is noticed that these models shows superdiffusion with a Hurst exponent H > 1/2. We study in this work a superdiffusive random walk model with exponentially decaying memory. This seems to be a self-contradictory statement, since it is well known that random walks with exponentially decaying temporal correlations can be approximated arbitrarily well by Markov processes and that central limit theorems prohibit superdiffusion for Markovian walks with finite variance of step sizes. The solution to the apparent paradox is that the model is genuinely non-Markovian, due to a time-dependent decay constant associated with the exponential behavior. In the end, we discuss ideas for future investigations.

Enhancing the Visualization of the Peripheral Retina with Wide Field-of-View Optical Coherence Tomography

The goal of my Ph.D. thesis is to enhance the visualization of the peripheral retina using wide-field optical coherence tomography (OCT) in a clinical setting.

OCT has gain widespread adoption in clinical ophthalmology due to its ability to visualize the diseases of the macula and central retina in three-dimensions, however, clinical OCT has a limited field-of-view of 300. There has been increasing interest to obtain high-resolution images outside of this narrow field-of-view, because three-dimensional imaging of the peripheral retina may prove to be important in the early detection of neurodegenerative diseases, such as Alzheimer's and dementia, and the monitoring of known ocular diseases, such as diabetic retinopathy, retinal vein occlusions, and choroid masses.

Before attempting to build a wide-field OCT system, we need to better understand the peripheral optics of the human eye. Shack-Hartmann wavefront sensors are commonly used tools for measuring the optical imperfections of the eye, but their acquisition speed is limited by their underlying camera hardware. The first aim of my thesis research is to create a fast method of ocular wavefront sensing such that we can measure the wavefront aberrations at numerous points across a wide visual field. In order to address aim one, we will develop a sparse Zernike reconstruction technique (SPARZER) that will enable Shack-Hartmann wavefront sensors to use as little as 1/10th of the data that would normally be required for an accurate wavefront reading. If less data needs to be acquired, then we can increase the speed at which wavefronts can be recorded.

For my second aim, we will create a sophisticated optical model that reproduces the measured aberrations of the human eye. If we know how the average eye's optics distort light, then we can engineer ophthalmic imaging systems that preemptively cancel inherent ocular aberrations. This invention will help the retinal imaging community to design systems that are capable of acquiring high resolution images across a wide visual field. The proposed model eye is also of interest to the field of vision science as it aids in the study of how anatomy affects visual performance in the peripheral retina.

Using the optical model from aim two, we will design and reduce to practice a clinical OCT system that is capable of imaging a large (800) field-of-view with enhanced visualization of the peripheral retina. A key aspect of this third and final aim is to make the imaging system compatible with standard clinical practices. To this end, we will incorporate sensorless adaptive optics in order to correct the inter- and intra- patient variability in ophthalmic aberrations. Sensorless adaptive optics will improve both the brightness (signal) and clarity (resolution) of features in the peripheral retina without affecting the size of the imaging system.

The proposed work should not only be a noteworthy contribution to the ophthalmic and engineering communities, but it should strengthen our existing collaborations with the Duke Eye Center by advancing their capability to diagnose pathologies of the peripheral retinal.

Sensor Planning for Bayesian Nonparametric Target Modeling

Bayesian nonparametric models, such as the Gaussian process and the Dirichlet process, have been extensively applied for target kinematics modeling in various applications including environmental monitoring, traffic planning, endangered species tracking, dynamic scene analysis, autonomous robot navigation, and human motion modeling. As shown by these successful applications, Bayesian nonparametric models are able to adjust their complexities adaptively from data as necessary, and are resistant to overfitting or underfitting. However, most existing works assume that the sensor measurements used to learn the Bayesian nonparametric target kinematics models are obtained a priori or that the target kinematics can be measured by the sensor at any given time throughout the task. Little work has been done for controlling the sensor with bounded field of view to obtain measurements of mobile targets that are most informative for reducing the uncertainty of the Bayesian nonparametric models. To present the systematic sensor planning approach to leaning Bayesian nonparametric models, the Gaussian process target kinematics model is introduced at first, which is capable of describing time-invariant spatial phenomena, such as ocean currents, temperature distributions and wind velocity fields. The Dirichlet process-Gaussian process target kinematics model is subsequently discussed for modeling mixture of mobile targets, such as pedestrian motion patterns.

Novel information theoretic functions are developed for these introduced Bayesian nonparametric target kinematics models to represent the expected utility of measurements as a function of sensor control inputs and random environmental variables. A Gaussian process expected Kullback Leibler divergence is developed as the expectation of the KL divergence between the current (prior) and posterior Gaussian process target kinematics models with respect to the future measurements. Then, this approach is extended to develop a new information value function that can be used to estimate target kinematics described by a Dirichlet process-Gaussian process mixture model. A theorem is proposed that shows the novel information theoretic functions are bounded. Based on this theorem, efficient estimators of the new information theoretic functions are designed, which are proved to be unbiased with the variance of the resultant approximation error decreasing linearly as the number of samples increases. Computational complexities for optimizing the novel information theoretic functions under sensor dynamics constraints are studied, and are proved to be NP-hard. A cumulative lower bound is then proposed to reduce the computational complexity to polynomial time.

Three sensor planning algorithms are developed according to the assumptions on the target kinematics and the sensor dynamics. For problems where the control space of the sensor is discrete, a greedy algorithm is proposed. The efficiency of the greedy algorithm is demonstrated by a numerical experiment with data of ocean currents obtained by moored buoys. A sweep line algorithm is developed for applications where the sensor control space is continuous and unconstrained. Synthetic simulations as well as physical experiments with ground robots and a surveillance camera are conducted to evaluate the performance of the sweep line algorithm. Moreover, a lexicographic algorithm is designed based on the cumulative lower bound of the novel information theoretic functions, for the scenario where the sensor dynamics are constrained. Numerical experiments with real data collected from indoor pedestrians by a commercial pan-tilt camera are performed to examine the lexicographic algorithm. Results from both the numerical simulations and the physical experiments show that the three sensor planning algorithms proposed in this dissertation based on the novel information theoretic functions are superior at learning the target kinematics with

little or no prior knowledge

Modelo de Kuramoto com campos aleatórios em redes complexas

Neste trabalho é estudado o modelo de Kuramoto num grafo completo, em redes scale-free com uma distribuição de ligações P(q) ~ q-Y e na presença de campos aleatórios com magnitude constante e gaussiana. Para tal, foi considerado o método Ott-Antonsen e uma aproximação "annealed network". Num grafo completo, na presença de campos aleatórios gaussianos, e em redes scale-free com 2 < y < 5 na presença de ambos os campos aleatórios referidos, foram encontradas transições de fase contínuas. Considerando a presença de campos aleatórios com magnitude constante num grafo completo e em redes scale-free com y > 5, encontraram-se transições de fase contínua (h < √2) e descontínua (h > √2). Para uma rede SF com y = 3, foi observada uma transição de fase de ordem infinita. Os resultados do modelo de Kuramoto num grafo completo e na presença de campos aleatórios com magnitude constante foram comparados aos de simulações, tendo-se verificado uma boa concordância. Verifica-se que, independentemente da topologia de rede, a constante de acoplamento crítico aumenta com a magnitude do campo considerado. Na topologia de rede scale-free, concluiu-se que o valor do acoplamento crítico diminui à medida que valor de y diminui e que o grau de sincronização aumenta com o aumento do número médio das ligações na rede. A presença de campos aleatórios com magnitude gaussiana num grafo completo e numa rede scale-free com y > 2 não destrói a transição de fase contínua e não altera o comportamento crítico do modelo de Kuramoto.

Fluoride-modified electrical properties of lead borate glasses and electrochemically induced crystallization in the glassy state

Lead fluoroborate glasses were prepared by the melt-quenching technique and characterized in terms of (micro)structural and electrical properties. The study was conducted on as prepared as well as temperature- and/or electric field-treated glass samples. The results show that, in the as-prepared glassy-state materials, electrical conductivity improved with increasing the PbF(2) glass content. This result involves both an increase of the fluoride charge carrier density and, especially, a decrease of the activation energy from a glass structure expansion improving charge carrier mobility. Moreover, for the electric field-treated glass samples, surface crystallization was observed even below the glass transition temperature. As previously proposed in literature, and shown here, the occurrence of this phenomenon arose from an electrochemically induced redox reaction at the electrodes, followed by crystallite nucleation. Once nucleated, growth of beta-PbF(2) crystallites, with the indication of incorporating reduced lead ions (Pb(+)), was both (micro)structurally and electrically detectable and analyzed. The overall crystallization-associated features observed here adapt well with the floppy-rigid model that has been proposed to further complete the original continuous-random-network model by Zachariasen for closely addressing not only glasses' structure but also crystallization mechanism. Finally, the crystallization-modified kinetic picture of the glasses' electrical properties, through application of polarization/depolarization measurements originally combined with impedance spectroscopy, was extensively explored. (c) 2008 American Institute of Physics.

Evolutionary dynamics on rugged fitness landscapes: Exact dynamics and information theoretical aspects

The parallel mutation-selection evolutionary dynamics, in which mutation and replication are independent events, is solved exactly in the case that the Malthusian fitnesses associated to the genomes are described by the random energy model (REM) and by a ferromagnetic version of the REM. The solution method uses the mapping of the evolutionary dynamics into a quantum Ising chain in a transverse field and the Suzuki-Trotter formalism to calculate the transition probabilities between configurations at different times. We find that in the case of the REM landscape the dynamics can exhibit three distinct regimes: pure diffusion or stasis for short times, depending on the fitness of the initial configuration, and a spin-glass regime for large times. The dynamic transition between these dynamical regimes is marked by discontinuities in the mean-fitness as well as in the overlap with the initial reference sequence. The relaxation to equilibrium is described by an inverse time decay. In the ferromagnetic REM, we find in addition to these three regimes, a ferromagnetic regime where the overlap and the mean-fitness are frozen. In this case, the system relaxes to equilibrium in a finite time. The relevance of our results to information processing aspects of evolution is discussed.

A generalized multi-period mean-variance portfolio optimization with Markov switching parameters

In this paper, we deal with a generalized multi-period mean-variance portfolio selection problem with market parameters Subject to Markov random regime switchings. Problems of this kind have been recently considered in the literature for control over bankruptcy, for cases in which there are no jumps in market parameters (see [Zhu, S. S., Li, D., & Wang, S. Y. (2004). Risk control over bankruptcy in dynamic portfolio selection: A generalized mean variance formulation. IEEE Transactions on Automatic Control, 49, 447-457]). We present necessary and Sufficient conditions for obtaining an optimal control policy for this Markovian generalized multi-period meal-variance problem, based on a set of interconnected Riccati difference equations, and oil a set of other recursive equations. Some closed formulas are also derived for two special cases, extending some previous results in the literature. We apply the results to a numerical example with real data for Fisk control over bankruptcy Ill a dynamic portfolio selection problem with Markov jumps selection problem. (C) 2008 Elsevier Ltd. All rights reserved.

A zero-augmented gamma mixed model for longitudinal data with many zeros

In many occupational safety interventions, the objective is to reduce the injury incidence as well as the mean claims cost once injury has occurred. The claims cost data within a period typically contain a large proportion of zero observations (no claim). The distribution thus comprises a point mass at 0 mixed with a non-degenerate parametric component. Essentially, the likelihood function can be factorized into two orthogonal components. These two components relate respectively to the effect of covariates on the incidence of claims and the magnitude of claims, given that claims are made. Furthermore, the longitudinal nature of the intervention inherently imposes some correlation among the observations. This paper introduces a zero-augmented gamma random effects model for analysing longitudinal data with many zeros. Adopting the generalized linear mixed model (GLMM) approach reduces the original problem to the fitting of two independent GLMMs. The method is applied to evaluate the effectiveness of a workplace risk assessment teams program, trialled within the cleaning services of a Western Australian public hospital.

Credit default swap (CDS) prediction model & trading strategy

This project focuses on the study of different explanatory models for the behavior of CDS security, such as Fixed-Effect Model, GLS Random-Effect Model, Pooled OLS and Quantile Regression Model. After determining the best fitness model, trading strategies with long and short positions in CDS have been developed. Due to some specifications of CDS, I conclude that the quantile regression is the most efficient model to estimate the data. The P&L and Sharpe Ratio of the strategy are analyzed using a backtesting analogy, where I conclude that, mainly for non-financial companies, the model allows traders to take advantage of and profit from arbitrages.

Learning joint representations for order and timing of perceptual-motor sequences: a dynamic neural field approach

Many of our everyday tasks require the control of the serial order and the timing of component actions. Using the dynamic neural field (DNF) framework, we address the learning of representations that support the performance of precisely time action sequences. In continuation of previous modeling work and robotics implementations, we ask specifically the question how feedback about executed actions might be used by the learning system to fine tune a joint memory representation of the ordinal and the temporal structure which has been initially acquired by observation. The perceptual memory is represented by a self-stabilized, multi-bump activity pattern of neurons encoding instances of a sensory event (e.g., color, position or pitch) which guides sequence learning. The strength of the population representation of each event is a function of elapsed time since sequence onset. We propose and test in simulations a simple learning rule that detects a mismatch between the expected and realized timing of events and adapts the activation strengths in order to compensate for the movement time needed to achieve the desired effect. The simulation results show that the effector-specific memory representation can be robustly recalled. We discuss the impact of the fast, activation-based learning that the DNF framework provides for robotics applications.

Off-line simulation inspires insight: a neurodynamics approach to efficient robot task learning

There is currently an increasing demand for robots able to acquire the sequential organization of tasks from social learning interactions with ordinary people. Interactive learning-by-demonstration and communication is a promising research topic in current robotics research. However, the efficient acquisition of generalized task representations that allow the robot to adapt to different users and contexts is a major challenge. In this paper, we present a dynamic neural field (DNF) model that is inspired by the hypothesis that the nervous system uses the off-line re-activation of initial memory traces to incrementally incorporate new information into structured knowledge. To achieve this, the model combines fast activation-based learning to robustly represent sequential information from single task demonstrations with slower, weight-based learning during internal simulations to establish longer-term associations between neural populations representing individual subtasks. The efficiency of the learning process is tested in an assembly paradigm in which the humanoid robot ARoS learns to construct a toy vehicle from its parts. User demonstrations with different serial orders together with the correction of initial prediction errors allow the robot to acquire generalized task knowledge about possible serial orders and the longer term dependencies between subgoals in very few social learning interactions. This success is shown in a joint action scenario in which ARoS uses the newly acquired assembly plan to construct the toy together with a human partner.

Sistema de reconeixement de cares basat en múltiples vistes

En aquest projecte es proposa un algorisme de detecció de pell que introdueix el veïnatge a l’hora de classificar píxels. Partim d’un espai de color invariant après a partir de múltiples vistes i introduïm la influència del veïnatge mitjançant camps aleatoris de Markov. A partir dels experiments realitzats podem concloure que la inclusió del veïnatge en el procés de classificació de píxels millora significativament els resultats de detecció.

Transition probabilities and duration analysis among disability states: Some evidence from Spanish data

In this paper we study the disability transition probabilities (as well as the mortalityprobabilities) due to concurrent factors to age such as income, gender and education. Althoughit is well known that ageing and socioeconomic status influence the probability ofcausing functional disorders, surprisingly little attention has been paid to the combined effectof those factors along the individuals' life and how this affects the transition from one degreeof disability to another. The assumption that tomorrow's disability state is only a functionof the today's state is very strong, since disability is a complex variable that depends onseveral other elements than time. This paper contributes into the field in two ways: (1) byattending the distinction between the initial disability level and the process that leads tohis course (2) by addressing whether and how education, age and income differentially affectthe disability transitions. Using a Markov chain discrete model and a survival analysis, weestimate the probability by year and individual characteristics that changes the state of disabilityand the duration that it takes its progression in each case. We find that people withan initial state of disability have a higher propensity to change and take less time to transitfrom different stages. Men do that more frequently than women. Education and incomehave negative effects on transition. Moreover, we consider the disability benefits associatedto those changes along different stages of disability and therefore we offer some clues onthe potential savings of preventive actions that may delay or avoid those transitions. Onpure cost considerations, preventive programs for improvement show higher benefits thanthose for preventing deterioration, and in general terms, those focussing individuals below65 should go first. Finally the trend of disability in Spain seems not to change among yearsand regional differences are not found.