Using artificial neural networks to generate trading signals for crude oil, copper and gold futures

In this thesis, a feed-forward, back-propagating Artificial Neural Network using the gradient descent algorithm is developed to forecast the directional movement of daily returns for WTI, gold and copper futures. Out-of-sample back-test results vary, with some predictive abilities for copper futures but none for either WTI or gold. The best statistically significant hit rate achieved was 57% for copper with an absolute return Sharpe Ratio of 1.25 and a benchmarked Information Ratio of 2.11.

Socio-demographic correlates of physical activity of European adults: A cross-sectional study from the European Social Survey

ABSTRACT - Background: From a public health perspective, the study of socio-demographic factors related to physical activity is important in order to identify subgroups for intervention programs. Purpose: This study also aimed to identify the prevalence and the socio-demographic correlates related with the achievement of recommended physical activity levels. Methods: Using data from the European Social Survey round 6, physical activity and socio-demographic characteristics were collected from 39278 European adults (18271 men, 21006 women), aged 18-64 years, from 28 countries in 2012. Meeting physical activity guidelines was assessed using World Health Organization criteria. Results: 64.50% (63.36% men, 66.49% women) attained physical activity recommended levels. The likelihood of attaining physical activity recommendations was higher in age group of 55-64 years (men: OR=1.22, p<0.05; women: OR=1.66, p<0.001), among those who had completed high school (men: OR=1.28, p<0.01; women: OR=1.26, p<0.05), among those who lived in rural areas (men: OR=1.20, p<0.001; women: OR=1.10, p<0.05), and among those who had 3 or more people living at home (men: OR=1.40, p<0.001; women: OR=1.43, p<0.001). On the other hand, attaining physical activity recommendations was negatively associated with being unemployed (men: OR=0.70, p<0.001; women: OR=0.87, p<0.05), being a student (men: OR=0.56, p<0.001; women: OR=0.64, p<0.01), being a retired person (men: OR=0.86, p<0.05) and with having a higher household income (OR=0.80, p<0.001; women: OR=0.81, p<0.01). Conclusion: This research helped clarify that, as the promotion of physical activity is critical to sustain health and prevent disease, socio-demographic factors are important to consider when planning the increase of physical activity.

Abstract computation in schizophrenia detection through artificial neural network based systems

Schizophrenia stands for a long-lasting state of mental uncertainty that may bring to an end the relation among behavior, thought, and emotion; that is, it may lead to unreliable perception, not suitable actions and feelings, and a sense of mental fragmentation. Indeed, its diagnosis is done over a large period of time; continuos signs of the disturbance persist for at least 6 (six) months. Once detected, the psychiatrist diagnosis is made through the clinical interview and a series of psychic tests, addressed mainly to avoid the diagnosis of other mental states or diseases. Undeniably, the main problem with identifying schizophrenia is the difficulty to distinguish its symptoms from those associated to different untidiness or roles. Therefore, this work will focus on the development of a diagnostic support system, in terms of its knowledge representation and reasoning procedures, based on a blended of Logic Programming and Artificial Neural Networks approaches to computing, taking advantage of a novel approach to knowledge representation and reasoning, which aims to solve the problems associated in the handling (i.e., to stand for and reason) of defective information.

Thrombophilia screening: An artificial neural network approach

Thrombotic disorders have severe consequences for the patients and for the society in general, being one of the main causes of death. These facts reveal that it is extremely important to be preventive; being aware of how probable is to have that kind of syndrome. Indeed, this work will focus on the development of a decision support system that will cater for an individual risk evaluation with respect to the surge of thrombotic complaints. The Knowledge Representation and Reasoning procedures used will be based on an extension to the Logic Programming language, allowing the handling of incomplete and/or default data. The computational framework in place will be centered on Artificial Neural Networks.

Artificial neural networks in diagnosis of liver diseases

Liver diseases have severe patients’ consequences, being one of the main causes of premature death. These facts reveal the centrality of one`s daily habits, and how important it is the early diagnosis of these kind of illnesses, not only to the patients themselves, but also to the society in general. Therefore, this work will focus on the development of a diagnosis support system to these kind of maladies, built under a formal framework based on Logic Programming, in terms of its knowledge representation and reasoning procedures, complemented with an approach to computing grounded on Artificial Neural Networks.

Logic programming and artificial neural networks in breast cancer detection

About 90% of breast cancers do not cause or are capable of producing death if detected at an early stage and treated properly. Indeed, it is still not known a specific cause for the illness. It may be not only a beginning, but also a set of associations that will determine the onset of the disease. Undeniably, there are some factors that seem to be associated with the boosted risk of the malady. Pondering the present study, different breast cancer risk assessment models where considered. It is our intention to develop a hybrid decision support system under a formal framework based on Logic Programming for knowledge representation and reasoning, complemented with an approach to computing centered on Artificial Neural Networks, to evaluate the risk of developing breast cancer and the respective Degree-of-Confidence that one has on such a happening.

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.

[Letter to the editor] Sustained effects of a neural-based intervention in a refractory case of Tourette syndrome

There are only a few treatments available for Tourette syndrome (TS). These treatments frequently do notwork in patients with moderate to severe TS [1]. Neuroimaging studies show a correlation between tics severity and increased activation over motor pathways, along with reduced activation over the control areas of the cortico-striato-thalamo-cortical circuits [2]. Moreover, the temporal pattern of tic generation suggests that cortical activation especially in the SMA precedes subcortical activation [3]. Following this assumption, here we explored the brain effects of 10-daily sessions of cathodal transcranial Direct Current Stimulation (tDCS) delivered over the pre-SMA in a patient with refractory and severe TS and also assessed whether those changes were long lasting (up to 6 months).

High-aspect-ratio tridimensional electrode arrays for neural applications

Tese de Doutoramento em Engenharia Biomédica.

Age effects on EEG correlates of the Wisconsin card sorting test

Body and brain undergo several changes with aging. One of the domains in which these changes are more remarkable relates with cognitive performance. In the present work, electroencephalogram (EEG) markers (power spectral density and spectral coherence) of age-related cognitive decline were sought whilst the subjects performed the Wisconsin Card Sorting Test (WCST). Considering the expected age-related cognitive deficits, WCST was applied to young, mid-age and elderly participants, and the theta and alpha frequency bands were analyzed. From the results herein presented, higher theta and alpha power were found to be associated with a good performance in the WCST of younger subjects. Additionally, higher theta and alpha coherence were also associated with good performance and were shown to decline with age and a decrease in alpha peak frequency seems to be associated with aging. Additionally, inter-hemispheric long-range coherences and parietal theta power were identified as age-independent EEG correlates of cognitive performance. In summary, these data reveals age-dependent as well as age-independent EEG correlates of cognitive performance that contribute to the understanding of brain aging and related cognitive deficits.

Participación de las células de la cresta neural en el desarrollo de anomalías inducidas por agentes exógenos (síndrome fetal alcohólico y embriopatía por ácido retinoico)

En la etapa embrionaria temprana de los vertebrados, las células de la cresta neural (CCN) se segregan del tubo neural y se distribuyen con patrones temporales y espaciales muy precisos, contribuyendo a la formación de muchos derivados: neuronas y glía del sistema nervioso periférico, parte del sistema endócrino, sistema pigmentario y la mayor parte de los tejidos cráneo-faciales. Las bases morfogenéticas de esta movilización de las CCN se asocian con la disponibilidad de componentes de la matriz extracelular, con fenómenos de apoptosis selectiva, y con la expresión de genes homeóticos, de proteínas transportadoras de retinoides y de receptores de ácido retinoico (AR). En consecuencia, el mecanismo que define el comportamiento de las CCN migratorias asume una especial importancia, desde que cualquier fallo producido en estos "reguladores topográficos" podrá alterar la ordenada traslocación de CN, induciendo una dismorfogénesis. (...) Objetivos: 1) Analizar el comportamiento dinámico de la etapa migratoria temprana de las CCN de niveles cefálico y troncal expuestas a etanol o AR in vitro. 2) Evaluar la posible reversibilidad de los efectos del etanol y del AR sobre la morfología y dinámica migratoria de las CCN de niveles cefálico y troncal in vitro. 3) Analizar los componentes del citoesqueleto asociados con los cambios de forma y motilidad celular en CCN de niveles cefálico y troncal expuestas a etanol y AR in vitro. Los resultados del proyecto permitirán aportar al conocimiento de los mecanismos básicos que regulan la movilidad de poblaciones celulares de gran importancia para el desarrollo humano. Los datos obtenidos servirán de base para futuros enfoques de biología molecular tendientes a innovar aspectos del diagnóstico, pronóstico y prevención de patologías humanas de creciente prevalencia provocadas por el etanol (FAS) y los retinoides (RAE).

Gangliósidos, Neuritogénesis y Regeneración Neural "in vitro"

El presente plan tiene como objetivo general la caracterización de factores celulares y moleculares que afecten la sobrevida, la diferenciación neural y la regeneración axonal en células del sistema nervioso central (SNC). Las neuronas maduras de vertebrados superiores son incapaces de regenerar sus axones dañados, razón por la cual todo estudio experimental de regeneración axonal "in vitro", si bien aporta conocimientos básicos, tiene potenciales aplicaciones prácticas en relación a la recuperación de la función neuronal. Diversos estudios de regeneración axonal, especialmente para las células gangionares (CGR) han sido realizados con cultivos de células retinales. Estos cultivos están compuestos por diversos tipos de neuronas, lo que hace que cuando se quiere determinar los efectos de un agente trófico, no sea éste el mejor sistema dado que los efectos observados pueden estar afectados por otros tipos celulares del cultivo. Por ello, para optimizar un modelo para estos estudios, hemos desarrollado un método de cultivo para las CGR purificadas por "panning" de retinas de embrión de pollo de diverso desarrollo ontogénico. Las CGR son sembradas a baja densidad en un medio sintético que especialmente hemos formulado (BP5). (...) En base a la experiencia adquirida, y utilizando las técnicas puestas en marcha en nuestro laboratorio, nos proponemos caracterizar, mediante el análisis de parámetros bioquímicos y de video-microscopía con analizador de la diferenciación y el crecimiento axonal de las CGR purificadas. Las CGR serán cultivadas en condiciones basales con el medio PB5, o en presencia de diversos factores de crecimiento, sustancias de la matriz extracelular y gangliósidos exógenos, agregados individualmente o en combinación. En estas condiciones se correlacionarán los efectos observados con los cambios en los "patterns" de síntesis y expresión de los gangliósidos y con el flujo intracelular de Ca2+.

Motilidad Orientada de Células Neurales: La comunicación celular a distancia. Oriented neural cell motility: Cell comunication at a distance.

La motilidad celular orientada (o mecanismo quimiotáctico de orientación), es una respuesta celular a señales moleculares de su micro-ambiente necesaria para modular la distribución celular en sitios específicos y con elevada precisión. Nuestra hipótesis establece que la migración orientada de células neurales es regulada por gradientes de concentración de moléculas solubles liberadas por sus regiones "blanco". Este proyecto es continuación del estudio de la quimiotaxis de células de cresta neural (CCN) y de neuronas ventriculares (NV) inducida respectivamente por factores difusibles de la región del futuro ganglio ciliar y del bulbo olfatorio.En el sistema de CCN, hemos caracterizado como moléculas quimiotácticas a la quimioquina Stromal Cell-Derived Factor-1, y los factores tróficos Stem Cell Factor y Neurotrophic Factor-3, habiendo determinado la expresión de sus respectivos receptores CXCR4, TrkC y p75 en la población de CCN mesencefálicas de ambrión de pollo. Actualmente, estamos desarrollando experimentos con el Ciliary Neurotrophic Factor y factores de la familia Bone Morphogenetic Proteins. Además de la estrategia experimental in vitro, hemos determinado en el embrión entero la expresión de las moléculas quimioatractantes mediante hibridación in situ del ARNm y la presencia de las respectivas proteínas mediante inmunocitoquímica. En el sistema de NV, estamos analizando la motilidad celular en relación con moléculas liberadas por el bulbo olfatorio. En los dos sistemas biológicos, estamos analizando elementos de la transducción de señales y cambios en el citoesqueleto, en ambos casos asociados con la respuesta temprana en la orientación quimiotáctica de la célula. Asimismo, en ambos sistemas biológicos, evaluamos los efectos del etanol sobre la migración y distribución celular, en condiciones equivalentes a las que inducen el Sindrome Fetal Alcohólico en mamíferos.En base a resultados ya obtenidos en experimentos in vitro, en la presente etapa intentaremos su caracterización in vivo mediante el bloqueo funcional de las moléculas quimiotácticas (y/o sus receptores) sobre embriones enteros, mediante silenciamiento con ARNsi (o morfolinos específicos) mediante electroporación, y posterior determinación de la distribución celular mediante marcadores específicos anti-CCN (o lipofílicos de tipo DiI).Los resultados permitirán mejorar el conocimiento del mecanismo de la migración celular orientada y aportar al diseño de recursos diagnósticos, terapéuticos o de control de anomalías embrionarias o patologías tumorales por mala distribución celular como las Neurocristopatías, o inducidas por tóxicos exógenos como el Sindrome Fetal Alcohólico.

Neural mechanisms of attentional selection in vision : locations, features, and objects

Magdeburg, Univ., Fak. für Naturwiss., Diss., 2012