Dam seepage analysis based on artificial neural networks: the hysteresis phenomenon

Seepage flow measurement is an important behavior indicator when providing information about dam performance. The main objective of this study is to analyze seepage by means of an artificial neural network model. The model is trained and validated with data measured at a case study. The dam behavior towards different water level changes is reproduced by the model and a hysteresis phenomenon detected and studied. Artificial neural network models are shown to be a powerful tool for predicting and understanding seepage phenomenon.

Distinct short-term plasticity at two excitatory synapses in the hippocampus

A single mossy fiber input contains several release sites and is located on the proximal portion of the apical dendrite of CA3 neurons. It is, therefore, well suited to exert a strong influence on pyramidal cell excitability. Accordingly, the mossy fiber synapse has been referred to as a detonator or teacher synapse in autoassociative network models of the hippocampus. The very low firing rates of granule cells [Jung, M. W. & McNaughton, B. L. (1993) Hippocampus 3, 165–182], which give rise to the mossy fibers, raise the question of how the mossy fiber synapse temporally integrates synaptic activity. We have therefore addressed the frequency dependence of mossy fiber transmission and compared it to associational/commissural synapses in the CA3 region of the hippocampus. Paired pulse facilitation had a similar time course, but was 2-fold greater for mossy fiber synapses. Frequency facilitation, during which repetitive stimulation causes a reversible growth in synaptic transmission, was markedly different at the two synapses. At associational/commissural synapses facilitation occurred only at frequencies greater than once every 10 s and reached a magnitude of about 125% of control. At mossy fiber synapses, facilitation occurred at frequencies as low as once every 40 s and reached a magnitude of 6-fold. Frequency facilitation was dependent on a rise in intraterminal Ca2+ and activation of Ca2+/calmodulin-dependent kinase II, and was greatly reduced at synapses expressing mossy fiber long-term potentiation. These results indicate that the mossy fiber synapse is able to integrate granule cell spiking activity over a broad range of frequencies, and this dynamic range is substantially reduced by long-term potentiation.

Modelos de rede de transporte público e individual para estudos de acessibilidade em São Paulo.

O presente estudo tem como objetivo comparar a eficiência dos sistemas de transporte público e individual através da modelagem de redes em SIG. Foram revisados os conceitos de acessibilidade e indicadores de acessibilidade, modelos de rede de transportes, abordadas as etapas para criação dos modelos de rede, bases de dados utilizadas, configurações e atributos no sistema SIG. Os comparativos foram realizados através de dois níveis de detalhamento (simples e avançado) para as redes de transporte e elaborados índices de acessibilidade para os bairros do município de São Paulo através de parâmetros extraídos das redes modeladas. O estudo de caso consiste na medição de um índice de acessibilidade para empregos de baixa renda. Como resultado, os bairros centrais do município apresentam maior acessibilidade, porém, para o transporte público, alguns bairros fora da zona central também apresentaram alta acessibilidade devido à oferta de transporte público (metrô).

Fault location in power distribution networks with distributed generation.

This research presents the development and implementation of fault location algorithms in power distribution networks with distributed generation units installed along their feeders. The proposed algorithms are capable of locating the fault based on voltage and current signals recorded by intelligent electronic devices installed at the end of the feeder sections, information to compute the loads connected to these feeders and their electric characteristics, and the operating status of the network. In addition, this work presents the study of analytical models of distributed generation and load technologies that could contribute to the performance of the proposed fault location algorithms. The validation of the algorithms was based on computer simulations using network models implemented in ATP, whereas the algorithms were implemented in MATLAB.

Across the dividing range - bridging the divides: Pharmacy opportunities across the hospital/community and inter-professional divides in rural and remote Australia

Rural and remote areas of Australia offer many opportunities for innovation in healthcare services. Some true healthcare 'network' models based around rural pharmacy can be established and evaluated. The lines between community and hospital pharmacy are often blurred and communication between health professionals enhanced. The blurring divide between hospital and community pharmacy in rural and remote areas has provided significant advances in practice. Projects have been set up to investigate the feasibility of community pharmacists integrating care for patients. These projects take advantage of the dual roles and the enhanced interaction between pharmacists and other health professionals in the bush. Opportunities for provision of clinical services beyond the traditional supply role have been taken in a number of remote communities

Neural networks for time-varying data

This paper reviews some basic issues and methods involved in using neural networks to respond in a desired fashion to a temporally-varying environment. Some popular network models and training methods are introduced. A speech recognition example is then used to illustrate the central difficulty of temporal data processing: learning to notice and remember relevant contextual information. Feedforward network methods are applicable to cases where this problem is not severe. The application of these methods are explained and applications are discussed in the areas of pure mathematics, chemical and physical systems, and economic systems. A more powerful but less practical algorithm for temporal problems, the moving targets algorithm, is sketched and discussed. For completeness, a few remarks are made on reinforcement learning.

Mixture density networks

Minimization of a sum-of-squares or cross-entropy error function leads to network outputs which approximate the conditional averages of the target data, conditioned on the input vector. For classifications problems, with a suitably chosen target coding scheme, these averages represent the posterior probabilities of class membership, and so can be regarded as optimal. For problems involving the prediction of continuous variables, however, the conditional averages provide only a very limited description of the properties of the target variables. This is particularly true for problems in which the mapping to be learned is multi-valued, as often arises in the solution of inverse problems, since the average of several correct target values is not necessarily itself a correct value. In order to obtain a complete description of the data, for the purposes of predicting the outputs corresponding to new input vectors, we must model the conditional probability distribution of the target data, again conditioned on the input vector. In this paper we introduce a new class of network models obtained by combining a conventional neural network with a mixture density model. The complete system is called a Mixture Density Network, and can in principle represent arbitrary conditional probability distributions in the same way that a conventional neural network can represent arbitrary functions. We demonstrate the effectiveness of Mixture Density Networks using both a toy problem and a problem involving robot inverse kinematics.

A representation of representation applied to a discussion of variable binding

States or state sequences in neural network models are made to represent concepts from applications. This paper motivates, introduces and discusses a formalism for denoting such representations; a representation for representations. The formalism is illustrated by using it to discuss the representation of variable binding and inference abstractly, and then to present four specific representations. One of these is an apparently novel hybrid of phasic and tensor-product representations which retains the desirable properties of each.

Two Bayesian treatments of the n-tuple recognition method

Two probabilistic interpretations of the n-tuple recognition method are put forward in order to allow this technique to be analysed with the same Bayesian methods used in connection with other neural network models. Elementary demonstrations are then given of the use of maximum likelihood and maximum entropy methods for tuning the model parameters and assisting their interpretation. One of the models can be used to illustrate the significance of overlapping n-tuple samples with respect to correlations in the patterns.

The learning dynamics of a universal approximator

The learning properties of a universal approximator, a normalized committee machine with adjustable biases, are studied for on-line back-propagation learning. Within a statistical mechanics framework, numerical studies show that this model has features which do not exist in previously studied two-layer network models without adjustable biases, e.g., attractive suboptimal symmetric phases even for realizable cases and noiseless data.

Theoretical foundations of neural networks

Neural networks have often been motivated by superficial analogy with biological nervous systems. Recently, however, it has become widely recognised that the effective application of neural networks requires instead a deeper understanding of the theoretical foundations of these models. Insight into neural networks comes from a number of fields including statistical pattern recognition, computational learning theory, statistics, information geometry and statistical mechanics. As an illustration of the importance of understanding the theoretical basis for neural network models, we consider their application to the solution of multi-valued inverse problems. We show how a naive application of the standard least-squares approach can lead to very poor results, and how an appreciation of the underlying statistical goals of the modelling process allows the development of a more general and more powerful formalism which can tackle the problem of multi-modality.

Topographic mappings and feed-forward neural networks

This thesis is a study of the generation of topographic mappings - dimension reducing transformations of data that preserve some element of geometric structure - with feed-forward neural networks. As an alternative to established methods, a transformational variant of Sammon's method is proposed, where the projection is effected by a radial basis function neural network. This approach is related to the statistical field of multidimensional scaling, and from that the concept of a 'subjective metric' is defined, which permits the exploitation of additional prior knowledge concerning the data in the mapping process. This then enables the generation of more appropriate feature spaces for the purposes of enhanced visualisation or subsequent classification. A comparison with established methods for feature extraction is given for data taken from the 1992 Research Assessment Exercise for higher educational institutions in the United Kingdom. This is a difficult high-dimensional dataset, and illustrates well the benefit of the new topographic technique. A generalisation of the proposed model is considered for implementation of the classical multidimensional scaling (¸mds}) routine. This is related to Oja's principal subspace neural network, whose learning rule is shown to descend the error surface of the proposed ¸mds model. Some of the technical issues concerning the design and training of topographic neural networks are investigated. It is shown that neural network models can be less sensitive to entrapment in the sub-optimal global minima that badly affect the standard Sammon algorithm, and tend to exhibit good generalisation as a result of implicit weight decay in the training process. It is further argued that for ideal structure retention, the network transformation should be perfectly smooth for all inter-data directions in input space. Finally, there is a critique of optimisation techniques for topographic mappings, and a new training algorithm is proposed. A convergence proof is given, and the method is shown to produce lower-error mappings more rapidly than previous algorithms.

Bayesian methods for neural networks

Bayesian techniques have been developed over many years in a range of different fields, but have only recently been applied to the problem of learning in neural networks. As well as providing a consistent framework for statistical pattern recognition, the Bayesian approach offers a number of practical advantages including a potential solution to the problem of over-fitting. This chapter aims to provide an introductory overview of the application of Bayesian methods to neural networks. It assumes the reader is familiar with standard feed-forward network models and how to train them using conventional techniques.

Bayesian methods for neural networks

Bayesian techniques have been developed over many years in a range of different fields, but have only recently been applied to the problem of learning in neural networks. As well as providing a consistent framework for statistical pattern recognition, the Bayesian approach offers a number of practical advantages including a potential solution to the problem of over-fitting. This chapter aims to provide an introductory overview of the application of Bayesian methods to neural networks. It assumes the reader is familiar with standard feed-forward network models and how to train them using conventional techniques.

Estimating conditional volatility with neural networks

It is well known that one of the obstacles to effective forecasting of exchange rates is heteroscedasticity (non-stationary conditional variance). The autoregressive conditional heteroscedastic (ARCH) model and its variants have been used to estimate a time dependent variance for many financial time series. However, such models are essentially linear in form and we can ask whether a non-linear model for variance can improve results just as non-linear models (such as neural networks) for the mean have done. In this paper we consider two neural network models for variance estimation. Mixture Density Networks (Bishop 1994, Nix and Weigend 1994) combine a Multi-Layer Perceptron (MLP) and a mixture model to estimate the conditional data density. They are trained using a maximum likelihood approach. However, it is known that maximum likelihood estimates are biased and lead to a systematic under-estimate of variance. More recently, a Bayesian approach to parameter estimation has been developed (Bishop and Qazaz 1996) that shows promise in removing the maximum likelihood bias. However, up to now, this model has not been used for time series prediction. Here we compare these algorithms with two other models to provide benchmark results: a linear model (from the ARIMA family), and a conventional neural network trained with a sum-of-squares error function (which estimates the conditional mean of the time series with a constant variance noise model). This comparison is carried out on daily exchange rate data for five currencies.