http://hdl.handle.net/2117/3930 Mon, 20 May 2013 17:28:59 GMT 2013-05-20T17:28:59Z webmaster.bupc@upc.edu Universitat Politècnica de Catalunya. Servei de Biblioteques i Documentació no http://hdl.handle.net/2117/19266 Title: Ranking and selection of unsupervised learning marketing segmentation Authors: Sanchez Hernandez, German; Chiclana, Francisco; Agell Jané, Núria; Aguado Chao, Juan Carlos Abstract: This paper addresses the problem of choosing the most appropriate classification from a given set of classifications of a set of patterns. This is a relevant topic on unsupervised systems and clustering analysis because different classifications can in general be obtained from the same data set. The provided methodology is based on five fuzzy criteria which are aggregated using an Ordered Weighted Averaging (OWA) operator. To this end, a novel multi-criteria decision making (MCDM) system is defined, which assesses the degree up to which each criterion is met by all classifications. The corresponding single evaluations are then proposed to be aggregated into a collective one by means of an OWA operator guided by a fuzzy linguistic quantifier, which is used to implement the concept of fuzzy majority in the selection process. This new methodology is applied to a real marketing case based on a business to business (B2B) environment to help marketing experts during the segmentation process. As a result, a segmentation containing three segments consisting of 35, 98 and 127 points of sale respectively is selected to be the most suitable to endorse marketing strategies of the firm. Finally, an analysis of the managerial implications of the proposed methodology solution is provided. Wed, 15 May 2013 16:10:37 GMT http://hdl.handle.net/2117/19266 2013-05-15T16:10:37Z Sanchez Hernandez, German; Chiclana, Francisco; Agell Jané, Núria; Aguado Chao, Juan Carlos no Fuzzy selection criteria, OWA operator, Classification selection, Market segmentation, Linguistic quantifier This paper addresses the problem of choosing the most appropriate classification from a given set of classifications of a set of patterns. This is a relevant topic on unsupervised systems and clustering analysis because different classifications can in general be obtained from the same data set. The provided methodology is based on five fuzzy criteria which are aggregated using an Ordered Weighted Averaging (OWA) operator. To this end, a novel multi-criteria decision making (MCDM) system is defined, which assesses the degree up to which each criterion is met by all classifications. The corresponding single evaluations are then proposed to be aggregated into a collective one by means of an OWA operator guided by a fuzzy linguistic quantifier, which is used to implement the concept of fuzzy majority in the selection process. This new methodology is applied to a real marketing case based on a business to business (B2B) environment to help marketing experts during the segmentation process. As a result, a segmentation containing three segments consisting of 35, 98 and 127 points of sale respectively is selected to be the most suitable to endorse marketing strategies of the firm. Finally, an analysis of the managerial implications of the proposed methodology solution is provided. http://hdl.handle.net/2117/19225 Title: Validation of Data Association for Monocular SLAM Authors: Guerra Paradas, Edmundo; Munguia Alcala, Rodrigo; Bolea Monte, Yolanda; Grau Saldes, Antoni Abstract: SimultaneousMapping and Localization (SLAM) is amultidisciplinary problem with ramifications within several fields. One of the key aspects for its popularity and success is the data fusion produced by SLAM techniques, providing strong and robust sensory systems even with simple devices, such as webcams in Monocular SLAM. This work studies a novel batch validation algorithm, the highest order hypothesis compatibility test (HOHCT), against one of the most popular approaches, the JCCB. The HOHCT approach has been developed as a way to improve performance of the delayed inverse-depth initialization monocular SLAM, a previously developed monocular SLAM algorithm based on parallax estimation. Both HOHCT and JCCB are extensively tested and compared within a delayed inverse-depth initialization monocular SLAM framework, showing the strengths and costs of this proposal. Wed, 15 May 2013 08:01:56 GMT http://hdl.handle.net/2117/19225 2013-05-15T08:01:56Z Guerra Paradas, Edmundo; Munguia Alcala, Rodrigo; Bolea Monte, Yolanda; Grau Saldes, Antoni no SimultaneousMapping and Localization (SLAM) is amultidisciplinary problem with ramifications within several fields. One of the key aspects for its popularity and success is the data fusion produced by SLAM techniques, providing strong and robust sensory systems even with simple devices, such as webcams in Monocular SLAM. This work studies a novel batch validation algorithm, the highest order hypothesis compatibility test (HOHCT), against one of the most popular approaches, the JCCB. The HOHCT approach has been developed as a way to improve performance of the delayed inverse-depth initialization monocular SLAM, a previously developed monocular SLAM algorithm based on parallax estimation. Both HOHCT and JCCB are extensively tested and compared within a delayed inverse-depth initialization monocular SLAM framework, showing the strengths and costs of this proposal. http://hdl.handle.net/2117/19156 Title: A study on output normalization in multiclass SVMs Authors: González Abril, Luis; Velasco Morente, Francisco; Angulo Bahón, Cecilio; Ortega Ramírez, Juan Antonio Abstract: The use of binary support vector machines (SVMs) in multi-classification is addressed in this paper. Margins associated to the bi-classifiers, since they depend on the geometrical disposition of the classes being separated, are, in general, of various magnitudes. In order to overcome this scaling problem, a normalization process should be applied on the SVMs’ outputs. Thus, a new normalization approach is presented based on the convex hulls that contain the classes to be separated. Furthermore, a theoretical study is developed which justifies the proposed approach, and an interpretation is provided. An empirical study is also carried out to compare this normalization with others found in the literature. Fri, 10 May 2013 10:50:07 GMT http://hdl.handle.net/2117/19156 2013-05-10T10:50:07Z González Abril, Luis; Velasco Morente, Francisco; Angulo Bahón, Cecilio; Ortega Ramírez, Juan Antonio no 1-v-r SVM, Convex hull, Kernel methods, Multiclassification The use of binary support vector machines (SVMs) in multi-classification is addressed in this paper. Margins associated to the bi-classifiers, since they depend on the geometrical disposition of the classes being separated, are, in general, of various magnitudes. In order to overcome this scaling problem, a normalization process should be applied on the SVMs’ outputs. Thus, a new normalization approach is presented based on the convex hulls that contain the classes to be separated. Furthermore, a theoretical study is developed which justifies the proposed approach, and an interpretation is provided. An empirical study is also carried out to compare this normalization with others found in the literature. http://hdl.handle.net/2117/19055 Title: Stochastic Phase-Field simulations of symmetric alloy solidification Authors: Benítez Iglesias, Raúl; Ramírez de la Piscina Millán, Laureano Abstract: We study initial transient stages in directional solidification by means of a non-variational phase field model with fluctuations. This model applies for the symmetric solidification of dilute binary solutions and does not invoke fluctuation-dissipation theorem to account for the fluctuation statistics. We devote our attention to the transient regime during which concentration gradients are building up and fluctuations act to destabilize the interface. To this end, we calculate both the temporally dependent growth rate of each mode and the power spectrum of the interface evolving under the effect of fluctuations. Quantitative agreement is found when comparing the phase-field simulations with theoretical predictions. Tue, 30 Apr 2013 11:08:59 GMT http://hdl.handle.net/2117/19055 2013-04-30T11:08:59Z Benítez Iglesias, Raúl; Ramírez de la Piscina Millán, Laureano no We study initial transient stages in directional solidification by means of a non-variational phase field model with fluctuations. This model applies for the symmetric solidification of dilute binary solutions and does not invoke fluctuation-dissipation theorem to account for the fluctuation statistics. We devote our attention to the transient regime during which concentration gradients are building up and fluctuations act to destabilize the interface. To this end, we calculate both the temporally dependent growth rate of each mode and the power spectrum of the interface evolving under the effect of fluctuations. Quantitative agreement is found when comparing the phase-field simulations with theoretical predictions. http://hdl.handle.net/2117/18996 Title: Flooding management using hybrid model predictive control: Application to the Spanish Ebro River Authors: Romera Formiguera, Juli; Ocampo-Martínez, Carlos; Puig Cayuela, Vicenç; Quevedo Casín, Joseba Jokin Abstract: In this paper, the problem of flooding management using hybrid model predictive control is presented and applied to the Ebro River in Spain. The Ebro River presents flooding episodes in the city of Zaragoza during spring when snow melts in the Pyrenees. To avoid flooding in populated areas, some land outside the city is prepared for flooding. This paper presents a control approach to determine and fix the level of flooding in pre-established zones by controlling side gates that determine the water input to the land to be flooded. Finally, several scenarios are used to validate the performance of the proposed approach Fri, 26 Apr 2013 08:15:14 GMT http://hdl.handle.net/2117/18996 2013-04-26T08:15:14Z Romera Formiguera, Juli; Ocampo-Martínez, Carlos; Puig Cayuela, Vicenç; Quevedo Casín, Joseba Jokin no dynamic programming linear quadratic control optimisation predictive control water systems, rivers, simulation, predictive control, tele-control systems In this paper, the problem of flooding management using hybrid model predictive control is presented and applied to the Ebro River in Spain. The Ebro River presents flooding episodes in the city of Zaragoza during spring when snow melts in the Pyrenees. To avoid flooding in populated areas, some land outside the city is prepared for flooding. This paper presents a control approach to determine and fix the level of flooding in pre-established zones by controlling side gates that determine the water input to the land to be flooded. Finally, several scenarios are used to validate the performance of the proposed approach http://hdl.handle.net/2117/18985 Title: SVM-based feature selection to optimize sensitivity–specificity balance applied to weaning Authors: Garde, Ainara; Voss, Andreas; Caminal Magrans, Pere; Benito Vales, Salvador; Giraldo Giraldo, Beatriz Abstract: Classification algorithms with unbalanced data sets tend to produce high predictive accuracy over the majority class, but poor predictive accuracy over the minority class. This problem is very common in biomedical data mining. This paper introduces a Support Vector Machine(SVM)-based optimized features election method, to select the most relevant features and maintain an accurate and well-balanced sensitivity–specificity result between unbalanced groups. A new metric called the balance index(B) is defined to implement this optimization. The balance index measures the difference between the misclassified data within each class. The proposed optimized feature selection is applied to the classification of patients’ weaning trials from mechanical ventilation: patients with successful trials who were able to maintain spontaneous breathing after 48 h and patients who failed to maintain spontaneous breathing and were reconnected to mechanical ventilation after 30min. Patients are characterized through cardiac and respiratory signals, applying joint symbolic dynamic (JSD) analys is to cardiac interbeat and breath durations. First, the most suitable parameters (C þ ,C ,s)are selected to define the appropriate SVM. Then, the features election process is carried out with this SVM, to maintain B lower than 40%. The best result is obtained using 6 features with an accuracy of 80%, a B of 18.64%, a sensitivity of 74.36% and a specificity of 82.42%. Thu, 25 Apr 2013 11:51:52 GMT http://hdl.handle.net/2117/18985 2013-04-25T11:51:52Z Garde, Ainara; Voss, Andreas; Caminal Magrans, Pere; Benito Vales, Salvador; Giraldo Giraldo, Beatriz no Support vectormachines Balance index Sensitivity–specificity balance Cardiorespiratory interaction Joint symbolicdynamics Feature selection Weaning procedure Classification algorithms with unbalanced data sets tend to produce high predictive accuracy over the majority class, but poor predictive accuracy over the minority class. This problem is very common in biomedical data mining. This paper introduces a Support Vector Machine(SVM)-based optimized features election method, to select the most relevant features and maintain an accurate and well-balanced sensitivity–specificity result between unbalanced groups. A new metric called the balance index(B) is defined to implement this optimization. The balance index measures the difference between the misclassified data within each class. The proposed optimized feature selection is applied to the classification of patients’ weaning trials from mechanical ventilation: patients with successful trials who were able to maintain spontaneous breathing after 48 h and patients who failed to maintain spontaneous breathing and were reconnected to mechanical ventilation after 30min. Patients are characterized through cardiac and respiratory signals, applying joint symbolic dynamic (JSD) analys is to cardiac interbeat and breath durations. First, the most suitable parameters (C þ ,C ,s)are selected to define the appropriate SVM. Then, the features election process is carried out with this SVM, to maintain B lower than 40%. The best result is obtained using 6 features with an accuracy of 80%, a B of 18.64%, a sensitivity of 74.36% and a specificity of 82.42%. http://hdl.handle.net/2117/18715 Title: Quasi-LPV modeling, identification and control of a twin rotor MIMO system Authors: Rotondo, Damiano; Nejjari Akhi-Elarab, Fatiha; Puig Cayuela, Vicenç Abstract: This paper describes the quasi-linear parameter varying (quasi-LPV) modeling, identification and control of a Twin Rotor MIMO System (TRMS). The non-linear model of the TRMS is transformed into a quasi-LPV system and approximated in a polytopic way. The unknown model parameters have been calibrated by means of the non-linear least squares identification approach and validated against real data. Finally, an LPV state observer and state-feedback controller have been designed using an LPV pole placement method based on LMI regions. The effectiveness and performance of the proposed control approach have been proved both in simulation and on the real set-up. Tue, 09 Apr 2013 08:02:32 GMT http://hdl.handle.net/2117/18715 2013-04-09T08:02:32Z Rotondo, Damiano; Nejjari Akhi-Elarab, Fatiha; Puig Cayuela, Vicenç no This paper describes the quasi-linear parameter varying (quasi-LPV) modeling, identification and control of a Twin Rotor MIMO System (TRMS). The non-linear model of the TRMS is transformed into a quasi-LPV system and approximated in a polytopic way. The unknown model parameters have been calibrated by means of the non-linear least squares identification approach and validated against real data. Finally, an LPV state observer and state-feedback controller have been designed using an LPV pole placement method based on LMI regions. The effectiveness and performance of the proposed control approach have been proved both in simulation and on the real set-up. http://hdl.handle.net/2117/18574 Title: Fractional DC-DC converter in solar-powered electrical generation systems Authors: Martínez González, Rubén; Bolea Monte, Yolanda; Grau Saldes, Antoni; Martínez García, Herminio Abstract: This paper deals with the fractional modeling of a DC-DC buck-boost converter, suitable in solar-powered electrical generation systems, and the design of a fractional controller for the aforementioned switching converter. Although the modeling and design of the controller is carried out for this particular DC-DC converter, it can be easily extended to other kind of switching converter. In addition, the comparison between integer-order plan/controller and fractional-order plants/controller is carried out. The article also shows that, under the same design conditions, the fractional-order controller has a better performance and behaviour than the classical integer-order controller in both situations, that is, with integer-order plant and fractional-order plant models. Wed, 03 Apr 2013 12:02:03 GMT http://hdl.handle.net/2117/18574 2013-04-03T12:02:03Z Martínez González, Rubén; Bolea Monte, Yolanda; Grau Saldes, Antoni; Martínez García, Herminio no This paper deals with the fractional modeling of a DC-DC buck-boost converter, suitable in solar-powered electrical generation systems, and the design of a fractional controller for the aforementioned switching converter. Although the modeling and design of the controller is carried out for this particular DC-DC converter, it can be easily extended to other kind of switching converter. In addition, the comparison between integer-order plan/controller and fractional-order plants/controller is carried out. The article also shows that, under the same design conditions, the fractional-order controller has a better performance and behaviour than the classical integer-order controller in both situations, that is, with integer-order plant and fractional-order plant models. http://hdl.handle.net/2117/18515 Title: Low density lipoproteins promote unstable calcium handling accompanied by reduced SERCA2 and connexin-40 expression in cardiomyocytes Authors: Barriga, Montserrat; Cal, Roi; Cabello, Nuria; Llach, Anna; Vallmitjana Lees, Alex; Benítez Iglesias, Raúl; Badimon, Lina; Cinca, J.; Llorente-Cortés, Vicenta; Hove-Madsen, Leif Abstract: The damaging effects of high plasma levels of cholesterol in the cardiovascular system are widely known, but little attention has been paid to direct effects on cardiomyocyte function. We therefore aimed at testing the hypothesis that Low Density Lipoprotein (LDL) cholesterol affects calcium dynamics and signal propagation in cultured atrial myocytes. For this purpose, mRNA and protein expression levels were determined by real time PCR and western blot analysis, respectively, and intracellular calcium was visualized in fluo-4 loaded atrial HL-1 myocyte cultures subjected to field stimulation. At low stimulation frequencies all cultures had uniform calcium transients at all tested LDL concentrations. However, 500 mg LDL/mL maximally reduced the calcium transient amplitude by 43% from 0.3060.04 to 0.1760.02 (p,0.05). Moreover, LDLcholesterol dose-dependently increased the fraction of alternating and irregular beat-to-beat responses observed when the stimulation interval was shortened. This effect was linked to a concurrent reduction in SERCA2, RyR2, IP3RI and IP3RII mRNA levels. SERCA2 protein levels were also reduced by 43% at 200 mg LDL/mL (p,0.05) and SR calcium loading was reduced by 3866% (p,0.001). By contrast, HDL-cholesterol had no significant effect on SERCA expression or SR calcium loading. LDLcholesterol also slowed the conduction velocity of the calcium signal from 3.2+0.2 mm/s without LDL to 1.760.1 mm/s with 500 mg LDL/mL (p,0.05). This coincided with a reduction in Cx40 expression (by 4463%; p,0.05 for mRNA and by 7962%; p,0.05 for Cx40 protein at 200 mg/ml LDL) whereas the Cx-43 expression did not significantly change. In conclusion, LDLcholesterol destabilizes calcium handling in cultured atrial myocytes subjected to rapid pacing by reducing SERCA2 and Cx40 expression and by slowing the conduction velocity of the calcium signal. Tue, 02 Apr 2013 09:45:58 GMT http://hdl.handle.net/2117/18515 2013-04-02T09:45:58Z Barriga, Montserrat; Cal, Roi; Cabello, Nuria; Llach, Anna; Vallmitjana Lees, Alex; Benítez Iglesias, Raúl; Badimon, Lina; Cinca, J.; Llorente-Cortés, Vicenta; Hove-Madsen, Leif no The damaging effects of high plasma levels of cholesterol in the cardiovascular system are widely known, but little attention has been paid to direct effects on cardiomyocyte function. We therefore aimed at testing the hypothesis that Low Density Lipoprotein (LDL) cholesterol affects calcium dynamics and signal propagation in cultured atrial myocytes. For this purpose, mRNA and protein expression levels were determined by real time PCR and western blot analysis, respectively, and intracellular calcium was visualized in fluo-4 loaded atrial HL-1 myocyte cultures subjected to field stimulation. At low stimulation frequencies all cultures had uniform calcium transients at all tested LDL concentrations. However, 500 mg LDL/mL maximally reduced the calcium transient amplitude by 43% from 0.3060.04 to 0.1760.02 (p,0.05). Moreover, LDLcholesterol dose-dependently increased the fraction of alternating and irregular beat-to-beat responses observed when the stimulation interval was shortened. This effect was linked to a concurrent reduction in SERCA2, RyR2, IP3RI and IP3RII mRNA levels. SERCA2 protein levels were also reduced by 43% at 200 mg LDL/mL (p,0.05) and SR calcium loading was reduced by 3866% (p,0.001). By contrast, HDL-cholesterol had no significant effect on SERCA expression or SR calcium loading. LDLcholesterol also slowed the conduction velocity of the calcium signal from 3.2+0.2 mm/s without LDL to 1.760.1 mm/s with 500 mg LDL/mL (p,0.05). This coincided with a reduction in Cx40 expression (by 4463%; p,0.05 for mRNA and by 7962%; p,0.05 for Cx40 protein at 200 mg/ml LDL) whereas the Cx-43 expression did not significantly change. In conclusion, LDLcholesterol destabilizes calcium handling in cultured atrial myocytes subjected to rapid pacing by reducing SERCA2 and Cx40 expression and by slowing the conduction velocity of the calcium signal. http://hdl.handle.net/2117/18476 Title: Experiences of simulation use in industrial projects Authors: Fonseca Casas, Pau; Casanovas Garcia, Josep; Montero García, Jordi; Guasch Petit, Antonio Abstract: This paper presents experiences obtained from our involvement in the development of industrial simulation projects. Some important, common questions are covered, such as the need to define model behavior using a conceptual model, the problem of choosing the appropriate tool to code the model, and the validation and verification process required. As we will see, the scope of applicability of simulation is broad and the tools are therefore diverse. A clear understanding of the objectives of the simulation, the client’s aims and the resources at our disposal are key issues that often determine the success of a simulation project. Fri, 22 Mar 2013 10:34:19 GMT http://hdl.handle.net/2117/18476 2013-03-22T10:34:19Z Fonseca Casas, Pau; Casanovas Garcia, Josep; Montero García, Jordi; Guasch Petit, Antonio no This paper presents experiences obtained from our involvement in the development of industrial simulation projects. Some important, common questions are covered, such as the need to define model behavior using a conceptual model, the problem of choosing the appropriate tool to code the model, and the validation and verification process required. As we will see, the scope of applicability of simulation is broad and the tools are therefore diverse. A clear understanding of the objectives of the simulation, the client’s aims and the resources at our disposal are key issues that often determine the success of a simulation project. http://hdl.handle.net/2117/18424 Title: Application of predictive control strategies to the management of complex networks in the urban water cycle Authors: Ocampo-Martínez, Carlos; Puig Cayuela, Vicenç; Cembrano Gennari, Gabriela; Quevedo Casín, Joseba Jokin Abstract: The management of the urban water cycle (UWC) is a subject of increasing interest because of its social, economic, and environmental impact. The most important issues include the sustainable use of limited resources and the reliability of service to consumers with adequate quality and pressure levels, as well as the urban drainage management to prevent flooding and polluting discharges to the environment. Tue, 19 Mar 2013 18:02:56 GMT http://hdl.handle.net/2117/18424 2013-03-19T18:02:56Z Ocampo-Martínez, Carlos; Puig Cayuela, Vicenç; Cembrano Gennari, Gabriela; Quevedo Casín, Joseba Jokin no The management of the urban water cycle (UWC) is a subject of increasing interest because of its social, economic, and environmental impact. The most important issues include the sustainable use of limited resources and the reliability of service to consumers with adequate quality and pressure levels, as well as the urban drainage management to prevent flooding and polluting discharges to the environment. http://hdl.handle.net/2117/18371 Title: Preface: Introduction to special issue Authors: Guasch Petit, Antonio; Piera, M Mon, 18 Mar 2013 14:43:10 GMT http://hdl.handle.net/2117/18371 2013-03-18T14:43:10Z Guasch Petit, Antonio; Piera, M no http://hdl.handle.net/2117/18361 Title: Técnicas de simulación Authors: Guasch Petit, Antonio; Hüber, Robert Mon, 18 Mar 2013 10:41:39 GMT http://hdl.handle.net/2117/18361 2013-03-18T10:41:39Z Guasch Petit, Antonio; Hüber, Robert no http://hdl.handle.net/2117/18081 Title: A software tool for large-scale synthetic experiments based on polymeric sensor arrays Authors: Ziyatdinov, Andrey; Fernandez Diaz, Eduard; Chaudry, A.; Marco Colás, Santiago; Persaud, K.; Perera Lluna, Alexandre Tue, 05 Mar 2013 18:34:30 GMT http://hdl.handle.net/2117/18081 2013-03-05T18:34:30Z Ziyatdinov, Andrey; Fernandez Diaz, Eduard; Chaudry, A.; Marco Colás, Santiago; Persaud, K.; Perera Lluna, Alexandre no http://hdl.handle.net/2117/18078 Title: Robust identification and fault diagnosis based on uncertain multiple input-multiple output linear parameter varying parity equations and zonotopes Authors: Blesa Izquierdo, Joaquim; Puig Cayuela, Vicenç; Saludes Closa, Jordi Tue, 05 Mar 2013 18:24:53 GMT http://hdl.handle.net/2117/18078 2013-03-05T18:24:53Z Blesa Izquierdo, Joaquim; Puig Cayuela, Vicenç; Saludes Closa, Jordi no control theory Author keywords: fault detection, isolation and estimation, linear parameter varying model, sensitivity matrix