José Manuel Ortiz-Rodríguez

Robust Design of Artificial Neural Networks Methodology in Neutron Spectrometry

In this work, a systematical and methodological ANN optimization process known as robust design of artificial neural networks methodology, based on Taguchi method and Design of Experiments methodology, was applied to the design, training and testing of feed forward artificial neural networks trained with back-propagation training algorithm applied in the neutron spectrometry research area. The methodology was utilized to study the neutron spectrum unfolding problem by using a data set composed by 187 neutron spectra compiled by the International Atomic Energy Agency. In order to study the behavior of the designed neural networks topologies, four cases of grouping the neutron spectra were considered. In the first case 17 neutron spectra subsets were tested. In the second one 6 subsets. In the third case a data set with 53 neutron spectra and finally, in the fourth case, a data set with 187 neutron spectra was tested. For all the subsets, the robust design of artificial neural networks methodology was carried out. Around 1000 different neural network topologies were trained and tested, 36 net topologies for each subset. After all the network topologies were trained and tested, it was observed that the near optimum neural network topology which produced the best results was the fourth case, with the following topology: 7 neurons in the input layer, corresponding to the Bonner spheres readings; 14 neurons in a hidden layer and 31 neurons in the output layer corresponding to the 31 energy bins in which the spectrum is expressed, a learning rate and momentum equal to 0.1. The results obtained reveal that the robust design methodology offer potential benefits in the evaluation of the behavior of the net as well as the ability to examine the interaction of the weights and neurons inside the same one.

A comparison of back propagation and Generalized Regression Neural Networks performance in neutron spectrometry.

The process of unfolding the neutron energy spectrum has been subject of research for many years. Monte Carlo, iterative methods, the bayesian theory, the principle of maximum entropy are some of the methods used. The drawbacks associated with traditional unfolding procedures have motivated the research of complementary approaches. Back Propagation Neural Networks (BPNN), have been applied with success in neutron spectrometry and dosimetry domains, however, the structure and learning parameters are factors that highly impact in the networks performance. In ANN domain, Generalized Regression Neural Network (GRNN) is one of the simplest neural networks in term of network architecture and learning algorithm. The learning is instantaneous, requiring no time for training. Opposite to BPNN, a GRNN would be formed instantly with just a 1-pass training on the development data. In the network development phase, the only hurdle is to optimize the hyper-parameter, which is known as sigma, governing the smoothness of the network. The aim of this work was to compare the performance of BPNN and GRNN in the solution of the neutron spectrometry problem. From results obtained it can be observed that despite the very similar results, GRNN performs better than BPNN.

Matrix metalloproteinase multiplex screening identifies increased MMP-2 urine concentrations in women predicted to develop preeclampsia.

Abstract Background: Preeclampsia, a pregnancy disorder characterized by hypertension and proteinuria, represents the leading cause of fetal and maternal morbidity and mortality in developing countries. The identification of novel and accurate biomarkers that are predictive of preeclampsia is necessary to improve the prognosis of patients with preeclampsia. Objective: The objective of this study is to evaluate the usefulness of nine urinary metalloproteinases to predict the risk of preeclampsia development. Methods: MMP-1, MMP-2, MMP-3, MMP-7, MMP-8, MMP-9, MMP-10, MMP-12 and MMP-13 were analyzed in urine (early-pregnancy) from 17 women predicted to develop preeclampsia and 48 controls using the Bio-Plex Pro-Human MMP panel (Bio-Rad, Hercules, CA). Results: Urinary MMP-2 showed differences between groups which allowed us to calculate an increased risk for PE development of up to 20 times among the study population. Conclusion: Increased urinary concentration of MMP-2 at 12 and 16 weeks of gestation predicted an increased risk of developing preeclampsia in the study population.

Evaluating the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks

In this work the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks is evaluated. The first one code based on traditional iterative procedures and called Neutron spectrometry and dosimetry from the Universidad Autonoma de Zacatecas (NSDUAZ) use the SPUNIT iterative algorithm and was designed to unfold neutron spectrum and calculate 15 dosimetric quantities and 7 IAEA survey meters. The main feature of this code is the automated selection of the initial guess spectrum trough a compendium of neutron spectrum compiled by the IAEA. The second one code known as Neutron spectrometry and dosimetry with artificial neural networks (NDSann) is a code designed using neural nets technology. The artificial intelligence approach of neural net does not solve mathematical equations. By using the knowledge stored at synaptic weights on a neural net properly trained, the code is capable to unfold neutron spectrum and to simultaneously calculate 15 dosimetric qua...

A neutron spectrum unfolding code based on generalized regression artificial neural networks

The most delicate part of neutron spectrometry, is the unfolding process. The derivation of the spectral information is not simple because the unknown is not given directly as a result of the measurements. Novel methods based on Artificial Neural Networks have been widely investigated. In prior works, back propagation neural networks (BPNN) have been used to solve the neutron spectrometry problem, however, some drawbacks still exist using this kind of neural nets, i.e. the optimum selection of the network topology and the long training time. Compared to BPNN, its usually much faster to train a generalized regression neural network (GRNN). Thats mainly because spread constant is the only parameter used in GRNN. Another feature is that the network will converge to a global minimum, provided that the optimal values of spread has been determined and that the dataset adequately represents the problem space. In addition, GRNN are often more accurate than BPNN in the prediction. These characteristics make GRNNs to be of great interest in the neutron spectrometry domain. This work presents a computational tool based on GRNN capable to solve the neutron spectrometry problem. This computational code, automates the pre-processing, training and testing stages using a k-fold cross validation of 3 folds, the statistical analysis and the post-processing of the information, using 7 Bonner spheres rate counts as only entrance data. The code was designed for a Bonner Spheres System based on a 6LiI(Eu) neutron detector and a response matrix expressed in 60 energy bins taken from an International Atomic Energy Agency compilation.

Generalized Regression Neural Networks with Application in Neutron Spectrometry

The aim of this research was to apply a generalized regression neural network (GRNN) to predict neutron spectrum using the rates count coming from a Bonner spheres system as the only piece of information. In the training and testing stages, a data set of 251 different types of neutron spectra, taken from the International Atomic Energy Agency compilation, were used. Fifty-one predicted spectra were analyzed at testing stage. Training and testing of GRNN were carried out in the MATLAB environment by means of a scientific and technological tool designed based on GRNN technology, which is capable of solving the neutron spectrometry problem with high performance and generalization capability. This computational tool automates the pre-processing of information, the training and testing stages, the statistical analysis, and the postprocessing of the information. In this work, the performance of feed-forward backpropagation neural networks (FFBPNN) and GRNN was compared in the solution of the neutron spectrometry problem. From the results obtained, it can be observed that

Evolutionary Artificial Neural Networks in Neutron Spectrometry

1.1 Artificial neural networks Artificial Neural Networks (ANN), are highly simplified models of the brain processes (Graupe, 2007; Kasabov, 1998). AnANN is a biologically inspired computational model which consists of a large number of simple processing elements called neurons, units, cells, or nodes which are interconnected and operate in parallel (Galushkin, 2007; Lakhmi & Fanelli, 2000). Each neuron is connected to other neurons by means of directed communication links, which constitute the neuronal structure, each with an associated weight (Dreyfus, 2005). The weights represent information being used by the net to solve a problem. Figure 1 shows an abbreviated notation for an individual artificial neuron, which is used in schemes of multiple neurons (Beale et al., 1992). Here the input p, a vector of R input elements, is represented by the solid dark vertical bar at the left. The dimensions of p are shown below the symbol p in the figure as Rx1. These inputs post multiply the single-row, R − column matrix W. A constant 1 enters the neuron as an input and is multiplied by a bias b. The net input to the transfer function f is n, the sum of the bias b and the product Wp. This sum is passed to the transfer function f to get the neuron’s output a.