A methodology for improving computed individual regressions predictions.

This research proposes a methodology to improve computed individual prediction values provided by an existing regression model without having to change either its parameters or its architecture. In other words, we are interested in achieving more accurate results by adjusting the calculated regression prediction values, without modifying or rebuilding the original regression model. Our proposition is to adjust the regression prediction values using individual reliability estimates that indicate if a single regression prediction is likely to produce an error considered critical by the user of the regression. The proposed method was tested in three sets of experiments using three different types of data. The first set of experiments worked with synthetically produced data, the second with cross sectional data from the public data source UCI Machine Learning Repository and the third with time series data from ISO-NE (Independent System Operator in New England). The experiments with synthetic data were performed to verify how the method behaves in controlled situations. In this case, the outcomes of the experiments produced superior results with respect to predictions improvement for artificially produced cleaner datasets with progressive worsening with the addition of increased random elements. The experiments with real data extracted from UCI and ISO-NE were done to investigate the applicability of the methodology in the real world. The proposed method was able to improve regression prediction values by about 95% of the experiments with real data.

Intensificação da transferência de calor e otimização de trocadores de calor compactos tipo venezianas com geradores de vórtices tipo delta-winglets.

Esta pesquisa visa a análise da contribuição de cinco variáveis de entrada e a otimização do desempenho termo-hidráulico de trocadores de calor com venezianas combinados com geradores de vórtices delta-winglets. O desempenho termohidráulico de duas geometrias distintas, aqui nomeadas por GEO1 e GEO2, foram avaliadas. Smoothing Spline ANOVA foi usado para avaliar a contribuição dos parâmetros de entrada na transferência de calor e perda de carga. Considerando aplicação automotiva, foram investigados números de Reynolds iguais a 120 e 240, baseados no diâmetro hidráulico. Os resultados indicaram que o ângulo de venezianas é o maior contribuidor para o aumento do fator de atrito para GEO1 e GEO2, para ambos os números de Reynolds. Para o número de Reynolds menor, o parâmetro mais importante em termos de transferência de calor foi o ângulo das venezianas para ambas as geometrias. Para o número de Reynolds maior, o ângulo de ataque dos geradores de vórtices posicionados na primeira fileira é o maior contribuidor para a tranfesferência de calor, no caso da geometria GEO1, enquanto que o ângulo de ataque dos geradores de vórtices na primeira fileira foi tão importante quanto os ângulos das venezianas para a geometria GEO2. Embora as geometrias analisadas possam ser consideradas como técnicas compostas de intensificação da transferência de calor, não foram observadas interações relevantes entre ângulo de venezianas e parâmetros dos geradores de vórtices. O processo de otimização usa NSGA-II (Non-Dominated Sorting Genetic Algorithm) combinado com redes neurais artificiais. Os resultados mostraram que a adição dos geradores de vórtices em GEO1 aumentaram a transferência de calor em 21% e 23% com aumentos na perda de carga iguais a 24,66% e 36,67% para o menor e maior números de Reynolds, respectivamente. Para GEO2, a transferência de calor aumentou 13% e 15% com aumento na perda de carga de 20,33% e 23,70%, para o menor e maior número de Reynolds, respectivamente. As soluções otimizadas para o fator de Colburn mostraram que a transferência de calor atrás da primeira e da segunda fileiras de geradores de vórtices tem a mesma ordem de magnitude para ambos os números de Reynolds. Os padrões de escoamento e as características de transferência de calor das soluções otimizadas apresentaram comportamentos vi particulares, diferentemente daqueles encontrados quando as duas técnicas de intensificação de transferência de calor são aplicadas separadamente.

Aplicação de métodos computacionais multidisciplinares de engenharia para otimização de carteiras de investimentos.

Este trabalho apresenta uma nova metodologia para otimizar carteiras de ativos financeiros. A metodologia proposta, baseada em interpoladores universais tais quais as Redes Neurais Artificiais e a Krigagem, permite aproximar a superfície de risco e consequentemente a solução do problema de otimização associado a ela de forma generalizada e aplicável a qualquer medida de risco disponível na literatura. Além disto, a metodologia sugerida permite que sejam relaxadas hipóteses restritivas inerentes às metodologias existentes, simplificando o problema de otimização e permitindo que sejam estimados os erros na aproximação da superfície de risco. Ilustrativamente, aplica-se a metodologia proposta ao problema de composição de carteiras com a Variância (controle), o Valor-em-Risco (VaR) e o Valor-em-Risco Condicional (CVaR) como funções objetivo. Os resultados são comparados àqueles obtidos pelos modelos de Markowitz e Rockafellar, respectivamente.

Growing Neural Gas approach for obtaining homogeneous maps by restricting the insertion of new nodes

The Growing Neural Gas model is used widely in artificial neural networks. However, its application is limited in some contexts by the proliferation of nodes in dense areas of the input space. In this study, we introduce some modifications to address this problem by imposing three restrictions on the insertion of new nodes. Each restriction aims to maintain the homogeneous values of selected criteria. One criterion is related to the square error of classification and an alternative approach is proposed for avoiding additional computational costs. Three parameters are added that allow the regulation of the restriction criteria. The resulting algorithm allows models to be obtained that suit specific needs by specifying meaningful parameters.

Improving 3D Keypoint Detection from Noisy Data Using Growing Neural Gas

3D sensors provides valuable information for mobile robotic tasks like scene classification or object recognition, but these sensors often produce noisy data that makes impossible applying classical keypoint detection and feature extraction techniques. Therefore, noise removal and downsampling have become essential steps in 3D data processing. In this work, we propose the use of a 3D filtering and down-sampling technique based on a Growing Neural Gas (GNG) network. GNG method is able to deal with outliers presents in the input data. These features allows to represent 3D spaces, obtaining an induced Delaunay Triangulation of the input space. Experiments show how the state-of-the-art keypoint detectors improve their performance using GNG output representation as input data. Descriptors extracted on improved keypoints perform better matching in robotics applications as 3D scene registration.

Morphological classification of microtidal sand and gravel beaches

A new classification of microtidal sand and gravel beaches with very different morphologies is presented below. In 557 studied transects, 14 variables were used. Among the variables to be emphasized is the depth of the Posidonia oceanica. The classification was performed for 9 types of beaches: Type 1: Sand and gravel beaches, Type 2: Sand and gravel separated beaches, Type 3: Gravel and sand beaches, Type 4: Gravel and sand separated beaches, Type 5: Pure gravel beaches, Type 6: Open sand beaches, Type 7: Supported sand beaches, Type 8: Bisupported sand beaches and Type 9: Enclosed beaches. For the classification, several tools were used: discriminant analysis, neural networks and Support Vector Machines (SVM), the results were then compared. As there is no theory for deciding which is the most convenient neural network architecture to deal with a particular data set, an experimental study was performed with different numbers of neuron in the hidden layer. Finally, an architecture with 30 neurons was chosen. Different kernels were employed for SVM (Linear, Polynomial, Radial basis function and Sigmoid). The results obtained for the discriminant analysis were not as good as those obtained for the other two methods (ANN and SVM) which showed similar success.

Aid decision algorithms to estimate the risk in congenital heart surgery

Background and objective: In this paper, we have tested the suitability of using different artificial intelligence-based algorithms for decision support when classifying the risk of congenital heart surgery. In this sense, classification of those surgical risks provides enormous benefits as the a priori estimation of surgical outcomes depending on either the type of disease or the type of repair, and other elements that influence the final result. This preventive estimation may help to avoid future complications, or even death. Methods: We have evaluated four machine learning algorithms to achieve our objective: multilayer perceptron, self-organizing map, radial basis function networks and decision trees. The architectures implemented have the aim of classifying among three types of surgical risk: low complexity, medium complexity and high complexity. Results: Accuracy outcomes achieved range between 80% and 99%, being the multilayer perceptron method the one that offered a higher hit ratio. Conclusions: According to the results, it is feasible to develop a clinical decision support system using the evaluated algorithms. Such system would help cardiology specialists, paediatricians and surgeons to forecast the level of risk related to a congenital heart disease surgery.

Calcareous plankton response to orbital and millennial-scale climate changes from ODP Leg 161-975

The paleoenvironmental conditions through MIS 15-9 at the Mediterranean Ocean Drilling Program (ODP) Site 975 were interpreted by high resolution study of calcareous plankton assemblages compared with available d18O and d13C records and high resolution paleoclimate proxies from the Atlantic Ocean. Sea Surface Temperatures (SSTs) have been estimated from planktonic foraminiferal assemblages using the artificial neural networks method. Calcareous plankton varied dominantly on a glacial-interglacial scale as testified by the SST record, foraminiferal diversity, total coccolith abundance and changes in warm-water calcareous nannofossil taxa. A general increase in foraminiferal diversity and of total coccolith abundance is observed during interglacials. Warmest SSTs are reached during MIS 11, while MIS 12 and MIS 10 represent the coldest intervals of the studied record. During MIS 12, one of the most extreme glacials of the last million years, occurrence of Globorotalia inflata and of neogloboquadrinids indicates a shoaling of the interface between Atlantic inflowing and Mediterranean outflowing waters. Among calcareous nannofossils the distribution of Gephyrocapsa margereli-G. muellerae > 4 µm also supports a reduced Atlantic-Mediterranean exchange during MIS 12. Superimposed on glacial-interglacial variability, six short-terms coolings are recognized during MIS 12 and 10, which appear comparable in their distribution and amplitude to the Heinrich - type events documented in the Atlantic Ocean in the same interval. During these H-type events, N. pachyderma (s) and G. margereli-G. muellerae > 4 µm increase as a response to the enhanced inflow of cold Atlantic water into the Mediterranean via the Strait of Gibraltar. Mediterranean surface water hydrography appears to have been most severely affected at Termination V during the H-type event Ht4, possibly as a response to a large volume of Atlantic meltwater inflow via the Strait of Gibraltar and/or to freshwater/terrigenous input deriving from local mountain glaciers. Three additional SST coolings are recorded through MIS 14-16, but these are not well correlated with Heinrich - type events documented in the Atlantic Ocean in the same interval; during these cooling episodes only the subpolar Turborotalita quinqueloba increases. These results highlight the sensitive response of the Mediterranean basin to millennial-scale climate variations related to Northern Hemisphere ice-sheet instability and support the hypothesis that the tight connection between high latitude climate dynamics and Mediterranean sea surface water features can be traced through the Middle Pleistocene.

Predictive vaccinology: Optimisation of predictions using support vector machine classifiers

Promiscuous human leukocyte antigen (HLA) binding peptides are ideal targets for vaccine development. Existing computational models for prediction of promiscuous peptides used hidden Markov models and artificial neural networks as prediction algorithms. We report a system based on support vector machines that outperforms previously published methods. Preliminary testing showed that it can predict peptides binding to HLA-A2 and -A3 super-type molecules with excellent accuracy, even for molecules where no binding data are currently available.

Calibrating photometric redshifts of luminous red galaxies

We discuss the construction of a photometric redshift catalogue of luminous red galaxies (LRGs) from the Sloan Digital Sky Survey (SDSS), emphasizing the principal steps necessary for constructing such a catalogue: (i) photometrically selecting the sample, (ii) measuring photometric redshifts and their error distributions, and (iii) estimating the true redshift distribution. We compare two photometric redshift algorithms for these data and find that they give comparable results. Calibrating against the SDSS and SDSS-2dF (Two Degree Field) spectroscopic surveys, we find that the photometric redshift accuracy is sigma similar to 0.03 for redshifts less than 0.55 and worsens at higher redshift (similar to 0.06 for z < 0.7). These errors are caused by photometric scatter, as well as systematic errors in the templates, filter curves and photometric zero-points. We also parametrize the photometric redshift error distribution with a sum of Gaussians and use this model to deconvolve the errors from the measured photometric redshift distribution to estimate the true redshift distribution. We pay special attention to the stability of this deconvolution, regularizing the method with a prior on the smoothness of the true redshift distribution. The methods that we develop are applicable to general photometric redshift surveys.

An Incremental EM-based Learning Approach for On-Line Prediction of Hospital Resource Utilization

Objective: Inpatient length of stay (LOS) is an important measure of hospital activity, health care resource consumption, and patient acuity. This research work aims at developing an incremental expectation maximization (EM) based learning approach on mixture of experts (ME) system for on-line prediction of LOS. The use of a batchmode learning process in most existing artificial neural networks to predict LOS is unrealistic, as the data become available over time and their pattern change dynamically. In contrast, an on-line process is capable of providing an output whenever a new datum becomes available. This on-the-spot information is therefore more useful and practical for making decisions, especially when one deals with a tremendous amount of data. Methods and material: The proposed approach is illustrated using a real example of gastroenteritis LOS data. The data set was extracted from a retrospective cohort study on all infants born in 1995-1997 and their subsequent admissions for gastroenteritis. The total number of admissions in this data set was n = 692. Linked hospitalization records of the cohort were retrieved retrospectively to derive the outcome measure, patient demographics, and associated co-morbidities information. A comparative study of the incremental learning and the batch-mode learning algorithms is considered. The performances of the learning algorithms are compared based on the mean absolute difference (MAD) between the predictions and the actual LOS, and the proportion of predictions with MAD < 1 day (Prop(MAD < 1)). The significance of the comparison is assessed through a regression analysis. Results: The incremental learning algorithm provides better on-line prediction of LOS when the system has gained sufficient training from more examples (MAD = 1.77 days and Prop(MAD < 1) = 54.3%), compared to that using the batch-mode learning. The regression analysis indicates a significant decrease of MAD (p-value = 0.063) and a significant (p-value = 0.044) increase of Prop(MAD

Extreme learning machine for predicting HLA-peptide binding

Machine learning techniques have been recognized as powerful tools for learning from data. One of the most popular learning techniques, the Back-Propagation (BP) Artificial Neural Networks, can be used as a computer model to predict peptides binding to the Human Leukocyte Antigens (HLA). The major advantage of computational screening is that it reduces the number of wet-lab experiments that need to be performed, significantly reducing the cost and time. A recently developed method, Extreme Learning Machine (ELM), which has superior properties over BP has been investigated to accomplish such tasks. In our work, we found that the ELM is as good as, if not better than, the BP in term of time complexity, accuracy deviations across experiments, and most importantly - prevention from over-fitting for prediction of peptide binding to HLA.

Rule extraction from technology IPOs in the US stock market

Machine learning techniques for prediction and rule extraction from artificial neural network methods are used. The hypothesis that market sentiment and IPO specific attributes are equally responsible for first-day IPO returns in the US stock market is tested. Machine learning methods used are Bayesian classifications, support vector machines, decision tree techniques, rule learners and artificial neural networks. The outcomes of the research are predictions and rules associated With first-day returns of technology IPOs. The hypothesis that first-day returns of technology IPOs are equally determined by IPO specific and market sentiment is rejected. Instead lower yielding IPOs are determined by IPO specific and market sentiment attributes, while higher yielding IPOs are largely dependent on IPO specific attributes.

Representation and learning of visual information for pose recognition

Recovering position from sensor information is an important problem in mobile robotics, known as localisation. Localisation requires a map or some other description of the environment to provide the robot with a context to interpret sensor data. The mobile robot system under discussion is using an artificial neural representation of position. Building a geometrical map of the environment with a single camera and artificial neural networks is difficult. Instead it would be simpler to learn position as a function of the visual input. Usually when learning images, an intermediate representation is employed. An appropriate starting point for biologically plausible image representation is the complex cells of the visual cortex, which have invariance properties that appear useful for localisation. The effectiveness for localisation of two different complex cell models are evaluated. Finally the ability of a simple neural network with single shot learning to recognise these representations and localise a robot is examined.

Modelling conditional probability distributions for periodic variables

Most of the common techniques for estimating conditional probability densities are inappropriate for applications involving periodic variables. In this paper we introduce two novel techniques for tackling such problems, and investigate their performance using synthetic data. We then apply these techniques to the problem of extracting the distribution of wind vector directions from radar scatterometer data gathered by a remote-sensing satellite.