On Building a Memory Evolutive System for Application to Learning and Cognition Modeling

We address here aspects of the implementation of a memory evolutive system (MES), based on the model proposed by A. Ehresmann and J. Vanbremeersch (2007), by means of a simulated network of spiking neurons with time dependent plasticity. We point out the advantages and challenges of applying category theory for the representation of cognition, by using the MES architecture. Then we discuss the issues concerning the minimum requirements that an artificial neural network (ANN) should fulfill in order that it would be capable of expressing the categories and mappings between them, underlying the MES. We conclude that a pulsed ANN based on Izhikevich`s formal neuron with STDP (spike time-dependent plasticity) has sufficient dynamical properties to achieve these requirements, provided it can cope with the topological requirements. Finally, we present some perspectives of future research concerning the proposed ANN topology.

Suitability of relative humidity as an estimator of leaf wetness duration

Leaf wetness duration (LWD) is a key parameter in agricultural meteorology since it is related to epidemiology of many important crops, controlling pathogen infection and development rates. Because LWD is not widely measured, several methods have been developed to estimate it from weather data. Among the models used to estimate LWD, those that use physical principles of dew formation and dew and/or rain evaporation have shown good portability and sufficiently accurate results, but their complexity is a disadvantage for operational use. Alternatively, empirical models have been used despite their limitations. The simplest empirical models use only relative humidity data. The objective of this study was to evaluate the performance of three RH-based empirical models to estimate LWD in four regions around the world that have different climate conditions. Hourly LWD, air temperature, and relative humidity data were obtained from Ames, IA (USA), Elora, Ontario (Canada), Florence, Toscany (Italy), and Piracicaba, Sao Paulo State (Brazil). These data were used to evaluate the performance of the following empirical LWD estimation models: constant RH threshold (RH >= 90%); dew point depression (DPD); and extended RH threshold (EXT_RH). Different performance of the models was observed in the four locations. In Ames, Elora and Piracicaba, the RH >= 90% and DPD models underestimated LWD, whereas in Florence these methods overestimated LWD, especially for shorter wet periods. When the EXT_RH model was used, LWD was overestimated for all locations, with a significant increase in the errors. In general, the RH >= 90% model performed best, presenting the highest general fraction of correct estimates (F(C)), between 0.87 and 0.92, and the lowest false alarm ratio (F(AR)), between 0.02 and 0.31. The use of specific thresholds for each location improved accuracy of the RH model substantially, even when independent data were used; MAE ranged from 1.23 to 1.89 h, which is very similar to errors obtained with published physical models for LWD estimation. Based on these results, we concluded that, if calibrated locally, LWD can be estimated with acceptable accuracy by RH above a specific threshold, and that the EXT_RH method was unsuitable for estimating LWD at the locations used in this study. (C) 2007 Elsevier B.V. All rights reserved.

Capillary network models for transport in packed beds: Considerations of pore aspect ratio

The conventional analysis for the estimation of the tortuosity factor for transport in porous media is modified here to account for the effect of pore aspect ratio. Structural models of the porous medium are also constructed for calculating the aspect ratio as a function of porosity. Comparison of the model predictions with the extensive data of Currie (1960) for the effective diffusivity of hydrogen in packed beds shows good agreement with a network model of randomly oriented intersecting pores for porosities upto about 50 percent, which is the region of practical interest. The predictions based on this network model are also found to be in better agreement with the data of Currie than earlier expressions developed for unconsolidated and grainy media.

Computational binding assays of antigenic peptides

Computer models can be combined with laboratory experiments for the efficient determination of (i) peptides that bind MHC molecules and (ii) T-cell epitopes. For maximum benefit, the use of computer models must be treated as experiments analogous to standard laboratory procedures. This requires the definition of standards and experimental protocols for model application. We describe the requirements for validation and assessment of computer models. The utility of combining accurate predictions with a limited number of laboratory experiments is illustrated by practical examples. These include the identification of T-cell epitopes from IDDM-, melanoma- and malaria-related antigens by combining computational and conventional laboratory assays. The success rate in determining antigenic peptides, each in the context of a specific HLA molecule, ranged from 27 to 71%, while the natural prevalence of MHC-binding peptides is 0.1-5%.

Context-free and context-sensitive dynamics in recurrent neural networks

Continuous-valued recurrent neural networks can learn mechanisms for processing context-free languages. The dynamics of such networks is usually based on damped oscillation around fixed points in state space and requires that the dynamical components are arranged in certain ways. It is shown that qualitatively similar dynamics with similar constraints hold for a(n)b(n)c(n), a context-sensitive language. The additional difficulty with a(n)b(n)c(n), compared with the context-free language a(n)b(n), consists of 'counting up' and 'counting down' letters simultaneously. The network solution is to oscillate in two principal dimensions, one for counting up and one for counting down. This study focuses on the dynamics employed by the sequential cascaded network, in contrast to the simple recurrent network, and the use of backpropagation through time. Found solutions generalize well beyond training data, however, learning is not reliable. The contribution of this study lies in demonstrating how the dynamics in recurrent neural networks that process context-free languages can also be employed in processing some context-sensitive languages (traditionally thought of as requiring additional computation resources). This continuity of mechanism between language classes contributes to our understanding of neural networks in modelling language learning and processing.

Computational methods for prediction of T-cell epitopes - a framework for modelling, testing, and applications

Computational models complement laboratory experimentation for efficient identification of MHC-binding peptides and T-cell epitopes. Methods for prediction of MHC-binding peptides include binding motifs, quantitative matrices, artificial neural networks, hidden Markov models, and molecular modelling. Models derived by these methods have been successfully used for prediction of T-cell epitopes in cancer, autoimmunity, infectious disease, and allergy. For maximum benefit, the use of computer models must be treated as experiments analogous to standard laboratory procedures and performed according to strict standards. This requires careful selection of data for model building, and adequate testing and validation. A range of web-based databases and MHC-binding prediction programs are available. Although some available prediction programs for particular MHC alleles have reasonable accuracy, there is no guarantee that all models produce good quality predictions. In this article, we present and discuss a framework for modelling, testing, and applications of computational methods used in predictions of T-cell epitopes. (C) 2004 Elsevier Inc. All rights reserved.

A decision support system to facilitate management of patients with acute gastrointestinal bleeding

Objective: To develop a model to predict the bleeding source and identify the cohort amongst patients with acute gastrointestinal bleeding (GIB) who require urgent intervention, including endoscopy. Patients with acute GIB, an unpredictable event, are most commonly evaluated and managed by non-gastroenterologists. Rapid and consistently reliable risk stratification of patients with acute GIB for urgent endoscopy may potentially improve outcomes amongst such patients by targeting scarce health-care resources to those who need it the most. Design and methods: Using ICD-9 codes for acute GIB, 189 patients with acute GIB and all. available data variables required to develop and test models were identified from a hospital medical records database. Data on 122 patients was utilized for development of the model and on 67 patients utilized to perform comparative analysis of the models. Clinical data such as presenting signs and symptoms, demographic data, presence of co-morbidities, laboratory data and corresponding endoscopic diagnosis and outcomes were collected. Clinical data and endoscopic diagnosis collected for each patient was utilized to retrospectively ascertain optimal management for each patient. Clinical presentations and corresponding treatment was utilized as training examples. Eight mathematical models including artificial neural network (ANN), support vector machine (SVM), k-nearest neighbor, linear discriminant analysis (LDA), shrunken centroid (SC), random forest (RF), logistic regression, and boosting were trained and tested. The performance of these models was compared using standard statistical analysis and ROC curves. Results: Overall the random forest model best predicted the source, need for resuscitation, and disposition with accuracies of approximately 80% or higher (accuracy for endoscopy was greater than 75%). The area under ROC curve for RF was greater than 0.85, indicating excellent performance by the random forest model Conclusion: While most mathematical models are effective as a decision support system for evaluation and management of patients with acute GIB, in our testing, the RF model consistently demonstrated the best performance. Amongst patients presenting with acute GIB, mathematical models may facilitate the identification of the source of GIB, need for intervention and allow optimization of care and healthcare resource allocation; these however require further validation. (c) 2007 Elsevier B.V. All rights reserved.

Desenvolvimento e análise de uma rede neural artificial para estimativa da erosividade da chuva para o Estado de São Paulo

O conhecimento do valor da erosividade da chuva (R) de determinada localidade é fundamental para a estimativa das perdas de solo feitas a partir da Equação Universal de Perdas de Solo, sendo, portanto, de grande importância no planejamento conservacionista. A fim de obter estimativas do valor de R para localidades onde este é desconhecido, desenvolveu-se uma rede neural artificial (RNA) e analisou-se a acurácia desta com o método de interpolação "Inverso de uma Potência da Distância" (ID). Comparando a RNA desenvolvida com o método de interpolação ID, verificou-se que a primeira apresentou menor erro relativo médio na estimativa de R e melhor índice de confiança, classificado como "Ótimo", podendo, portanto, ser utilizada no planejamento de uso, manejo e conservação do solo no Estado de São Paulo.

Virtual simulation of the postsurgical cosmetic outcome in patientswith pectus excavatum

Pectus excavatum is the most common congenital deformity of the anterior chest wall, in which several ribs and the sternum grow abnormally. Nowadays, the surgical correction is carried out in children and adults through Nuss technic. This technic has been shown to be safe with major drivers as cosmesis and the prevention of psychological problems and social stress. Nowadays, no application is known to predict the cosmetic outcome of the pectus excavatum surgical correction. Such tool could be used to help the surgeon and the patient in the moment of deciding the need for surgery correction. This work is a first step to predict postsurgical outcome in pectus excavatum surgery correction. Facing this goal, it was firstly determined a point cloud of the skin surface along the thoracic wall using Computed Tomography (before surgical correction) and the Polhemus FastSCAN (after the surgical correction). Then, a surface mesh was reconstructed from the two point clouds using a Radial Basis Function algorithm for further affine registration between the meshes. After registration, one studied the surgical correction influence area (SCIA) of the thoracic wall. This SCIA was used to train, test and validate artificial neural networks in order to predict the surgical outcome of pectus excavatum correction and to determine the degree of convergence of SCIA in different patients. Often, ANN did not converge to a satisfactory solution (each patient had its own deformity characteristics), thus invalidating the creation of a mathematical model capable of estimating, with satisfactory results, the postsurgical outcome

Short-term wind forecasting for energy resources scheduling

This paper proposes a wind power forecasting methodology based on two methods: direct wind power forecasting and wind speed forecasting in the first phase followed by wind power forecasting using turbines characteristics and the aforementioned wind speed forecast. The proposed forecasting methodology aims to support the operation in the scope of the intraday resources scheduling model, namely with a time horizon of 5 minutes. This intraday model supports distribution network operators in the short-term scheduling problem, in the smart grid context. A case study using a real database of 12 months recorded from a Portuguese wind power farm was used. The results show that the straightforward methodology can be applied in the intraday model with high wind speed and wind power accuracy. The wind power forecast direct method shows better performance than wind power forecast using turbine characteristics and wind speed forecast obtained in first phase.

ANN-Based LMP forecasting in a distribution network with large penetration of DG

In recent years, power systems have experienced many changes in their paradigm. The introduction of new players in the management of distributed generation leads to the decentralization of control and decision-making, so that each player is able to play in the market environment. In the new context, it will be very relevant that aggregator players allow midsize, small and micro players to act in a competitive environment. In order to achieve their objectives, virtual power players and single players are required to optimize their energy resource management process. To achieve this, it is essential to have financial resources capable of providing access to appropriate decision support tools. As small players have difficulties in having access to such tools, it is necessary that these players can benefit from alternative methodologies to support their decisions. This paper presents a methodology, based on Artificial Neural Networks (ANN), and intended to support smaller players. In this case the present methodology uses a training set that is created using energy resource scheduling solutions obtained using a mixed-integer linear programming (MIP) approach as the reference optimization methodology. The trained network is used to obtain locational marginal prices in a distribution network. The main goal of the paper is to verify the accuracy of the ANN based approach. Moreover, the use of a single ANN is compared with the use of two or more ANN to forecast the locational marginal price.

Symbolic Knowledge Extraction from Trained Neural Networks Governed by Lukasiewicz Logics

This work describes a methodology to extract symbolic rules from trained neural networks. In our approach, patterns on the network are codified using formulas on a Lukasiewicz logic. For this we take advantage of the fact that every connective in this multi-valued logic can be evaluated by a neuron in an artificial network having, by activation function the identity truncated to zero and one. This fact simplifies symbolic rule extraction and allows the easy injection of formulas into a network architecture. We trained this type of neural network using a back-propagation algorithm based on Levenderg-Marquardt algorithm, where in each learning iteration, we restricted the knowledge dissemination in the network structure. This makes the descriptive power of produced neural networks similar to the descriptive power of Lukasiewicz logic language, minimizing the information loss on the translation between connectionist and symbolic structures. To avoid redundance on the generated network, the method simplifies them in a pruning phase, using the "Optimal Brain Surgeon" algorithm. We tested this method on the task of finding the formula used on the generation of a given truth table. For real data tests, we selected the Mushrooms data set, available on the UCI Machine Learning Repository.

Avaliação de um sistema CAD na deteção de lesões em imagens mamográficas

Mestrado em Radiações Aplicadas às Tecnologias da Saúde - Área de especialização: Imagem Digital por Radiação X.

FMRI 3D registration based on Fourier space subsets using neural networks

In this work, we present a neural network (NN) based method designed for 3D rigid-body registration of FMRI time series, which relies on a limited number of Fourier coefficients of the images to be aligned. These coefficients, which are comprised in a small cubic neighborhood located at the first octant of a 3D Fourier space (including the DC component), are then fed into six NN during the learning stage. Each NN yields the estimates of a registration parameter. The proposed method was assessed for 3D rigid-body transformations, using DC neighborhoods of different sizes. The mean absolute registration errors are of approximately 0.030 mm in translations and 0.030 deg in rotations, for the typical motion amplitudes encountered in FMRI studies. The construction of the training set and the learning stage are fast requiring, respectively, 90 s and 1 to 12 s, depending on the number of input and hidden units of the NN. We believe that NN-based approaches to the problem of FMRI registration can be of great interest in the future. For instance, NN relying on limited K-space data (possibly in navigation echoes) can be a valid solution to the problem of prospective (in frame) FMRI registration.

Estimação de cobertura rádio em GSM-R através de redes neuronais

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia de Eletrónica e Telecomunicações