Addisson Salazar

Universitat Politècnica de València | UPV · Institute of Telecommunications and Multimedia Applications (iTEAM)

In this paper, a theoretical learning curve is derived for the multi-class Bayes classifier. This curve fits general multivariate parametric models of the class-conditional probability density. The derivation uses a proxy approach based on analyzing the convergence of a statistic which is proportional to the posterior probability of the true class....

It is demonstrated that data augmentation is a promising approach to reduce the size of the captured dataset required for training automatic road surface classifiers. The context is on-board systems for autonomous or semi-autonomous driving assistance: automatic power-assisted steering. Evidence is obtained by extensive experiments involving multip...

Purpose-This research aims to study the effect of R&D (research and development) enablers and barriers as well as industrial property on exploration, their influence on exploitation and finally the possible impact on innovative outcome (IO) as a result variable. The IO can be defined as the orientation towards new or improved products, services and...

Purpose – This research aims to study the effect of R&D (research and development) enablers and barriers as well as industrial property on exploration, their influence on exploitation and finally the possible impact on innovative outcome (IO) as a result variable. The IO can be defined as the orientation towards new or improved products, services a...

This work presents in detail a new method for the optimization of rectangular spread spectrum excitation signals for its use in simple and low-cost ultrasonic pulsers, but that could be extended to other applications based on spread spectrum signals. Starting from rectangular linear frequency modulated (RLFM) chirps, it uses the transfer function o...

Purpose This research aims to study the effect of R&D (research and development) enablers and barriers as well as industrial property on exploration, their influence on exploitation and finally the possible impact on innovative outcome (IO) as a result variable. The IO can be defined as the orientation towards new or improved products, services and...

Innovative remote sensing image processing techniques have been progressively studied due to the increasing availability of remote sensing images, powerful techniques of data analysis, and computational power [...]

This paper presents a new detector method based on alpha integration decision fusion. The detector incorporates a regularization element in the cost function. This element is considered a measure of the smoothness of the signal in graph signal processing. We theorize that minimizing this term will reduce the dispersion of the statistics of the fusi...

Many tasks in hyperspectral imaging, such as spectral unmixing and sub-pixel matching, require knowing how many substances or materials are present in the scene captured by a hyperspectral image. In this paper, we present an algorithm that estimates the number of materials in the scene using agglomerative clustering. The algorithm is based on the a...

In this work, we propose a new method for oversampling the training set of a classifier, in a scenario of extreme scarcity of training data. It is based on two concepts: Generative Adversarial Networks (GAN) and vector Markov Random Field (vMRF). Thus, the generative block of GAN uses the vMRF model to synthesize surrogates by the Graph Fourier Tra...

This paper presents a novel method for detection of frauds that uses the differences in temporal dependence (sequential patterns) between valid and non-legitimate credit card operations to increase the detection performance. A two-level fusion is proposed from the results of single classifiers. The first fusion is made in low-dimension feature spac...

Road surface identification is attracting more attention in recent years as part of the development of autonomous vehicle technologies. Most works consider multiple sensors and many features in order to produce a more reliable and robust result. However, on-board limitations and generalization concerns dictate the need for dimensionality reduction...

Alpha integration is a family of integrators that encompasses many classic fusion operators (e.g., mean, product, minimum, maximum) as particular cases. This paper proposes vector score integration (VSI), a new alpha integration method for late fusion of multiple classifiers considering the joint effect of all the classes of the multi-class problem...

This paper presents a novel application of pattern recognition to the provenance classification of archaeological ceramics. This is a challenging problem for archaeologists, which involves assigning a making location to a fragment of archaeological pottery that was found along with other fragments of pieces made in different distant locations from...

The essential step of surrogating algorithms is phase randomizing the Fourier transform while preserving the original spectrum amplitude before computing the inverse Fourier transform. In this paper, we propose a new method which considers the graph Fourier transform. In this manner, much more flexibility is gained to define properties of the origi...

In this paper, we present the optimization and parallelization of a state-of-the-art algorithm for automatic classification, in order to perform real-time classification of clinical data. The parallelization has been carried out so that the algorithm can be used in real time in standard computers, or in high performance computing servers. The faste...

This work introduces vector score integration (VSI), a novel alpha integration method to perform soft fusion of scores in K-class classification problems. The parameters of the method are optimized to achieve the least mean squared error between the fused scores and the ideal scores over a set of training data. VSI was applied to perform soft fusio...

This paper presents a new measure of brain connectivity based on graphs. The method to estimate connectivity is derived from the set of transition matrices obtained by multichannel hidden Markov modeling and graph connectivity theory. Analysis of electroencephalographic signals from epileptic patients performing neuropsychological tests with visual...

This paper presents a novel method that combines coupled hidden Markov models (HMM) and non-Gaussian mixture models based on independent component analyzer mixture models (ICAMM). The proposed method models the joint behavior of a number of synchronized sequential independent component analyzer mixture models (SICAMM), thus we have named it general...

Alpha integration methods have been used for integrating stochastic models and fusion in the context of detection (binary classification). Our work proposes separated score integration (SSI), a new method based on alpha integration to perform soft fusion of scores in multiclass classification problems, one of the most common problems in automatic c...

Automatic credit card fraud detection (ACCFD) is a challenge issue that has been increasingly studied considering the expanded potential of new technologies to emulate legitimate operations. Solution has to handle changing fraud behavior, detection in data with very small fraud/legitimate operations ratio, and accomplish operation requirements of v...

Conventional partial correlation coefficients (PCC) were extended to the non-Gaussian case, in particular to independent component analysis (ICA) models of the observed multivariate samples. Thus, the usual methods that define the pairwise connections of a graph from the precision matrix were correspondingly extended. The basic concept involved rep...

The main aim of this study is to establish the effect of the Exploitation and Exploration; and the influence of these learning flows on the Innovative Outcome (IO). The Innovative Outcome refers to new products, services, processes (or improvements) that the organization has obtained as a result of an innovative process. For this purpose, a relatio...

Independent Component Analyzers Mixture Models (ICAMM) are versatile and general models for a large variety of probability density functions. In this paper we assume ICAMM to derive new MAP and LMSE estimators. The first one (MAP-ICAMM) is obtained by an iterative gradient algorithm, while the second (LMSE-ICAMM) admits a closed-form solution. Both...

Recent works in signal processing on graphs have been driven to estimate the precision matrix and to use it as the graph Laplacian matrix. The normalized elements of the precision matrix are the partial correlation coefficients which measure the pairwise conditional linear dependencies of the graph. However, the non-linear dependencies inherent in...

One of the most difficult constraints in machine learning is to have enough data for an adequate training of the methods. The amount of knowledge about the labels for grouping data in significant populations mostly determines the success in pattern recognition for several applications. However, labeling could be costly due to several issues, e.g.,...

This paper presents a novel method for modeling the joint behavior of a number of synchronized Independent Component Analysis Mixture Models (ICAMM), which we have named Multi-chain ICAMM (MCICAMM). This allows flexible estimation of complex densities of data, subspace classification, blind source separation, accurate local dynamic learning, and gl...

Independent Component Analyzers Mixture Models (ICAMM) are versatile and general models for a large variety of probability density functions. In this paper, we assume ICAMM to derive a closed-form solution to the optimal Least Mean Squared Error predictor, which we have named E-ICAMM. The new predictor is compared with four classical alternatives (...

Independent component analysis (ICA) is a blind source separation technique where data are modeled as linear combinations of several independent non-Gaussian sources. The independence and linear restrictions are relaxed using several ICA mixture models (ICAMMs) obtaining a two-layer artificial neural network structure. This allows for dependence be...

In this paper we present a new method to obtain the density of solid composites using ultrasound. The method exploits the relation between density and acoustic impedance and only requires the measurement of a reference signal form the interface water-air. Once made in a controlled environment, it can be used for any material, and does not require a...

Independence between detectors is normally assumed in order to simplify the algorithms and techniques used in decision fusion. In this paper, we derive the optimum fusion rule of N non-independent detectors in terms of the individual probabilities of detection and false alarm and defined dependence factors. This has interest for the implementation...

We present a new method for fusing scores corresponding to different detectors (two-hypotheses case). It is based on alpha integration, which we have adapted to the detection context. Three optimization methods are presented: least mean square error, maximization of the area under the ROC curve, and minimization of the probability of error. Gradien...

The detection and identification of internal defects in a material require the use of some technology that translates the hidden interior damages into observable signals with different signature-defect correspondences. We apply impact-echo techniques for this purpose. The materials are classified according to their defective status (homogeneous, on...

In this work, we have studied the Autonomous Nervous System (ANS) sympathovagal balance during a test period using the LF signal variance to the HF signal variance ratio. To compute, more accurately, these variances of the LF and HF temporal signals, we have extracted the latter from the heart rate variability signal (HRV) using wavelet packet db4,...

The Autonomous Nervous System (ANS) sympathovagal balance was studied using several features derived from Heart Rate Variability signals (HRV). The HRV signals are, however naturally, non-stationary since their statistical properties vary under time transition. A useful approach to quantifying them is, therefore, to consider them as consisting of s...

We tackle the parallelization of Non-Negative Matrix Factorization (NNMF), using the Alternating Least Squares and Lee and Seung algorithms, motivated by its use in audio source separation. For the first algorithm, a very suitable technique is the use of active set algorithms for solving several non-negative inequality constraints least squares pro...

Banks collect large amount of historical records corresponding to millions of credit cards operations, but, unfortunately, only a small portion, if any, is open access. This is because, e.g., the records include confidential customer data and banks are afraid of public quantitative evidence of existing fraud operations. This paper tackles this prob...

A new method for the automatic and simultaneous measurement of phase velocity and thickness for thin composite plates was developed based on Ping He׳s method, without any need of a priori knowledge of the material parameters. Two composites were analyzed: a block of clean epoxy and a thin specimen of glass–fiber reinforced plastic produced by resin...

This paper presents a method for estimation of consolidation profiles for archaeological ceramics that uses an ultrasonic signature. The consolidation process consists in injecting a material in the ceramic to preserve it from damage. The signature consists of a set of features extracted from an ultrasonic signal that is recorded in through-transmi...

The aim of this work is the design of an automatic method for Steel Fiber Reinforce Concrete imaging and characterization. We present a new procedure that combines iterative deconvolution with time-to-frequency analysis to obtain simultaneously the thickness and speed of sound of the specimen. It can also detect the steel wires inside the structure...

Missing traces in ground penetrating radar (GPR) B-scans (radargrams) may appear because of limited scanning resolution, failures during the acquisition process or the lack of accessibility to some areas under test. Four statistical interpolation methods for recovering these missing traces are compared in this paper: Kriging, Wiener structures, Spl...

This paper presents a novel procedure to classify materials with different defects, such as holes or cracks, from mixtures of independent component analyzers. The data correspond to the ultrasonic echo recorded after an impact by several sensors on the surface of the material. These signals are modelled by independent component analysis mixture mod...

This chapter presents an experimental sensitivity study of several dynamic modeling methods applied to simulated scenarios and electroencephalographic (EEG) signal processing. The studied methods are the following: Dynamic Bayesian Networks (DBN, using Gaussian-mixture- models-GMM) and Sequential Independent Component Analysis Mixture Modeling (SIC...

This paper presents a study of the application of new variants of the Sequential Independent Analysis Mixture Models (SICAMM) to the modeling and classification of electroencephalographic (EEG) signals. The real application approached was the detection of microarousals in EEG signals from sleep apnea patients. In addition, the proposed methods were...

Much of heritage buildings are made of stone, mortar or brick, and degradation processes are inevitable. Due to historical and cultural value, non-destructive evaluation techniques (NDE) are essential for the assessment and restoration tasks. In this work, we study the capability of ultrasonic to detect fissures and to determine the degree of conso...

This paper presents a method for assessment of historic structures based on the fusion of data from ground-penetrating radar (GPR), ultrasound, and impact-echo testing. The method consists of the following steps: measuring, feature extraction, fusion, representation, and evaluation. The employed techniques for an application in scale models of hist...

This chapter presents two diverse applications: diagnosis of sleep disorders (apnea) and data mining in a web of a virtual campus. The first application presents a procedure to extend ICA mixture models (ICAMM) to the case of having sequential dependence in the feature observation record. We call it sequential ICAMM (SICAMM). We present the algorit...

Independent component analysis (ICA) aims to separate hidden sources from their observed linear mixtures without any prior knowledge. The only assumption about the sources is that they are mutually independent. Thus, the goal is blind source estimation; although it has been recently alleviated by incorporating prior knowledge about the sources into...

In this chapter, we present a procedure for clustering (unsupervised learning) data from a model based on mixtures of independent component analyzers. Clustering techniques have been extensively studied in many different fields for a long time. They can be organized in different ways according to several theoretical criteria. However, a rough widel...

Having information about the condition of a material is an important issue for many industries. This is especially valued if the applied procedure is not time-consuming and is easy to employ in the production line. This is the case of the so-called impact-echo method, which is simply based on making an impact in the material being analyzed. Neverth...

This chapter presents a new procedure for learning mixtures of independent component analyzers. The procedure includes non-parametric estimation of the source densities, supervised–unsupervised learning of the model parameters, incorporation of any independent component analysis (ICA) algorithm into the learning of the ICA mixtures, and estimation...

This chapter presents two applications: classification of archaeological ceramics and diagnosis of historic building restoration. In the first application, we consider the ICAMM-based algorithm proposed in Chap. 3 (Mixca) to model the joint-probability density of the features. This classifier is applied to a challenging novel application: classific...

Independent Component Analysis (ICA) is a blind source separation method that has proven popular in many fields of application. ICA can be improved incorporating temporal dependencies creating dynamic ICA methods and defining subspaces with multiple ICAs. Such a dynamic ICA method is called Sequential Independent Component Analysis Mixture Model (S...

This paper presents an application of ultrasounds and ground-penetrating radar (GPR) for analysis of historic walls. The objectives are to characterize the deformation of a historic wall under different levels of load weights and to obtain an enhanced image of the wall. A new method that fuses data from ultrasound and GPR traces is proposed which i...

The different structures of the brain of human beings produce spontaneous electroencephalographic (EEG) records that can be used to identify subjects. This paper presents a method for biometric authorization and identification based on EEG signals. The hardware uses a simple 2-signal electrode and a reference electrode configuration. The electrodes...

Fraud detection is a critical problem affecting large financial companies that has increased due to the growth in credit card transactions. This paper presents a new method for automatic detection of frauds in credit card transactions based on non-linear signal processing. The proposed method consists of the following stages: feature extraction, tr...

In this paper we study the problem of automatic detection of ultrasonic echo pulses in a grain noise background considering split-spectrum (SS) algorithms as sub-optimum solutions. First, SS algorithms are reformulated following an algebraic approach which is more appropriate from the perspective of automatic detection. Then, recombination methods...

A detection problem, where we have a set of two types of different measurements or modalities of one event, is considered. The optimal fusion rule to combine both modalities in one detector needs the knowledge of the joint statistics of modalities. In many cases we do not know these joint statistics and it is usual to consider independence between...

This paper presents a prospective analysis of non destructive testing (NDT) based on ultrasounds in the field of archaeology applications. Classical applications of ultrasounds techniques are reviewed, including ocean exploration to detect wrecks, imaging of archaeological sites, and cleaning archaeological objects. The potential of prospective app...

In this paper the performance of Split-Spectrum Processing algorithms combined with Spread Spectrum excitation for ultrasonic imaging of new composites were analyzed. Glass and carbon fiber reinforced plastic produced by Resin Transfer Molding (RTM) were the analyzed specimens. These materials are strongly affected by structural noise since air bub...

This paper presents a new application of independent component analysis mixture modeling (ICAMM) for prediction of electroencephalographic (EEG) signals. Demonstrations in prediction of missing EEG data in a working memory task using classic methods and an ICAMM-based algorithm are included. The performance of the methods is measured by using four...

A natural evolution of statistical signal processing, in connection with the progressive increase in computational power, has been exploiting higher-order information. Thus, high-order spectral analysis and nonlinear adaptive filtering have received the attention of many researchers. One of the most successful techniques for non-linear processing o...