Esteban García-Cuesta

User modeling: Through statistical analysis and subspace learning

One of the challenges which must be faced in the field of the information processing is the need to cope with huge amounts of data. There exist many different environments in which large quantities of information are produced. For example, in a command-line interface, a computer user types thousands of commands which can hide information about the behavior of her/his. However, processing this kind of streaming data on-line is a hard problem. This paper addresses the problem of the classification of streaming data from a dimensionality reduction perspective. We propose to learn a lower dimensionality input model which best represents the data and improves the prediction performance versus standard techniques. The proposed method uses maximum dependence criteria as distance measurement and finds the transformation which best represents the command-line user. We also make a comparison between the dimensionality reduction approach and using the full dataset. The results obtained give some deeper understanding in advantages and drawbacks of using both perspectives in this user classifying environment.

Multilayer perceptron as inverse model in a ground-based remote sensing temperature retrieval problem

In this paper, a combustion temperature retrieval approximation for high-resolution infrared ground-based measurements has been developed based on a multilayer perceptron (MLP) technique. The introduction of a selection subset of features is mandatory due to the problems related to the high dimensionality data and the worse performance of MLPs with this high input dimensionality. Principal component analysis is used to reduce the input data dimensionality, selecting the physically important features in order to improve MLP performance. The use of a priori physical information over other methods in the chosen features phase has been tested and has appeared jointly with the MLP technique as a good alternative for this problem.

Temperature Profile Retrieval in Axisymmetric Combustion Plumes Using Multilayer Perceptron Modeling and Spectral Feature Selection in the Infrared CO2 Emission Band

In this work, a methodology based on the combined use of a multilayer perceptron model fed using selected spectral information is presented to invert the radiative transfer equation (RTE) and to recover the spatial temperature profile inside an axisymmetric flame. The spectral information is provided by the measurement of the infrared CO2 emission band in the 3–5 μm spectral region. A guided spectral feature selection was carried out using a joint criterion of principal component analysis and a priori physical knowledge of the radiative problem. After applying this guided feature selection, a subset of 17 wavenumbers was selected. The proposed methodology was applied over synthetic scenarios. Also, an experimental validation was carried out by measuring the spectral emission of the exhaust hot gas plume in a microjet engine with a Fourier transform-based spectroradiometer. Temperatures retrieved using the proposed methodology were compared with classical thermocouple measurements, showing a good agreement between them. Results obtained using the proposed methodology are very promising and can encourage the use of sensor systems based on the spectral measurement of the CO2 emission band in the 3–5 μm spectral window to monitor combustion processes in a nonintrusive way.

RECURSIVE DISCRIMINANT REGRESSION ANALYSIS TO FIND HOMOGENEOUS GROUPS

The main motivation of this paper is to propose a method to extract the output structure and find the input data manifold that best represents that output structure in a multivariate regression problem. A graph similarity viewpoint is used to develop an algorithm based on LDA, and to find out different output models which are learned as an input subspace. The main novelty of the algorithm is related with finding different structured groups and apply different models to fit better those structures. Finally, the proposed method is applied to a real remote sensing retrieval problem where we want to recover the physical parameters from a spectrum of energy.

Spectral high resolution feature selection for retrieval of combustion temperature profiles

The use of high spectral resolution measurements to obtain a retrieval of certain physical properties related with the radiative transfer of energy leads a priori to a better accuracy. But this improvement in accuracy is not easy to achieve due to the great amount of data which makes difficult any treatment over it and it’s redundancies. To solve this problem, a pick selection based on principal component analysis has been adopted in order to make the mandatory feature selection over the different channels. In this paper, the capability to retrieve the temperature profile in a combustion environment using neural networks jointly with this spectral high resolution feature selection method is studied.

Neural Networks and Spectral Feature Selection for Retrieval of Hot Gases Temperature Profiles

Neural networks appear to be a promising tool to solve the so-called inverse problems focused to obtain a retrieval of certain physical properties related to the radiative transference of energy. In this paper the capability of neural networks to retrieve the temperature profile in a combustion environment is proposed. Temperature profile retrieval will be obtained from the measurement of the spectral distribution of energy radiated by the hot gases (combustion products) at wavelengths corresponding to the infrared region. High spectral resolution is usually needed to gain a certain accuracy in the retrieval process. However, this great amount of information makes mandatory a reduction of the dimensionality of the problem. In this sense a careful selection of wavelengths in the spectrum must be performed. With this purpose principal component analysis technique is used to automatically determine those wavelengths in the spectrum that carry relevant information on temperature distribution. A multilayer perceptron will be trained with the different energies associated to the selected wavelengths. The results presented show that multilayer perceptron combined with principal component analysis is a suitable alternative in this field

Supervised clustering via principal component analysis in a retrieval application

In regression problems where the number of predictors exceeds the number of observations and the correlation between the predictors is high, a dimensionality reduction or a variable selection approach is demanded. In this paper we deal with a real application where we want to retrieve the physical characteristics of a combustion process from the measurements obtained with a spectroscopic sensor. This application shows up a multicollinearity problem but furthermore it is considered an ill-posed problem. Guided by this application scenario, we propose a clustering approach to find out homogeneous subsets of data which are embedded in arbitrary oriented linear manifold. This model is developed under certain assumptions guided by a priori problem knowledge. The resulting division preserves both, the priori assumptions and the homogeneity in the models. Thereby we break the whole problem in n subproblems improving its individual prediction accuracy versus a global solution. We show the obtained improvements in a real application scenario related with estimating the temperature from spectroscopic data in a remote sensing framework.

Discriminant regression analysis to find homogeneous structures

The main motivation of this paper is to propose a method to extract the structure information from the output data and find the input data manifold that best represents that output structure. A graph similarity viewpoint is used to build up a clustering algorithm that tries to find out different linear models in a regression framework. The main novelty of the algorithm is related with using the structured information of the output data, to find out several input models that best represent that structure. This novelty is base on the intuition that similar structures in the output must share a common model. Finally, the proposed method is applied to a real remote sensing retrieval problem where we want to recover the physical parameters from a spectrum of energy.

Machine Learning Approaches for the Inversion of the Radiative Transfer Equation

Estimation of the constituents of a gas (e.g. temperature, concentration) from high resolution spectroscopic measurements is a fundamental step to con- trol and improve the efficiency of combustion processes governed by the Radiative Transfer Equation (RTE). Typically such estimation is performed using thermocou- ples; however, these sensors are intrusive and must undergo the harsh furnace envi- ronment. In this paper, we follow a machine learning approach to learn the relation between the spectroscopic measurements and gas constituents such as temperature, concentration and length. This is a challenging problem due to the non-linear behav- ior of the RTE and the high dimensional data obtained from sensor measurements. We perform a comparative study of linear and neural network regression models, using canonical correlation analysis (CCA), principal component analysis (PCA), reduced rank regression (RRR), and kernel canonical correlation (KCCA) to reduce the dimensionality.

Quantitative analysis of open-path FTIR spectra by using artificial neural networks

Quantitative analysis of absorbance spectra to retrieve gas concentrations in open-path FTIR air monitoring is not always a straightforward task. Most of commercial software use classical-least-squared algorithms to retrieve the unknown concentrations. These codes usually work in real time and give appropriate results. However, sometimes these codes fail when the background reference spectrum presents absorption lines of the gas to be monitorized. This effect is frequent in some applications. Line-by-line approaches give satisfactory results because these codes solve the problem associated to the reference spectrum generating a synthetic reference background. The main drawback is that these algorithms do not work in real time, and need a skilled operator. In this work, we propose the use of artificial neural networks to analyze absorbance spectra in real time to retrieve the unknown concentrations in a simultaneous way. In addition, capabilities of the method to solve spectral overlapping will be studied. In this sense, simultaneous analysis of four atmospheric gases (CO2, CO, H2O and N2O) will be included in this first version. The effectiveness of the method will be evaluated from the experimental point of view. Experimental open-path FTIR spectra (0.5 cm-1 of spectral resolution) will be analyzed with the proposed method, as well as with CLS and LBL codes for comparison purposes. Moreover, in these experiments CO concentration has been measured by using standard extractive equipment and can be compared with the values provided by our method. Finally, some indications will be pointed to extend the method to other gases and spectral regions.