http://hdl.handle.net/2117/3686 Sat, 25 May 2013 11:21:50 GMT 2013-05-25T11:21:50Z webmaster.bupc@upc.edu Universitat Politècnica de Catalunya. Servei de Biblioteques i Documentació no http://hdl.handle.net/2117/18837 Title: Group-wise sparse correspondences between images based on a common labelling approach Authors: Solé Ribalta, Albert; Sanromà Güell, Gerard; Serratosa Casanelles, Francesc; Alquézar Mancho, René Abstract: Finding sparse correspondences between two images is a usual process needed for several higher-level computer vision tasks. For instance, in robot positioning, it is frequent to make use of images that the robot captures from their cameras to guide the localisation or reduce the intrinsic ambiguity of a specific localisation obtained by other methods. Nevertheless, obtaining good correspondence between two images with a high degree of dissimilarity is a complex task that may lead to important positioning errors. With the aim of increasing the accuracy with respect to the pair-wise image matching approaches, we present a new method to compute group-wise correspondences among a set of images. Thus, pair-wise errors are compensated and better correspondences between images are obtained. These correspondences can be used as a less-noisy input for the localisation process. Group-wise correspondences are computed by finding the common labelling of a set of salient points obtained from the images. Results show a clear increase in effectiveness with respect to methods that use only two images. Wed, 17 Apr 2013 07:41:29 GMT http://hdl.handle.net/2117/18837 2013-04-17T07:41:29Z Solé Ribalta, Albert; Sanromà Güell, Gerard; Serratosa Casanelles, Francesc; Alquézar Mancho, René no Multiple point set alignment, Group wise point set alignment Finding sparse correspondences between two images is a usual process needed for several higher-level computer vision tasks. For instance, in robot positioning, it is frequent to make use of images that the robot captures from their cameras to guide the localisation or reduce the intrinsic ambiguity of a specific localisation obtained by other methods. Nevertheless, obtaining good correspondence between two images with a high degree of dissimilarity is a complex task that may lead to important positioning errors. With the aim of increasing the accuracy with respect to the pair-wise image matching approaches, we present a new method to compute group-wise correspondences among a set of images. Thus, pair-wise errors are compensated and better correspondences between images are obtained. These correspondences can be used as a less-noisy input for the localisation process. Group-wise correspondences are computed by finding the common labelling of a set of salient points obtained from the images. Results show a clear increase in effectiveness with respect to methods that use only two images. http://hdl.handle.net/2117/18672 Title: On the computation of the geodesic distance with an application to dimensionality reduction in a neuro-oncology problem Authors: Cruz Barbosa, Raúl; Bautista Villavicencio, David; Vellido Alcacena, Alfredo Abstract: Manifold learning models attempt to parsimoniously describe multivariate data through a low-dimensional manifold embedded in data space. Similarities between points along this manifold are often expressed as Euclidean distances. Previous research has shown that these similarities are better expressed as geodesic distances. Some problems concerning the computation of geodesic distances along the manifold have to do with time and storage restrictions related to the graph representation of the manifold. This paper provides different approaches to the computation of the geodesic distance and the implementation of Dijkstra’s shortest path algorithm, comparing their performances. The optimized procedures are bundled into a software module that is embedded in a dimensionality reduction method, which is applied to MRS data from human brain tumours. The experimental results show that the proposed implementation explains a high proportion of the data variance with a very small number of extracted features, which should ease the medical interpretation of subsequent results obtained from the reduced datasets. Mon, 08 Apr 2013 08:50:58 GMT http://hdl.handle.net/2117/18672 2013-04-08T08:50:58Z Cruz Barbosa, Raúl; Bautista Villavicencio, David; Vellido Alcacena, Alfredo no Manifold learning models attempt to parsimoniously describe multivariate data through a low-dimensional manifold embedded in data space. Similarities between points along this manifold are often expressed as Euclidean distances. Previous research has shown that these similarities are better expressed as geodesic distances. Some problems concerning the computation of geodesic distances along the manifold have to do with time and storage restrictions related to the graph representation of the manifold. This paper provides different approaches to the computation of the geodesic distance and the implementation of Dijkstra’s shortest path algorithm, comparing their performances. The optimized procedures are bundled into a software module that is embedded in a dimensionality reduction method, which is applied to MRS data from human brain tumours. The experimental results show that the proposed implementation explains a high proportion of the data variance with a very small number of extracted features, which should ease the medical interpretation of subsequent results obtained from the reduced datasets. http://hdl.handle.net/2117/18670 Title: Comparative diagnostic accuracy of linear and nonlinear feature extraction methods in a neuro-oncology problem Authors: Cruz Barbosa, Raúl; Bautista Villavicencio, David; Vellido Alcacena, Alfredo Abstract: The diagnostic classification of human brain tumours on the basis of magnetic resonance spectra is a non-trivial problem in which dimensionality reduction is almost mandatory. This may take the form of feature selection or feature extraction. In feature extraction using manifold learning models, multivariate data are described through a low-dimensional manifold embedded in data space. Similarities between points along this manifold are best expressed as geodesic distances or their approximations. These approximations can be computationally intensive, and several alternative software implementations have been recently compared in terms of computation times. The current brief paper extends this research to investigate the comparative ability of dimensionality-reduced data descriptions to accurately classify several types of human brain tumours. The results suggest that the way in which the underlying data manifold is constructed in nonlinear dimensionality reduction methods strongly influences the classification results. Mon, 08 Apr 2013 08:37:01 GMT http://hdl.handle.net/2117/18670 2013-04-08T08:37:01Z Cruz Barbosa, Raúl; Bautista Villavicencio, David; Vellido Alcacena, Alfredo no The diagnostic classification of human brain tumours on the basis of magnetic resonance spectra is a non-trivial problem in which dimensionality reduction is almost mandatory. This may take the form of feature selection or feature extraction. In feature extraction using manifold learning models, multivariate data are described through a low-dimensional manifold embedded in data space. Similarities between points along this manifold are best expressed as geodesic distances or their approximations. These approximations can be computationally intensive, and several alternative software implementations have been recently compared in terms of computation times. The current brief paper extends this research to investigate the comparative ability of dimensionality-reduced data descriptions to accurately classify several types of human brain tumours. The results suggest that the way in which the underlying data manifold is constructed in nonlinear dimensionality reduction methods strongly influences the classification results. http://hdl.handle.net/2117/18311 Title: Making machine learning models interpretable Authors: Vellido Alcacena, Alfredo; Martin Guerrero, Jose D.; Lisboa, Paulo J.G. Thu, 14 Mar 2013 16:35:08 GMT http://hdl.handle.net/2117/18311 2013-03-14T16:35:08Z Vellido Alcacena, Alfredo; Martin Guerrero, Jose D.; Lisboa, Paulo J.G. no http://hdl.handle.net/2117/18008 Title: Predicting software anomalies using machine learning techniques Authors: Alonso, Javier; Belanche Muñoz, Luis Antonio; Avresky, Dimiter Abstract: In this paper, we present a detailed evaluation of a set of well-known Machine Learning classifiers in front of dynamic and non-deterministic software anomalies. The system state prediction is based on monitoring system metrics. This allows software proactive rejuvenation to be triggered automatically. Random Forest approach achieves validation errors less than 1% in comparison to the well-known ML algorithms under avaluation. In order to reduce automatically the number of monitored parameters, needed to predict software anomalies, we analyze Lasso Regularization technique jointly with the Machine Learning classifiers to evaluate how the prediction accuracy could be guaranteed within an acceptable threshold. This allows to reduce drastically (around 60% in the best case) the number of monitoring parameters. The framework, based on ML and Lasso regularization techniques, has been validated using an e-commerce environment with Apache Tomcat server, and MySql database server. Wed, 27 Feb 2013 15:11:07 GMT http://hdl.handle.net/2117/18008 2013-02-27T15:11:07Z Alonso, Javier; Belanche Muñoz, Luis Antonio; Avresky, Dimiter no Computer crashes, Instruction sets, Machine learning algorithms, Monitoring, Prediction algorithms, Predictive models In this paper, we present a detailed evaluation of a set of well-known Machine Learning classifiers in front of dynamic and non-deterministic software anomalies. The system state prediction is based on monitoring system metrics. This allows software proactive rejuvenation to be triggered automatically. Random Forest approach achieves validation errors less than 1% in comparison to the well-known ML algorithms under avaluation. In order to reduce automatically the number of monitored parameters, needed to predict software anomalies, we analyze Lasso Regularization technique jointly with the Machine Learning classifiers to evaluate how the prediction accuracy could be guaranteed within an acceptable threshold. This allows to reduce drastically (around 60% in the best case) the number of monitoring parameters. The framework, based on ML and Lasso regularization techniques, has been validated using an e-commerce environment with Apache Tomcat server, and MySql database server. http://hdl.handle.net/2117/18005 Title: A software system for the microbial source tracking problem Authors: Sànchez Mendoza, David; Belanche Muñoz, Luis Antonio; Blanch, Anicet R. Abstract: The aim of this paper is to report the achievement of Ichnaea, a fully computer-based prediction system that is able to make fairly accurate predictions for Microbial Source Tracking studies. The system accepts examples showing diff erent concentration levels, uses indicators (variables) with diff erent environmental persistence, and can be applied at diff erent geographical or climatic areas. We describe the inner workings of the system and report on the specifi c problems and challenges arisen from the machine learning point of view and how they have been addressed. Wed, 27 Feb 2013 12:32:55 GMT http://hdl.handle.net/2117/18005 2013-02-27T12:32:55Z Sànchez Mendoza, David; Belanche Muñoz, Luis Antonio; Blanch, Anicet R. no Microbial source tracking, Real-world machine learning applications The aim of this paper is to report the achievement of Ichnaea, a fully computer-based prediction system that is able to make fairly accurate predictions for Microbial Source Tracking studies. The system accepts examples showing diff erent concentration levels, uses indicators (variables) with diff erent environmental persistence, and can be applied at diff erent geographical or climatic areas. We describe the inner workings of the system and report on the specifi c problems and challenges arisen from the machine learning point of view and how they have been addressed. http://hdl.handle.net/2117/18003 Title: Feature selection in proton magnetic resonance spectroscopy data of brain tumors Authors: González Navarro, Félix Fernando; Belanche Muñoz, Luis Antonio Abstract: In cancer diagnosis, classification of the different tumor types is of great importance. An accurate prediction of different tumor types provides better treatment and may minimize the negative impact of incorrectly targeted toxic or aggressive treatments. Moreover, the correct prediction of cancer types using non-invasive information –e.g. 1H-MRS data– could avoid patients to suffer collateral problems derived from exploration techniques that require surgery. A Feature Selection Algorithm specially designed to be use in 1H-MRS Proton Magnetic Resonance Spectroscopy data of brain tumors is presented. It takes advantage of a highly distinctive aspect in this data: some metabolite levels are notoriously different between types of tumors. Experimental read- ings on an international dataset show highly competitive models in terms of accuracy, complexity and medical interpretability. Wed, 27 Feb 2013 11:29:50 GMT http://hdl.handle.net/2117/18003 2013-02-27T11:29:50Z González Navarro, Félix Fernando; Belanche Muñoz, Luis Antonio no Cancer research, Feature selection, Classification In cancer diagnosis, classification of the different tumor types is of great importance. An accurate prediction of different tumor types provides better treatment and may minimize the negative impact of incorrectly targeted toxic or aggressive treatments. Moreover, the correct prediction of cancer types using non-invasive information –e.g. 1H-MRS data– could avoid patients to suffer collateral problems derived from exploration techniques that require surgery. A Feature Selection Algorithm specially designed to be use in 1H-MRS Proton Magnetic Resonance Spectroscopy data of brain tumors is presented. It takes advantage of a highly distinctive aspect in this data: some metabolite levels are notoriously different between types of tumors. Experimental read- ings on an international dataset show highly competitive models in terms of accuracy, complexity and medical interpretability. http://hdl.handle.net/2117/18002 Title: Using machine learning techniques to explore 1H-MRS data of brain tumors Authors: González Navarro, Félix Fernando; Belanche Muñoz, Luis Antonio Abstract: Machine learning is a powerful paradigm to analyze Proton Magnetic Resonance Spectroscopy (1H-MRS) spectral data for the classification of brain tumor pathologies. An important characteristic of this task is the high dimensionality of the involved data sets. In this work we apply filter feature selection methods on three types of 1H-MRS spectral data: long echo time, short echo time and an ad hoc combination of both. The experimental findings show that feature selection permits to drastically reduce the dimension, offering at the same time very attractive solutions both in terms of prediction accuracy and the ability to interpret the involved spectral frequencies. A linear dimensionality reduction technique that preserves the class discrimination capabilities is additionally used for visualization of the selected frequencies. Wed, 27 Feb 2013 10:58:24 GMT http://hdl.handle.net/2117/18002 2013-02-27T10:58:24Z González Navarro, Félix Fernando; Belanche Muñoz, Luis Antonio no Feature selection, Classification, Visualization Machine learning is a powerful paradigm to analyze Proton Magnetic Resonance Spectroscopy (1H-MRS) spectral data for the classification of brain tumor pathologies. An important characteristic of this task is the high dimensionality of the involved data sets. In this work we apply filter feature selection methods on three types of 1H-MRS spectral data: long echo time, short echo time and an ad hoc combination of both. The experimental findings show that feature selection permits to drastically reduce the dimension, offering at the same time very attractive solutions both in terms of prediction accuracy and the ability to interpret the involved spectral frequencies. A linear dimensionality reduction technique that preserves the class discrimination capabilities is additionally used for visualization of the selected frequencies. http://hdl.handle.net/2117/17987 Title: Intelligent management of sepsis in the intensive care unit Authors: Ribas Ripoll, Vicent; Ruiz Rodríguez, Juan Carlos; Vellido Alcacena, Alfredo Tue, 26 Feb 2013 15:01:43 GMT http://hdl.handle.net/2117/17987 2013-02-26T15:01:43Z Ribas Ripoll, Vicent; Ruiz Rodríguez, Juan Carlos; Vellido Alcacena, Alfredo no http://hdl.handle.net/2117/17986 Title: On the use of graphical models to study ICU outcome prediction in septic patients treated with statins Authors: Ribas, Vicent J.; Caballero López, Jesús; Sáez de Tejada, Anna; Ruiz Rodríguez, Juan Carlos; Ruiz Sanmartin, Adolfo; Rello, Jordi; Vellido Alcacena, Alfredo Tue, 26 Feb 2013 14:24:00 GMT http://hdl.handle.net/2117/17986 2013-02-26T14:24:00Z Ribas, Vicent J.; Caballero López, Jesús; Sáez de Tejada, Anna; Ruiz Rodríguez, Juan Carlos; Ruiz Sanmartin, Adolfo; Rello, Jordi; Vellido Alcacena, Alfredo no http://hdl.handle.net/2117/17985 Title: Complementing kernel-based visualization of protein sequences with their phylogenetic tree Authors: Cárdenas, Martha Ivón; Vellido Alcacena, Alfredo; Olier, Iván; Rovira, Xavier; Giraldo, Jesus Tue, 26 Feb 2013 14:17:25 GMT http://hdl.handle.net/2117/17985 2013-02-26T14:17:25Z Cárdenas, Martha Ivón; Vellido Alcacena, Alfredo; Olier, Iván; Rovira, Xavier; Giraldo, Jesus no http://hdl.handle.net/2117/17984 Title: Discovering hidden pathways in bioinformatics Authors: Lisboa, Paulo J.G.; Jarman, Ian H.; Etchells, Terence A.; Chambers, Simon J.; Bacciu, Davide; Whittaker, Joe; Garibaldi, Jon M.; Ortega Martorell, Sandra; Vellido Alcacena, Alfredo; Ellis, Ian O. Tue, 26 Feb 2013 14:08:36 GMT http://hdl.handle.net/2117/17984 2013-02-26T14:08:36Z Lisboa, Paulo J.G.; Jarman, Ian H.; Etchells, Terence A.; Chambers, Simon J.; Bacciu, Davide; Whittaker, Joe; Garibaldi, Jon M.; Ortega Martorell, Sandra; Vellido Alcacena, Alfredo; Ellis, Ian O. no http://hdl.handle.net/2117/17939 Title: Statistical approaches for modeling in microbial source tracking Authors: Belanche Muñoz, Luis Antonio; Blanch, Anicet R. Abstract: Microbial source tracking (MST) concerns the definition of new indicators and appropriate detection methods, the identification of host-specific indicators of fecal pollution, and ultimately the development of useful and reliable predictive models for practical deployment. Optimal predictive models should be designed using proper statistical and computational tools for the analysis of the available data samples. A further requirement is found in the determination of appropriate sets of predictors (indicators, tracers) for developing accurate and low-cost MST solutions. This chapter briefly reviews some of these modeling tools, and their use and feasibility in providing more accurate MST-based results. It also evaluates the potential of established and new algorithmic methods to the identification of fecal pollution sources. Fri, 22 Feb 2013 12:56:43 GMT http://hdl.handle.net/2117/17939 2013-02-22T12:56:43Z Belanche Muñoz, Luis Antonio; Blanch, Anicet R. no Predictive models, Fecal pollution, Microbial indicators Microbial source tracking (MST) concerns the definition of new indicators and appropriate detection methods, the identification of host-specific indicators of fecal pollution, and ultimately the development of useful and reliable predictive models for practical deployment. Optimal predictive models should be designed using proper statistical and computational tools for the analysis of the available data samples. A further requirement is found in the determination of appropriate sets of predictors (indicators, tracers) for developing accurate and low-cost MST solutions. This chapter briefly reviews some of these modeling tools, and their use and feasibility in providing more accurate MST-based results. It also evaluates the potential of established and new algorithmic methods to the identification of fecal pollution sources. http://hdl.handle.net/2117/17935 Title: Learning with heterogeneous neural networks Authors: Belanche Muñoz, Luis Antonio Abstract: This chapter studies a class of neuron models that computes a user-defined similarity function between inputs and weights. The neuron transfer function is formed by composition of an adapted logistic function with the quasi-linear mean of the partial input-weight similarities. The neuron model is capable of dealing directly with mixtures of continuous as well as discrete quantities, among other data types and there is provision for missing values. An artificial neural network using these neuron models is trained using a breeder genetic algorithm until convergence. A number of experiments are carried out in several real-world problems in very different application domains described by mixtures of variales of distinct types and eventually showing missing values. This heterogeneous network is compared to a standard radial basis function network and to a multi-layer perceptron networks and shown to learn from with superior generalization ability at a comparable computational cost. A further important advantage of the resulting neural solutions is the great interpretability of the learned weights, which is done in terms of weighted similarities to prototypes. Fri, 22 Feb 2013 12:18:30 GMT http://hdl.handle.net/2117/17935 2013-02-22T12:18:30Z Belanche Muñoz, Luis Antonio no Artificial neural networks, Similarity measures, Data heterogeneity, Missing values, Evolutionary algorithms This chapter studies a class of neuron models that computes a user-defined similarity function between inputs and weights. The neuron transfer function is formed by composition of an adapted logistic function with the quasi-linear mean of the partial input-weight similarities. The neuron model is capable of dealing directly with mixtures of continuous as well as discrete quantities, among other data types and there is provision for missing values. An artificial neural network using these neuron models is trained using a breeder genetic algorithm until convergence. A number of experiments are carried out in several real-world problems in very different application domains described by mixtures of variales of distinct types and eventually showing missing values. This heterogeneous network is compared to a standard radial basis function network and to a multi-layer perceptron networks and shown to learn from with superior generalization ability at a comparable computational cost. A further important advantage of the resulting neural solutions is the great interpretability of the learned weights, which is done in terms of weighted similarities to prototypes. http://hdl.handle.net/2117/17558 Title: Leakage localization in water networks using fuzzy logic Authors: Sanz Estapé, Gerard; Pérez Magrané, Ramon; Escobet Canal, Antoni Abstract: This paper presents a methodology for leakage localization using FIR (Fuzzy Inductive Reasoning). A real water network situated in Barcelona has been subdivided in zones which could contain a leakage. Two sensors measure pressures on two separated points of the network. A faulty fuzzy model for each zone and sensor is generated. Test data have been used for classification of leakages in order to evaluate how this methodology helps in leakage localization. Results are compared with another isolation methodology. All the work has been done using simulations carried out by EPANET connected with Matlab. FIR applications used are programmed in Matlab too. Fri, 01 Feb 2013 11:48:26 GMT http://hdl.handle.net/2117/17558 2013-02-01T11:48:26Z Sanz Estapé, Gerard; Pérez Magrané, Ramon; Escobet Canal, Antoni no This paper presents a methodology for leakage localization using FIR (Fuzzy Inductive Reasoning). A real water network situated in Barcelona has been subdivided in zones which could contain a leakage. Two sensors measure pressures on two separated points of the network. A faulty fuzzy model for each zone and sensor is generated. Test data have been used for classification of leakages in order to evaluate how this methodology helps in leakage localization. Results are compared with another isolation methodology. All the work has been done using simulations carried out by EPANET connected with Matlab. FIR applications used are programmed in Matlab too.