http://hdl.handle.net/2117/3976 Wed, 22 May 2013 18:15:35 GMT 2013-05-22T18:15:35Z webmaster.bupc@upc.edu Universitat Politècnica de Catalunya. Servei de Biblioteques i Documentació no http://hdl.handle.net/2117/18252 Title: Dr. D. Juan A. Subirana : Medio siglo investigando : los orígenes Authors: Subirana Torrent, Juan A. Abstract: Ressenya autobiogràfica Wed, 13 Mar 2013 09:55:13 GMT http://hdl.handle.net/2117/18252 2013-03-13T09:55:13Z Subirana Torrent, Juan A. no Ressenya autobiogràfica 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/2117/17284 Title: Preprocessing MRS information for classification of human brain tumours Authors: Arizmendi Pereira, Carlos Julio; Vellido Alcacena, Alfredo; Romero Merino, Enrique Fri, 11 Jan 2013 15:18:55 GMT http://hdl.handle.net/2117/17284 2013-01-11T15:18:55Z Arizmendi Pereira, Carlos Julio; Vellido Alcacena, Alfredo; Romero Merino, Enrique no http://hdl.handle.net/2117/17282 Title: Kernel generative topographic mapping of protein sequences Authors: Cárdenas, Martha Ivón; Vellido Alcacena, Alfredo; Olier Caparroso, Iván; Rovira, Xavier; Giraldo, Jesús Fri, 11 Jan 2013 14:57:40 GMT http://hdl.handle.net/2117/17282 2013-01-11T14:57:40Z Cárdenas, Martha Ivón; Vellido Alcacena, Alfredo; Olier Caparroso, Iván; Rovira, Xavier; Giraldo, Jesús no http://hdl.handle.net/2117/17023 Title: A logic programming approach to parsing and production in fluid construction grammar Authors: Sierra Santibáñez, Josefina Abstract: This paper presents a Logic Programming approach to parsing and production in Fluid Construction Grammar (FCG). It builds on previous work on the formalisation of FCG in terms of First Order Logic (FOL) concepts, more specifically on the definition of its core inference operations, unification and merge, in terms of FOL unification and search in the space of a particular set of FOL terms called structure arrangements. An implementation of such inference operations based on Logic Programming and Artificial Intelligence techniques such as unification and heuristic search is outlined. Mon, 26 Nov 2012 15:45:23 GMT http://hdl.handle.net/2117/17023 2012-11-26T15:45:23Z Sierra Santibáñez, Josefina no Logic programming, Parsing, Fluid construction grammar This paper presents a Logic Programming approach to parsing and production in Fluid Construction Grammar (FCG). It builds on previous work on the formalisation of FCG in terms of First Order Logic (FOL) concepts, more specifically on the definition of its core inference operations, unification and merge, in terms of FOL unification and search in the space of a particular set of FOL terms called structure arrangements. An implementation of such inference operations based on Logic Programming and Artificial Intelligence techniques such as unification and heuristic search is outlined. http://hdl.handle.net/2117/15684 Title: Machine learning in human cancer research Authors: Vellido Alcacena, Alfredo; Lisboa, Paulo J.G. Abstract: Evidence-based medicine has grown in stature over three decades and is now regarded a key development of modern medicine. The evidence base can be heterogeneous, involving both qualitative knowledge and measured quantitative data. Data analysis in the area of cancer research has for long been the playing field of statisticians but, over the last decade, Machine Learning (ML) methods have also begun to establish themselves an an alternative and promising approach to computer-based data analysis in oncology. In this chapter, we provide a state-of-the-art in the main areas of cancer research in which ML methods are currently being applied, and discuss some of the advantages and disadvantages of their application. We also comment on and illustrate the integration of ML methods in clinical oncology decision support systems. Wed, 28 Mar 2012 15:19:41 GMT http://hdl.handle.net/2117/15684 2012-03-28T15:19:41Z Vellido Alcacena, Alfredo; Lisboa, Paulo J.G. no Cancer research, Machine learning, Data analysis, Decision support systems Evidence-based medicine has grown in stature over three decades and is now regarded a key development of modern medicine. The evidence base can be heterogeneous, involving both qualitative knowledge and measured quantitative data. Data analysis in the area of cancer research has for long been the playing field of statisticians but, over the last decade, Machine Learning (ML) methods have also begun to establish themselves an an alternative and promising approach to computer-based data analysis in oncology. In this chapter, we provide a state-of-the-art in the main areas of cancer research in which ML methods are currently being applied, and discuss some of the advantages and disadvantages of their application. We also comment on and illustrate the integration of ML methods in clinical oncology decision support systems. http://hdl.handle.net/2117/14742 Title: Artificial Intelligence tools applied to wastewater treatment Authors: Sánchez Marrè, Miquel; Cortés García, Claudio Ulises Abstract: The selection of an appropriate technique for the supervision and control of complex processes is crucial for achieving optimal results. A lot of effort, therefore, has been devoted to developing more efficient methodologies Mon, 23 Jan 2012 14:04:53 GMT http://hdl.handle.net/2117/14742 2012-01-23T14:04:53Z Sánchez Marrè, Miquel; Cortés García, Claudio Ulises no The selection of an appropriate technique for the supervision and control of complex processes is crucial for achieving optimal results. A lot of effort, therefore, has been devoted to developing more efficient methodologies http://hdl.handle.net/2117/14460 Title: Tracking deformable objects and dealing with same class object occlusion Authors: Alquézar Mancho, René; Amézquita, N; Serratosa Casanelles, Francesc Abstract: This paper presents an extension of a previously reported method for object tracking in video sequences to handle the problems of object crossing and occlusion by other objects in the same class that the one followed. The proposed solution is embedded in a system that integrates recognition and tracking in a probabilistic framework. In a recent work, a method to approach the object occlusion problem was proposed that failed when the object crossed or was occluded by another object of the same class. Here we present an attempt to overcome this limitation and show some promising results. The method is based on the assumption that when two objects cross each other there is not a brusque change of the trajectories. Our system uses object recognition results provided by a neural net that are computed from colour features of image regions for each frame. The location of tracked objects is represented through probability images that are updated dynamically using both recognition and tracking results. From these probabilities and a prediction of the motion of the object in the image, a binary decision is made for each pixel and object. Tue, 10 Jan 2012 19:22:24 GMT http://hdl.handle.net/2117/14460 2012-01-10T19:22:24Z Alquézar Mancho, René; Amézquita, N; Serratosa Casanelles, Francesc no Object tracking, Video sequences, Object crossing, Object occlusion, Motion This paper presents an extension of a previously reported method for object tracking in video sequences to handle the problems of object crossing and occlusion by other objects in the same class that the one followed. The proposed solution is embedded in a system that integrates recognition and tracking in a probabilistic framework. In a recent work, a method to approach the object occlusion problem was proposed that failed when the object crossed or was occluded by another object of the same class. Here we present an attempt to overcome this limitation and show some promising results. The method is based on the assumption that when two objects cross each other there is not a brusque change of the trajectories. Our system uses object recognition results provided by a neural net that are computed from colour features of image regions for each frame. The location of tracked objects is represented through probability images that are updated dynamically using both recognition and tracking results. From these probabilities and a prediction of the motion of the object in the image, a binary decision is made for each pixel and object. http://hdl.handle.net/2117/14421 Title: Coordination, organisation and model driven approaches for dynamic, flexible, robust software and services engineering Authors: Reed, Cris; Nieves Sánchez, Juan Carlos; Padget, Julián; Vasconcelos, Wamberto; Staikopoulos, Athanasios; Cliffe, Owen; Dignum, Frank; Vázquez Salceda, Javier; Clarke, Siobhán Abstract: Enterprise systems are increasingly composed of (and even functioning as) components in a dynamic, digital ecosystem. On the one hand, this new situation requires flexible, spontaneous and opportunistic collaboration activities to be identified and established among (electronic) business parties. On the other, it demands engineering methods that are able to integrate new functionalities and behaviours into running systems composed by active, distributed, interdependent processes. Here we present a multi-level architecture that combines organisational and coordination theories with model driven development, for the implementation, deployment and management of dynamic, flexible and robust service-oriented business applications, combined with a service layer that accommodates semantic service description, fine-grained semantic service discovery and the dynamic adaptation of services to meet changing circumstances Mon, 09 Jan 2012 10:48:14 GMT http://hdl.handle.net/2117/14421 2012-01-09T10:48:14Z Reed, Cris; Nieves Sánchez, Juan Carlos; Padget, Julián; Vasconcelos, Wamberto; Staikopoulos, Athanasios; Cliffe, Owen; Dignum, Frank; Vázquez Salceda, Javier; Clarke, Siobhán no Enterprise systems are increasingly composed of (and even functioning as) components in a dynamic, digital ecosystem. On the one hand, this new situation requires flexible, spontaneous and opportunistic collaboration activities to be identified and established among (electronic) business parties. On the other, it demands engineering methods that are able to integrate new functionalities and behaviours into running systems composed by active, distributed, interdependent processes. Here we present a multi-level architecture that combines organisational and coordination theories with model driven development, for the implementation, deployment and management of dynamic, flexible and robust service-oriented business applications, combined with a service layer that accommodates semantic service description, fine-grained semantic service discovery and the dynamic adaptation of services to meet changing circumstances http://hdl.handle.net/2117/14376 Title: Web-based organization models Authors: Dignum, Virginia; Vázquez Salceda, Javier Abstract: Current visions about the Internet of the future require an evolution in the way distributed applications are designed, implemented, and deployed, moving from top-down approaches that generate partial, static (business) process descriptions to holistic approaches where both the participants and their surrounding environment are modeled. Such approaches will empower distributed applications with the ability to flexibly adapt their behavior to environmental changes, being able to identify opportunities and recover from unexpected failures or market switches. In this chapter we have presented a holistic approach based on organizational theory. The ALIVE framework aims to support the design and development of distributed systems suitable for such highly dynamic environments, is based on model-driven engineering, and consists of three interconnected levels: service, oordination, and organization. Fri, 30 Dec 2011 10:59:06 GMT http://hdl.handle.net/2117/14376 2011-12-30T10:59:06Z Dignum, Virginia; Vázquez Salceda, Javier no Current visions about the Internet of the future require an evolution in the way distributed applications are designed, implemented, and deployed, moving from top-down approaches that generate partial, static (business) process descriptions to holistic approaches where both the participants and their surrounding environment are modeled. Such approaches will empower distributed applications with the ability to flexibly adapt their behavior to environmental changes, being able to identify opportunities and recover from unexpected failures or market switches. In this chapter we have presented a holistic approach based on organizational theory. The ALIVE framework aims to support the design and development of distributed systems suitable for such highly dynamic environments, is based on model-driven engineering, and consists of three interconnected levels: service, oordination, and organization.