F. Sánchez Lasheras

Hybrid PSO–SVM-based method for forecasting of the remaining useful life for aircraft engines and evaluation of its reliability

Abstract The present paper describes a hybrid PSO–SVM-based model for the prediction of the remaining useful life of aircraft engines. The proposed hybrid model combines support vector machines (SVMs), which have been successfully adopted for regression problems, with the particle swarm optimization (PSO) technique. This optimization technique involves kernel parameter setting in the SVM training procedure, which significantly influences the regression accuracy. However, its use in reliability applications has not been yet widely explored. Bearing this in mind, remaining useful life values have been predicted here by using the hybrid PSO–SVM-based model from the remaining measured parameters (input variables) for aircraft engines with success. A coefficient of determination equal to 0.9034 was obtained when this hybrid PSO–RBF–SVM-based model was applied to experimental data. The agreement of this model with experimental data confirmed its good performance. One of the main advantages of this predictive model is that it does not require information about the previous operation states of the engine. Finally, the main conclusions of this study are exposed.

Hybrid modelling based on support vector regression with genetic algorithms in forecasting the cyanotoxins presence in the Trasona reservoir (Northern Spain).

Cyanotoxins, a kind of poisonous substances produced by cyanobacteria, are responsible for health risks in drinking and recreational waters. As a result, anticipate its presence is a matter of importance to prevent risks. The aim of this study is to use a hybrid approach based on support vector regression (SVR) in combination with genetic algorithms (GAs), known as a genetic algorithm support vector regression (GA-SVR) model, in forecasting the cyanotoxins presence in the Trasona reservoir (Northern Spain). The GA-SVR approach is aimed at highly nonlinear biological problems with sharp peaks and the tests carried out proved its high performance. Some physical-chemical parameters have been considered along with the biological ones. The results obtained are two-fold. In the first place, the significance of each biological and physical-chemical variable on the cyanotoxins presence in the reservoir is determined with success. Finally, a predictive model able to forecast the possible presence of cyanotoxins in a short term was obtained.

Open-loop tomography with artificial neural networks on CANARY: on-sky results

We present recent results from the initial testing of an artificial neural network (ANN)-based tomographic reconstructor Complex Atmospheric Reconstructor based on Machine lEarNing (CARMEN) on CANARY, an adaptive optics demonstrator operated on the 4.2m William Herschel Telescope, La Palma. The reconstructor was compared with contemporaneous data using the Learn and Apply (L&A) tomographic reconstructor. We find that the fully optimized L&A tomographic reconstructor outperforms CARMEN by approximately 5percent in Strehl ratio or 15nm rms in wavefront error. We also present results for CANARY in Ground Layer Adaptive Optics mode to show that the reconstructors are tomographic. The results are comparable and this small deficit is attributed to limitations in the training data used to build the ANN. Laboratory bench tests show that the ANN can outperform L&A under certain conditions, e.g. if the higher layer of a model two layer atmosphere was to change in altitude by ∼300m (equivalent to a shift of approximately one tenth of a subaperture).

Support Vector Machines and Multilayer Perceptron Networks Used to Evaluate the Cyanotoxins Presence from Experimental Cyanobacteria Concentrations in the Trasona Reservoir (Northern Spain)

Cyanobacteria also known as blue-green algae can be found in almost every conceivable environment. Cyanobacteria blooms occur frequently and globally in water bodies and they are a major concern in terms of their effects on other species such as plants, fish and other microorganisms, but especially by the possible acute and chronic effects on human health due to the potential danger from cyanobacterial toxins produced by some of them in recreational or drinking waters. Consequently, anticipation of cyanotoxins presence is a matter of importance to prevent risks. The aim of this study is to build a cyanotoxin diagnostic model by using support vector machines and multilayer perceptron networks from cyanobacterial concentrations determined experimentally in the Trasona reservoir (recreational reservoir used as a high performance training centre of canoeing in the Northern Spain). The results of the present study are two-fold. In the first place, the significance of each biological and physical-chemical variables on the cyanotoxins presence in the reservoir is presented through the model. Secondly, a predictive model able to forecast the possible presence of cyanotoxins is obtained. The agreement of the model with experimental data confirmed its good performance. Finally, conclusions of this innovative research work are exposed.

Artificial neural networks applied to cancer detection in a breast screening programme

Breast screening is a method of detecting breast cancer at a very early stage. The first step involves taking an X-ray, called a mammogram, of each breast. The mammogram can detect small changes in breast tissue which may indicate cancers which are too small to be felt either by the woman herself or by a doctor. The World Health Organisations International Agency for Research on Cancer (IARC) concluded that mammography screening for breast cancer reduces mortality. This means that out of every 500 women screened, one life will be saved. The present research uses the information obtained from the breast screening programme carried out in the public health area of Aviles (Principality of Asturias, Spain) from 1999 to 2007. The public health area of Aviles is formed by nine municipalities with a total of 160,000 inhabitants. The selection of the public health area was based on the following criteria: *This is the first screening programme performed in the area. *Almost 100% of the population in the area benefit from the public health system. *The Aviles public health area is a well-defined area of the region that does not send patients to other public health areas, which makes the study easier and more accurate. This paper describes a neural network based approach to breast cancer diagnosis; the model developed is able to determine which women are more likely to suffer from a particular kind of tumour before they undergo a mammography.

A new data mining methodology applied to the modelling of the influence of diet and lifestyle on the value of bone mineral density in post-menopausal women

In this work, the application of ‘multivariate adaptive regression splines’ (MARS) for modelling osteoporosis is described. This article focuses on the explanation of a new technique that combines the use of the principal components analysis (PCA) method with MARS. The use of this new technique allows for an easier management of large databases with a lower computational cost as the PCA allows the elimination of those variables that are redundant from the point of view of the phenomena under study. Osteoporosis is characterized by low ‘bone mineral density’ (BMD). This illness has a high-cost impact in all developed countries. The aim of this article is the development of a mathematical method capable of predicting the BMD of post-menopausal women, taking into account only certain nutritional variables. A nutritional habits and lifestyle questionnaire is drawn up. The variables obtained from this, together with the BMD of the patients calculated by densitometry, are processed using the ‘principal component analysis’ (PCA) algorithm in order to reduce the size of the database. Finally, the ‘MARS method’ is applied. It has been proved to be possible to build a MARS model in order to forecast the BMD of the post-menopausal women in function of their responses to the questionnaire. This model can be used to determine which women should take a densitometry.

The use of design of experiments to improve a neural network model in order to predict the thickness of the chromium layer in a hard chromium plating process

The hard chromium plating process aims at creating a coating of hard and wear-resistant chromium with a thickness of some micrometres directly on the metal part without the insertion of copper or nickel layers. Chromium plating features high levels of hardness and resistance to wear and it is due to these properties that they can be applied in a huge range of sectors. Resistance to corrosion of a hard chromium plate depends on the thickness of its coating, and its adherence and micro-fissures. This micro-fissured structure is what provides the optimal hardness of the layers. The hard chromium plating process is one of the most effective ways of protecting the base material against a hostile environment or improving the surface properties of the base material. However, in the electroplating industry, electroplaters are faced with many problems and undesirable results with chromium plated materials. Common problems faced in the electroplating industry include matt deposition, milky white chromium deposition, rough or sandy chromium deposition and insufficient thickness and hardness. This article presents an artificial neural network (ANN) model to predict the thickness of the layer in a hard chromium plating process. The optimization of the ANN was performed by means of the design of experiments theory (DOE). In the present work the purpose of using DOE is twofold: to define the optimal experiments which maximize the ratio of the model accuracy, and to minimize the number of necessary experiments (ANN models trained and validated).

Study of cyanotoxins presence from experimental cyanobacteria concentrations using a new data mining methodology based on multivariate adaptive regression splines in Trasona reservoir (Northern Spain).

There is an increasing need to describe cyanobacteria blooms since some cyanobacteria produce toxins, termed cyanotoxins. These latter can be toxic and dangerous to humans as well as other animals and life in general. It must be remarked that the cyanobacteria are reproduced explosively under certain conditions. This results in algae blooms, which can become harmful to other species if the cyanobacteria involved produce cyanotoxins. In this research work, the evolution of cyanotoxins in Trasona reservoir (Principality of Asturias, Northern Spain) was studied with success using the data mining methodology based on multivariate adaptive regression splines (MARS) technique. The results of the present study are two-fold. On one hand, the importance of the different kind of cyanobacteria over the presence of cyanotoxins in the reservoir is presented through the MARS model and on the other hand a predictive model able to forecast the possible presence of cyanotoxins in a short term was obtained. The agreement of the MARS model with experimental data confirmed the good performance of the same one. Finally, conclusions of this innovative research are exposed.

A new improved study of cyanotoxins presence from experimental cyanobacteria concentrations in the Trasona reservoir (Northern Spain) using the MARS technique

Cyanotoxins, a kind of poisonous substances produced by cyanobacteria, are responsible for health risks in drinking and recreational water uses. The aim of this study is to improve our previous and successful work about cyanotoxins prediction from some experimental cyanobacteria concentrations in the Trasona reservoir (Asturias, Northern Spain) using the multivariate adaptive regression splines (MARS) technique at a local scale. In fact, this new improvement consists of using not only biological variables, but also the physical-chemical ones. As a result, the coefficient of determination has improved from 0.84 to 0.94, that is to say, more accurate predictive calculations and a better approximation to the real problem were obtained. Finally the agreement of the MARS model with experimental data confirmed the good performance.

Using multivariate adaptive regression splines and multilayer perceptron networks to evaluate paper manufactured using Eucalyptus globulus

Abstract Using advanced machine learning techniques as an alternative to conventional double-entry volume equations known as classical allometric models , regression models of the inside-bark volume (dependent variable) for standing Eucalyptus globulus trunks (or main stems) have been built as a function of the following three independent variables: age, height and outside-bark diameter at breast height ( D ). The allometric models of volume, biomass or carbon support the estimation of carbon storage in forests and agroforestry systems. On one hand, this paper presents the construction of allometric models of the inside-bark volume for E. globulus trees. On the other hand, the experimental observed data (age, height, D and inside-bark volume) for 142 trees ( E. globulus ) were measured and a nonlinear model was built using a data-mining methodology based on multivariate adaptive regression splines (MARS) technique and multilayer perceptron networks (MLP) for regression problems. Coefficients of determination and Furnival’s indices indicate the superiority of the MARS technique over the allometric regression models and the MLP network. The agreement of the MARS model with observed data confirmed the good performance of the same one. Finally, conclusions of this innovative research are exposed.