Analysis of large-scale digital optical neural networks by Feynman diagrams

A new method to study large scale neural networks is presented in this paper. The basis is the use of Feynman- like diagrams. These diagrams allow the analysis of collective and cooperative phenomena with a similar methodology to the employed in the Many Body Problem. The proposed method is applied to a very simple structure composed by an string of neurons with interaction among them. It is shown that a new behavior appears at the end of the row. This behavior is different to the initial dynamics of a single cell. When a feedback is present, as in the case of the hippocampus, this situation becomes more complex with a whole set of new frequencies, different from the proper frequencies of the individual neurons. Application to an optical neural network is reported.

Artificial metaplasticity prediction model for cognitive rehabilitation outcome in acquired brain injury patients

Objective The main purpose of this research is the novel use of artificial metaplasticity on multilayer perceptron (AMMLP) as a data mining tool for prediction the outcome of patients with acquired brain injury (ABI) after cognitive rehabilitation. The final goal aims at increasing knowledge in the field of rehabilitation theory based on cognitive affectation. Methods and materials The data set used in this study contains records belonging to 123 ABI patients with moderate to severe cognitive affectation (according to Glasgow Coma Scale) that underwent rehabilitation at Institut Guttmann Neurorehabilitation Hospital (IG) using the tele-rehabilitation platform PREVIRNEC©. The variables included in the analysis comprise the neuropsychological initial evaluation of the patient (cognitive affectation profile), the results of the rehabilitation tasks performed by the patient in PREVIRNEC© and the outcome of the patient after a 3–5 months treatment. To achieve the treatment outcome prediction, we apply and compare three different data mining techniques: the AMMLP model, a backpropagation neural network (BPNN) and a C4.5 decision tree. Results The prediction performance of the models was measured by ten-fold cross validation and several architectures were tested. The results obtained by the AMMLP model are clearly superior, with an average predictive performance of 91.56%. BPNN and C4.5 models have a prediction average accuracy of 80.18% and 89.91% respectively. The best single AMMLP model provided a specificity of 92.38%, a sensitivity of 91.76% and a prediction accuracy of 92.07%. Conclusions The proposed prediction model presented in this study allows to increase the knowledge about the contributing factors of an ABI patient recovery and to estimate treatment efficacy in individual patients. The ability to predict treatment outcomes may provide new insights toward improving effectiveness and creating personalized therapeutic interventions based on clinical evidence.

Data Mining with Enhanced Neural Networks-CMMSE

Abstract This paper presents a new method to extract knowledge from existing data sets, that is, to extract symbolic rules using the weights of an Artificial Neural Network. The method has been applied to a neural network with special architecture named Enhanced Neural Network (ENN). This architecture improves the results that have been obtained with multilayer perceptron (MLP). The relationship among the knowledge stored in the weights, the performance of the network and the new implemented algorithm to acquire rules from the weights is explained. The method itself gives a model to follow in the knowledge acquisition with ENN.

Analysis of the discharge capacity of radial-gated spillways using CFD and ANN - Oliana Dam case study.

The paper focuses on the analysis of radial-gated spillways, which is carried out by the solution of a numerical model based on the finite element method (FEM). The Oliana Dam is considered as a case study and the discharge capacity is predicted both by the application of a level-set-based free-surface solver and by the use of traditional empirical formulations. The results of the analysis are then used for training an artificial neural network to allow real-time predictions of the discharge in any situation of energy head and gate opening within the operation range of the reservoir. The comparison of the results obtained with the different methods shows that numerical models such as the FEM can be useful as a predictive tool for the analysis of the hydraulic performance of radial-gated spillways.

Bus line classification using neural networks

Grouping urban bus routes is necessary when there are evidences of significant differences among them. In Jiménez et al. (2013), a reduced sample of routes was grouped into clusters utilizing kinematic measured data. As a further step, in this paper, the remaining urban bus routes of a city, for which no kinematic measurements are available, are classified. For such purpose we use macroscopic geographical and functional variables to describe each route, while the clustering process is performed by means of a neural network. Limitations caused by reduced training samples are solved using the bootstrap method.

Glucose-Insulin regulator for type 1 diabetes using high order neural networks

In this paper a Glucose-Insulin regulator for Type 1 Diabetes using artificial neural networks (ANN) is proposed. This is done using a discrete recurrent high order neural network in order to identify and control a nonlinear dynamical system which represents the pancreas? beta-cells behavior of a virtual patient. The ANN which reproduces and identifies the dynamical behavior system, is configured as series parallel and trained on line using the extended Kalman filter algorithm to achieve a quickly convergence identification in silico. The control objective is to regulate the glucose-insulin level under different glucose inputs and is based on a nonlinear neural block control law. A safety block is included between the control output signal and the virtual patient with type 1 diabetes mellitus. Simulations include a period of three days. Simulation results are compared during the overnight fasting period in Open-Loop (OL) versus Closed- Loop (CL). Tests in Semi-Closed-Loop (SCL) are made feedforward in order to give information to the control algorithm. We conclude the controller is able to drive the glucose to target in overnight periods and the feedforward is necessary to control the postprandial period.

Polynomial regression using a perceptron with axo-axonic connections

Social behavior is mainly based on swarm colonies, in which each individual shares its knowledge about the environment with other individuals to get optimal solutions. Such co-operative model differs from competitive models in the way that individuals die and are born by combining information of alive ones. This paper presents the particle swarm optimization with differential evolution algorithm in order to train a neural network instead the classic back propagation algorithm. The performance of a neural network for particular problems is critically dependant on the choice of the processing elements, the net architecture and the learning algorithm. This work is focused in the development of methods for the evolutionary design of artificial neural networks. This paper focuses in optimizing the topology and structure of connectivity for these networks

Overtopping of harbour breakwaters: a comparison of semi-empirical equations, neural networks, and physical model tests

This paper reports extensive tests of empirical equations developed by different authors for harbour breakwater overtopping. First, the existing equations are compiled and evaluated as tools for estimating the overtopping rates on sloping and vertical breakwaters. These equations are then tested using the data obtained in a number of laboratory studies performed in the Centre for Harbours and Coastal Studies of the CEDEX, Spain. It was found that the recommended application ranges of the empirical equations typically deviate from those revealed in the experimental tests. In addition, a neural network model developed within the European CLASH Project is tested. The wind effects on overtopping are also assessed using a reduced scale physical model

Análisis comparativo y nuevas estimaciones de las tasas de rebase en obras marítimas en grandes profundidades

El rebase se define como el transporte de una cantidad importante de agua sobre la coronación de una estructura. Por tanto, es el fenómeno que, en general, determina la cota de coronación del dique dependiendo de la cantidad aceptable del mismo, a la vista de condicionantes funcionales y estructurales del dique. En general, la cantidad de rebase que puede tolerar un dique de abrigo desde el punto de vista de su integridad estructural es muy superior a la cantidad permisible desde el punto de vista de su funcionalidad. Por otro lado, el diseño de un dique con una probabilidad de rebase demasiado baja o nula conduciría a diseños incompatibles con consideraciones de otro tipo, como son las estéticas o las económicas. Existen distintas formas de estudiar el rebase producido por el oleaje sobre los espaldones de las obras marítimas. Las más habituales son los ensayos en modelo físico y las formulaciones empíricas o semi-empíricas. Las menos habituales son la instrumentación en prototipo, las redes neuronales y los modelos numéricos. Los ensayos en modelo físico son la herramienta más precisa y fiable para el estudio específico de cada caso, debido a la complejidad del proceso de rebase, con multitud de fenómenos físicos y parámetros involucrados. Los modelos físicos permiten conocer el comportamiento hidráulico y estructural del dique, identificando posibles fallos en el proyecto antes de su ejecución, evaluando diversas alternativas y todo esto con el consiguiente ahorro en costes de construcción mediante la aportación de mejoras al diseño inicial de la estructura. Sin embargo, presentan algunos inconvenientes derivados de los márgenes de error asociados a los ”efectos de escala y de modelo”. Las formulaciones empíricas o semi-empíricas presentan el inconveniente de que su uso está limitado por la aplicabilidad de las fórmulas, ya que éstas sólo son válidas para una casuística de condiciones ambientales y tipologías estructurales limitadas al rango de lo reproducido en los ensayos. El objetivo de la presente Tesis Doctoral es el contrate de las formulaciones desarrolladas por diferentes autores en materia de rebase en distintas tipologías de diques de abrigo. Para ello, se ha realizado en primer lugar la recopilación y el análisis de las formulaciones existentes para estimar la tasa de rebase sobre diques en talud y verticales. Posteriormente, se llevó a cabo el contraste de dichas formulaciones con los resultados obtenidos en una serie de ensayos realizados en el Centro de Estudios de Puertos y Costas. Para finalizar, se aplicó a los ensayos de diques en talud seleccionados la herramienta neuronal NN-OVERTOPPING2, desarrollada en el proyecto europeo de rebases CLASH (“Crest Level Assessment of Coastal Structures by Full Scale Monitoring, Neural Network Prediction and Hazard Analysis on Permissible Wave Overtopping”), contrastando de este modo la tasa de rebase obtenida en los ensayos con este otro método basado en la teoría de las redes neuronales. Posteriormente, se analizó la influencia del viento en el rebase. Para ello se han realizado una serie de ensayos en modelo físico a escala reducida, generando oleaje con y sin viento, sobre la sección vertical del Dique de Levante de Málaga. Finalmente, se presenta el análisis crítico del contraste de cada una de las formulaciones aplicadas a los ensayos seleccionados, que conduce a las conclusiones obtenidas en la presente Tesis Doctoral. Overtopping is defined as the volume of water surpassing the crest of a breakwater and reaching the sheltered area. This phenomenon determines the breakwater’s crest level, depending on the volume of water admissible at the rear because of the sheltered area’s functional and structural conditioning factors. The ways to assess overtopping processes range from those deemed to be most traditional, such as semi-empirical or empirical type equations and physical, reduced scale model tests, to others less usual such as the instrumentation of actual breakwaters (prototypes), artificial neural networks and numerical models. Determining overtopping in reduced scale physical model tests is simple but the values obtained are affected to a greater or lesser degree by the effects of a scale model-prototype such that it can only be considered as an approximation to what actually happens. Nevertheless, physical models are considered to be highly useful for estimating damage that may occur in the area sheltered by the breakwater. Therefore, although physical models present certain problems fundamentally deriving from scale effects, they are still the most accurate, reliable tool for the specific study of each case, especially when large sized models are adopted and wind is generated Empirical expressions obtained from laboratory tests have been developed for calculating the overtopping rate and, therefore, the formulas obtained obviously depend not only on environmental conditions – wave height, wave period and water level – but also on the model’s characteristics and are only applicable in a range of validity of the tests performed in each case. The purpose of this Thesis is to make a comparative analysis of methods for calculating overtopping rates developed by different authors for harbour breakwater overtopping. First, existing equations were compiled and analysed in order to estimate the overtopping rate on sloping and vertical breakwaters. These equations were then compared with the results obtained in a number of tests performed in the Centre for Port and Coastal Studies of the CEDEX. In addition, a neural network model developed in the European CLASH Project (“Crest Level Assessment of Coastal Structures by Full Scale Monitoring, Neural Network Prediction and Hazard Analysis on Permissible Wave Overtopping“) was also tested. Finally, the wind effects on overtopping are evaluated using tests performed with and without wind in the physical model of the Levante Breakwater (Málaga).

Monitorización de estructuras aeronáuticas mediante técnicas de inteligencia artificial

Una de las barreras para la aplicación de las técnicas de monitorización de la integridad estructural (SHM) basadas en ondas elásticas guiadas (GLW) en aeronaves es la influencia perniciosa de las condiciones ambientales y de operación (EOC). En esta tesis se ha estudiado dicha influencia y la compensación de la misma, particularizando en variaciones del estado de carga y temperatura. La compensación de dichos efectos se fundamenta en Redes Neuronales Artificiales (ANN) empleando datos experimentales procesados con la Transformada Chirplet. Los cambios en la geometría y en las propiedades del material respecto al estado inicial de la estructura (lo daños) provocan cambios en la forma de onda de las GLW (lo que denominamos característica sensible al daño o DSF). Mediante técnicas de tratamiento de señal se puede buscar una relación entre dichas variaciones y los daños, esto se conoce como SHM. Sin embargo, las variaciones en las EOC producen también cambios en los datos adquiridos relativos a las GLW (DSF) que provocan errores en los algoritmos de diagnóstico de daño (SHM). Esto sucede porque las firmas de daño y de las EOC en la DSF son del mismo orden. Por lo tanto, es necesario cuantificar y compensar el efecto de las EOC sobre la GLW. Si bien existen diversas metodologías para compensar los efectos de las EOC como por ejemplo “Optimal Baseline Selection” (OBS) o “Baseline Signal Stretching” (BSS), estas, se emplean exclusivamente en la compensación de los efectos térmicos. El método propuesto en esta tesis mezcla análisis de datos experimentales, como en el método OBS, y modelos basados en Redes Neuronales Artificiales (ANN) que reemplazan el modelado físico requerido por el método BSS. El análisis de datos experimentales consiste en aplicar la Transformada Chirplet (CT) para extraer la firma de las EOC sobre la DSF. Con esta información, obtenida bajo diversas EOC, se entrena una ANN. A continuación, la ANN actuará como un interpolador de referencias de la estructura sin daño, generando información de referencia para cualquier EOC. La comparación de las mediciones reales de la DSF con los valores simulados por la ANN, dará como resultado la firma daño en la DSF, lo que permite el diagnóstico de daño. Este esquema se ha aplicado y verificado, en diversas EOC, para una estructura unidimensional con un único camino de daño, y para una estructura representativa de un fuselaje de una aeronave, con curvatura y múltiples elementos rigidizadores, sometida a un estado de cargas complejo, con múltiples caminos de daños. Los efectos de las EOC se han estudiado en detalle en la estructura unidimensional y se han generalizado para el fuselaje, demostrando la independencia del método respecto a la configuración de la estructura y el tipo de sensores utilizados para la adquisición de datos GLW. Por otra parte, esta metodología se puede utilizar para la compensación simultánea de una variedad medible de EOC, que afecten a la adquisición de datos de la onda elástica guiada. El principal resultado entre otros, de esta tesis, es la metodología CT-ANN para la compensación de EOC en técnicas SHM basadas en ondas elásticas guiadas para el diagnóstico de daño. ABSTRACT One of the open problems to implement Structural Health Monitoring techniques based on elastic guided waves in real aircraft structures at operation is the influence of the environmental and operational conditions (EOC) on the damage diagnosis problem. This thesis deals with the compensation of these environmental and operational effects, specifically, the temperature and the external loading, by the use of the Chirplet Transform working with Artificial Neural Networks. It is well known that the guided elastic wave form is affected by the damage appearance (what is known as the damage sensitive feature or DSF). The DSF is modified by the temperature and by the load applied to the structure. The EOC promotes variations in the acquired data (DSF) and cause mistakes in damage diagnosis algorithms. This effect promotes changes on the waveform due to the EOC variations of the same order than the damage occurrence. It is difficult to separate both effects in order to avoid damage diagnosis mistakes. Therefore it is necessary to quantify and compensate the effect of EOC over the GLW forms. There are several approaches to compensate the EOC effects such as Optimal Baseline Selection (OBS) or Baseline Signal Stretching (BSS). Usually, they are used for temperature compensation. The new method proposed here mixes experimental data analysis, as in the OBS method, and Artificial Neural Network (ANN) models to replace the physical modelling which involves the BSS method. The experimental data analysis studied is based on apply the Chirplet Transform (CT) to extract the EOC signature on the DSF. The information obtained varying EOC is employed to train an ANN. Then, the ANN will act as a baselines interpolator of the undamaged structure. The ANN generates reference information at any EOC. By comparing real measurements of the DSF against the ANN simulated values, the damage signature appears clearly in the DSF, enabling an accurate damage diagnosis. This schema has been applied in a range of EOC for a one-dimensional structure containing single damage path and two dimensional real fuselage structure with stiffener elements and multiple damage paths. The EOC effects tested in the one-dimensional structure have been generalized to the fuselage showing its independence from structural arrangement and the type of sensors used for GLW data acquisition. Moreover, it can be used for the simultaneous compensation of a variety of measurable EOC, which affects the guided wave data acquisition. The main result, among others, of this thesis is the CT-ANN methodology for the compensation of EOC in GLW based SHM technique for damage diagnosis.

Peptide design by artificial neural networks and computer-based evolutionary search

A technique for systematic peptide variation by a combination of rational and evolutionary approaches is presented. The design scheme consists of five consecutive steps: (i) identification of a “seed peptide” with a desired activity, (ii) generation of variants selected from a physicochemical space around the seed peptide, (iii) synthesis and testing of this biased library, (iv) modeling of a quantitative sequence-activity relationship by an artificial neural network, and (v) de novo design by a computer-based evolutionary search in sequence space using the trained neural network as the fitness function. This strategy was successfully applied to the identification of novel peptides that fully prevent the positive chronotropic effect of anti-β1-adrenoreceptor autoantibodies from the serum of patients with dilated cardiomyopathy. The seed peptide, comprising 10 residues, was derived by epitope mapping from an extracellular loop of human β1-adrenoreceptor. A set of 90 peptides was synthesized and tested to provide training data for neural network development. De novo design revealed peptides with desired activities that do not match the seed peptide sequence. These results demonstrate that computer-based evolutionary searches can generate novel peptides with substantial biological activity.

Deciphering a neural code for vision

Deciphering the information that eyes, ears, and other sensory organs transmit to the brain is important for understanding the neural basis of behavior. Recordings from single sensory nerve cells have yielded useful insights, but single neurons generally do not mediate behavior; networks of neurons do. Monitoring the activity of all cells in a neural network of a behaving animal, however, is not yet possible. Taking an alternative approach, we used a realistic cell-based model to compute the ensemble of neural activity generated by one sensory organ, the lateral eye of the horseshoe crab, Limulus polyphemus. We studied how the neural network of this eye encodes natural scenes by presenting to the model movies recorded with a video camera mounted above the eye of an animal that was exploring its underwater habitat. Model predictions were confirmed by simultaneously recording responses from single optic nerve fibers of the same animal. We report here that the eye transmits to the brain robust “neural images” of objects having the size, contrast, and motion of potential mates. The neural code for such objects is not found in ambiguous messages of individual optic nerve fibers but rather in patterns of coherent activity that extend over small ensembles of nerve fibers and are bound together by stimulus motion. Integrative properties of neurons in the first synaptic layer of the brain appear well suited to detecting the patterns of coherent activity. Neural coding by this relatively simple eye helps explain how horseshoe crabs find mates and may lead to a better understanding of how more complex sensory organs process information.

The neural development and organization of letter recognition: Evidence from functional neuroimaging, computational modeling, and behavioral studies

Although much of the brain’s functional organization is genetically predetermined, it appears that some noninnate functions can come to depend on dedicated and segregated neural tissue. In this paper, we describe a series of experiments that have investigated the neural development and organization of one such noninnate function: letter recognition. Functional neuroimaging demonstrates that letter and digit recognition depend on different neural substrates in some literate adults. How could the processing of two stimulus categories that are distinguished solely by cultural conventions become segregated in the brain? One possibility is that correlation-based learning in the brain leads to a spatial organization in cortex that reflects the temporal and spatial clustering of letters with letters in the environment. Simulations confirm that environmental co-occurrence does indeed lead to spatial localization in a neural network that uses correlation-based learning. Furthermore, behavioral studies confirm one critical prediction of this co-occurrence hypothesis, namely, that subjects exposed to a visual environment in which letters and digits occur together rather than separately (postal workers who process letters and digits together in Canadian postal codes) do indeed show less behavioral evidence for segregated letter and digit processing.

Self-organized phase transitions in neural networks as a neural mechanism of information processing.

Transitions between dynamically stable activity patterns imposed on an associative neural network are shown to be induced by self-organized infinitesimal changes in synaptic connection strength and to be a kind of phase transition. A key event for the neural process of information processing in a population coding scheme is transition between the activity patterns encoding usual entities. We propose that the infinitesimal and short-term synaptic changes based on the Hebbian learning rule are the driving force for the transition. The phase transition between the following two dynamical stable states is studied in detail, the state where the firing pattern is changed temporally so as to itinerate among several patterns and the state where the firing pattern is fixed to one of several patterns. The phase transition from the pattern itinerant state to a pattern fixed state may be induced by the Hebbian learning process under a weak input relevant to the fixed pattern. The reverse transition may be induced by the Hebbian unlearning process without input. The former transition is considered as recognition of the input stimulus, while the latter is considered as clearing of the used input data to get ready for new input. To ensure that information processing based on the phase transition can be made by the infinitesimal and short-term synaptic changes, it is absolutely necessary that the network always stays near the critical state corresponding to the phase transition point.

QSAR e dinâmica molecular no estudo de sistemas biomoleculares: predição da atividade biológica de antagonistas do receptor sigma-1 e simulações de bicamadas lipídicas

Diferentes abordagens teóricas têm sido utilizadas em estudos de sistemas biomoleculares com o objetivo de contribuir com o tratamento de diversas doenças. Para a dor neuropática, por exemplo, o estudo de compostos que interagem com o receptor sigma-1 (Sig-1R) pode elucidar os principais fatores associados à atividade biológica dos mesmos. Nesse propósito, estudos de Relações Quantitativas Estrutura-Atividade (QSAR) utilizando os métodos de regressão por Mínimos Quadrados Parciais (PLS) e Rede Neural Artificial (ANN) foram aplicados a 64 antagonistas do Sig-1R pertencentes à classe de 1-arilpirazóis. Modelos PLS e ANN foram utilizados com o objetivo de descrever comportamentos lineares e não lineares, respectivamente, entre um conjunto de descritores e a atividade biológica dos compostos selecionados. O modelo PLS foi obtido com 51 compostos no conjunto treinamento e 13 compostos no conjunto teste (r² = 0,768, q² = 0,684 e r²teste = 0,785). Testes de leave-N-out, randomização da atividade biológica e detecção de outliers confirmaram a robustez e estabilidade dos modelos e mostraram que os mesmos não foram obtidos por correlações ao acaso. Modelos também foram gerados a partir da Rede Neural Artificial Perceptron de Multicamadas (MLP-ANN), sendo que a arquitetura 6-12-1, treinada com as funções de transferência tansig-tansig, apresentou a melhor resposta para a predição da atividade biológica dos compostos (r²treinamento = 0,891, r²validação = 0,852 e r²teste = 0,793). Outra abordagem foi utilizada para simular o ambiente de membranas sinápticas utilizando bicamadas lipídicas compostas por POPC, DOPE, POPS e colesterol. Os estudos de dinâmica molecular desenvolvidos mostraram que altas concentrações de colesterol induzem redução da área por lipídeo e difusão lateral e aumento na espessura da membrana e nos valores de parâmetro de ordem causados pelo ordenamento das cadeias acil dos fosfolipídeos. As bicamadas lipídicas obtidas podem ser usadas para simular interações entre lipídeos e pequenas moléculas ou proteínas contribuindo para as pesquisas associadas a doenças como Alzheimer e Parkinson. As abordagens usadas nessa tese são essenciais para o desenvolvimento de novas pesquisas em Química Medicinal Computacional.