Rene Alquezar | Universitat Politecnica de Catalunya (original) (raw)

Papers by Rene Alquezar

Interdisciplinary sciences, computational life sciences, 2018

G-protein-coupled receptors (GPCRs) are a large and diverse super-family of eukaryotic cell membr... more G-protein-coupled receptors (GPCRs) are a large and diverse super-family of eukaryotic cell membrane proteins that play an important physiological role as transmitters of extracellular signal. In this paper, we investigate Class C, a member of this super-family that has attracted much attention in pharmacology. The limited knowledge about the complete 3D crystal structure of Class C receptors makes necessary the use of their primary amino acid sequences for analytical purposes. Here, we provide a systematic analysis of distinct receptor sequence segments with regard to their ability to differentiate between seven class C GPCR subtypes according to their topological location in the extracellular, transmembrane, or intracellular domains. We build on the results from the previous research that provided preliminary evidence of the potential use of separated domains of complete class C GPCR sequences as the basis for subtype classification. The use of the extracellular N-terminus domain ...

Neurocomputing, Aug 1, 2006

An algorithm for sequential approximation with optimal coefficients and interacting frequencies (... more An algorithm for sequential approximation with optimal coefficients and interacting frequencies (SAOCIF) for feed-forward neural networks is presented. SAOCIF combines two key ideas. The first one is the optimization of the coefficients (the linear part of the approximation). The second one is the strategy to choose the frequencies (the non-linear weights), taking into account the interactions with the previously selected ones. The resulting method combines the locality of sequential approximations, where only one frequency is found at every step, with the globality of non-sequential methods, where every frequency interacts with the others. The idea behind SAOCIF can be theoretically extended to general Hilbert spaces. Experimental results show a very satisfactory performance.

Proceedings 15th International Conference on Pattern Recognition Icpr 2000, 2000

Function-Described Graphs (FDGs) have been introduced by the authors as a representation of an en... more Function-Described Graphs (FDGs) have been introduced by the authors as a representation of an ensemble of Attributed Graphs (AGs) for structural pattern recognition alternative to first-order random graphs. In previous works, algorithms for the synthesis of FDGs and a branch-and-bound algorithm for errortolerant graph matching, which computes a distance measure between AGs and FDG, have been reported. Since the worst-case complexity of that matching algorithm is exponential in the number of nodes, an approximate algorithm to compute a sub-optimal measure is proposed in this paper. Results in 3D-object recognition show that, although the computational time is reduced, there is only a slight decrease of effectiveness while classifying an AG against a set of FDGs.

Marco is the name of a research mobile robot that is being developed at the In- stituto de Robóti... more Marco is the name of a research mobile robot that is being developed at the In- stituto de Robótica e Infomática Industrial of UPC-CSIC. It is designed with learn- ing abilities to acquire information about indoor environments using various percep- tion sensors. Marco uses video cameras and ultrasonic sensors to perceive the world, and pattern recognition and computer vision techniques

The prediction of ozone levels is an important task because this toxic gas can produce harmful ef... more The prediction of ozone levels is an important task because this toxic gas can produce harmful effects to the population health especially of children. This article describes the application of the Fuzzy Inductive Reasoning methodology and a Recurrent Neural Network (RNN) approach, the Long Short Term Memory (LSTM) architecture, to a signal forecasting task in an environmental domain. More specifically,

In order to extend the potential of application of the syntactic approach to pattern recognition,... more In order to extend the potential of application of the syntactic approach to pattern recognition, the e cient use of models capable of describing context-sensitive structural relationships is needed. Moreover, the ability to learn such models from examples is interesting to automate as much as possible the development of applications. In this paper, a new formalism that permits to describe a non-trivial class of context-sensitive languages, the Augmented Regular Expressions (AREs), is introduced. AREs augment the descriptive power of regular expressions by including a set of constraints that involve the number of instances of the operands of the star operations in each string of the language. Likewise, algorithms are given to infer AREs from string examples and to recognize language strings by AREs. The method for learning AREs consists of a regular grammatical inference step, aimed at obtaining a regular superset of the target language, followed by a constraint induction process, which reduces the extension of the inferred language transforming it into a context-sensitive one. Hence, this two-step approach avoids the di culty of learning context-sensitive grammars directly from the data. The method for recognizing language strings is also splitted in two stages: matching the underlying regular expression and checking that the resulting star instances satisfy the constraints.

Page 1. Local Maximum Ozone Concentration Prediction Using LSTM Recurrent Neural Networks Sabrine... more Page 1. Local Maximum Ozone Concentration Prediction Using LSTM Recurrent Neural Networks Sabrine Ribeiro René Alquézar Dept. Llenguatges i Sistemes Inform`atics Universitat Polit`ecnica de Catalunya Campus Nord ...

Proceedings of the 2009 Conference on Artificial Intelligence Research and Development Proceedings of the 12th International Conference of the Catalan Association For Artificial Intelligence, Jul 22, 2009

Google, Inc. (search), Subscribe (Full Service), Register (Limited Service, Free), Login. Search:... more Google, Inc. (search), Subscribe (Full Service), Register (Limited Service, Free), Login. Search: The ACM Digital Library The Guide. ...

PLOS ONE, 2016

We present a novel approach for feature correspondence and multiple structure discovery in comput... more We present a novel approach for feature correspondence and multiple structure discovery in computer vision. In contrast to existing methods, we exploit the fact that point-sets on the same structure usually lie close to each other, thus forming clusters in the image. Given a pair of input images, we initially extract points of interest and extract hierarchical representations by agglomerative clustering. We use the maximum weighted clique problem to find the set of corresponding clusters with maximum number of inliers representing the multiple structures at the correct scales. Our method is parameter-free and only needs two sets of points along with their tentative correspondences, thus being extremely easy to use. We demonstrate the effectiveness of our method in multiple-structure fitting experiments in both publicly available and in-house datasets. As shown in the experiments, our approach finds a higher number of structures containing fewer outliers compared to state-of-the-art methods.

BMC Bioinformatics, 2015

Background: The characterization of proteins in families and subfamilies, at different levels, en... more Background: The characterization of proteins in families and subfamilies, at different levels, entails the definition and use of class labels. When the adscription of a protein to a family is uncertain, or even wrong, this becomes an instance of what has come to be known as a label noise problem. Label noise has a potentially negative effect on any quantitative analysis of proteins that depends on label information. This study investigates class C of G protein-coupled receptors, which are cell membrane proteins of relevance both to biology in general and pharmacology in particular. Their supervised classification into different known subtypes, based on primary sequence data, is hampered by label noise. The latter may stem from a combination of expert knowledge limitations and the lack of a clear correspondence between labels that mostly reflect GPCR functionality and the different representations of the protein primary sequences. Results: In this study, we describe a systematic approach, using Support Vector Machine classifiers, to the analysis of G protein-coupled receptor misclassifications. As a proof of concept, this approach is used to assist the discovery of labeling quality problems in a curated, publicly accessible database of this type of proteins. We also investigate the extent to which physico-chemical transformations of the protein sequences reflect G protein-coupled receptor subtype labeling. The candidate mislabeled cases detected with this approach are externally validated with phylogenetic trees and against further trusted sources such as the

En este trabajo se describen los principales pasos de un nuevo método para lograr la reconstrucci... more En este trabajo se describen los principales pasos de un nuevo método para lograr la reconstrucción de la superficie que limita el material de interés de un objeto a partir de las secciones transversales paralelas que lo conforman. Dicho método constituye la extensión de uno anteriormente propuesto por los autores, que utiliza el esqueleto para dar solución al problema de investigación. El método garantiza la correcta topología de la superficie sin alterar los contornos originales. Se muestran los resultados de su aplicación en ejemplos con alto grado de complejidad. Todos los casos analizados, incluyendo uno no tratado por otros autores consultados, se logran manipular de igual manera. En casos reales, la complejidad computacional global mejora el tiempo cuadrático de los más rápidos métodos consultados.

RESUMEN La reconstrucción de superficies a partir de secciones planas paralelas es un importante ... more RESUMEN La reconstrucción de superficies a partir de secciones planas paralelas es un importante problema que encuentra aplicación en el procesamiento de imágenes médicas y otras aplicaciones de modelado de objetos. En este trabajo se muestran resultados experimentales de la aplicación de un nuevo método para darle solución a este problema. El método propuesto está basado en el uso del esqueleto (concepto del procesamiento de imágenes). Se comparan los resultados del método propuesto con los principales reportados por la literatura. Se muestran los resultados tanto en ejemplos sintéticos como en imágenes médicas reales. Palabras clave: reconstrucción de superficies, secciones paralelas.

A new method to solve the branching problem in surfaces of three-dimensional (3D) models reconstr... more A new method to solve the branching problem in surfaces of three-dimensional (3D) models reconstructed from parallel cross sections is presented in this paper. This is an important problem in medical imaging and others object-modeling applications, where the reconstruction of the surface of 3D models from images that represent a set of parallel planes is of interest. The proposed method is based on the skeletonization technique to create new contours, corresponding to an artificial intermediate slice that models the level where branching occurs. Some experimental results of the application of the proposed method to solve the branching problem on synthetic complex examples and actual medical imaging data are showed.

International Journal of Pattern Recognition and Artificial Intelligence, 2004

The aim of this article is to present a random graph representation, that is based on second-orde... more The aim of this article is to present a random graph representation, that is based on second-order relations between graph elements, for modeling sets of attributed graphs (AGs). We refer to these models as Second-Order Random Graphs (SORGs). The basic feature of SORGs is that they include both marginal probability functions of graph elements and second-order joint probability functions. This allows a more precise description of both the structural and semantic information contents in a set of AGs and, consequently, an expected improvement in graph matching and object recognition. The article presents a probabilistic formulation of SORGs that includes as particular cases the two previously proposed approaches based on random graphs, namely the First-Order Random Graphs (FORGs) and the Function-Described Graphs (FDGs). We then propose a distance measure derived from the probability of instantiating a SORG into an AG and an incremental procedure to synthesize SORGs from sequences of A...

Object recognition supported by user interaction for service robots, 2002

In this paper we study the application of Function-Described Graphs (FDGs) for 3D-object modeling... more In this paper we study the application of Function-Described Graphs (FDGs) for 3D-object modeling and recognition. From a set of topological different 2D-views taken of an object, FDGs are synthesized from the attributed adjacency graphs that are extracted for each view. It is shown that, by keeping in the object representation (an FDG) a qualitative information of the 2 nd-order joint probabilities between vertices, the object recognition ratio increases while the run time of the classification process decreases.

Lecture Notes in Computer Science, 1994

Recently, recurrent neural networks (RNNs) have been used to infer regular grammars from positive... more Recently, recurrent neural networks (RNNs) have been used to infer regular grammars from positive and negative examples. Several clustering algorithms have been suggested to extract a nite state automaton (FSA) from the activation patterns of a trained net. However, the consistency with the examples of the extracted FSA is not guaranteed in these methods, and typically, some parameter of the clustering algorithm must be set arbitrarily (e.g. the number of clusters in kmeans method). In this paper we present a hybrid approach to regular grammatical inference based on neural learning and hierarchical clustering. The important new feature in the proposed method is the use of symbolic representation (unbiased FSA) and processing (merge operation) along with the clustering performed after neural learning, which allows to guarantee the extraction of a consistent deterministic FSA with the "minimal" size (with respect to the consistent FSA extractable by hierarchical clustering). Moreover, it is only required to de ne the cluster distance measure criterion.