Grammar-Guided Evolutionary Construction of Bayesian networks

This paper proposes the EvoBANE system. EvoBANE automatically generates Bayesian networks for solving special-purpose problems. EvoBANE evolves a population of individuals that codify Bayesian networks until it finds near optimal individual that solves a given classification problem. EvoBANE has the flexibility to modify the constraints that condition the solution search space, self-adapting to the specifications of the problem to be solved. The system extends the GGEAS architecture. GGEAS is a general-purpose grammar-guided evolutionary automatic system, whose modular structure favors its application to the automatic construction of intelligent systems. EvoBANE has been applied to two classification benchmark datasets belonging to different application domains, and statistically compared with a genetic algorithm performing the same tasks. Results show that the proposed system performed better, as it manages different complexity constraints in order to find the simplest solution that best solves every problem.

Innovative self management system for guided cardiac rehabilitation

This paper describes the design and development of a system for cardio rehabilitation of patients that suffered a myocardial infarction. The proposed solution focuses on exercise prescriptions and the encouragement of healthy behaviors. The innovative strategy of the design takes into account health promotion models to provide safe, assistive exercise training sessions, personalized feedbacks, and educational contents.

Technical evaluation of a third generation optical pose tracker for motion analysis and image-guided surgery

Laparoscopic instrument tracking systems are an essential component in image-guided interventions and offer new possibilities to improve and automate objective assessment methods of surgical skills. In this study we present our system design to apply a third generation optical pose tracker (Micron- Tracker®) to laparoscopic practice. A technical evaluation of this design is performed in order to analyze its accuracy in computing the laparoscopic instrument tip position. Results show a stable fluctuation error over the entire analyzed workspace. The relative position errors are 1.776±1.675 mm, 1.817±1.762 mm, 1.854±1.740 mm, 2.455±2.164 mm, 2.545±2.496 mm, 2.764±2.342 mm, 2.512±2.493 mm for distances of 50, 100, 150, 200, 250, 300, and 350 mm, respectively. The accumulated distance error increases with the measured distance. The instrument inclination covered by the system is high, from 90 to 7.5 degrees. The system reports a low positional accuracy for the instrument tip.

A guided heuristic approach to the MEG inverse problem.

There is general agreement within the scientific community in considering Biology as the science with more potential to develop in the XXI century. This is due to several reasons, but probably the most important one is the state of development of the rest of experimental and technological sciences. In this context, there are a very rich variety of mathematical tools, physical techniques and computer resources that permit to do biological experiments that were unbelievable only a few years ago. Biology is nowadays taking advantage of all these newly developed technologies, which are been applied to life sciences opening new research fields and helping to give new insights in many biological problems. Consequently, biologists have improved a lot their knowledge in many key areas as human function and human diseases. However there is one human organ that is still barely understood compared with the rest: The human brain. The understanding of the human brain is one of the main challenges of the XXI century. In this regard, it is considered a strategic research field for the European Union and the USA. Thus, there is a big interest in applying new experimental techniques for the study of brain function. Magnetoencephalography (MEG) is one of these novel techniques that are currently applied for mapping the brain activity1. This technique has important advantages compared to the metabolic-based brain imagining techniques like Functional Magneto Resonance Imaging2 (fMRI). The main advantage is that MEG has a higher time resolution than fMRI. Another benefit of MEG is that it is a patient friendly clinical technique. The measure is performed with a wireless set up and the patient is not exposed to any radiation. Although MEG is widely applied in clinical studies, there are still open issues regarding data analysis. The present work deals with the solution of the inverse problem in MEG, which is the most controversial and uncertain part of the analysis process3. This question is addressed using several variations of a new solving algorithm based in a heuristic method. The performance of those methods is analyzed by applying them to several test cases with known solutions and comparing those solutions with the ones provided by our methods.

Comparative study of two laparoscopic instrument tracker designs for motion analysis and image-guided surgery: a technical evaluation

Laparoscopic instrument tracking systems are a key element in image-guided interventions, which requires high accuracy to be used in a real surgical scenario. In addition, these systems are a suitable option for objective assessment of laparoscopic technical skills based on instrument motion analysis. This study presents a new approach that improves the accuracy of a previously presented system, which applies an optical pose tracking system to laparoscopic practice. A design enhancement of the artificial markers placed on the laparoscopic instrument as well as an improvement of the calibration process are presented as a means to achieve more accurate results. A technical evaluation has been performed in order to compare the accuracy between the previous design and the new approach. Results show a remarkable improvement in the fluctuation error throughout the measurement platform. Moreover, the accumulated distance error and the inclination error have been improved. The tilt range covered by the system is the same for both approaches, from 90º to 7.5º. The relative position error is better for the new approach mainly at close distances to the camera system

Towards the automatic generation of card games through Grammar-Guided Genetic Programming

We demonstrate generating complete and playable card games using evolutionary algorithms. Card games are represented in a previously devised card game description language, a context-free grammar. The syntax of this language allows us to use grammar-guided genetic programming. Candidate card games are evaluated through a cascading evaluation function, a multi-step process where games with undesired properties are progressively weeded out. Three representa- tive examples of generated games are analysed. We observed that these games are reasonably balanced and have skill ele- ments, they are not yet entertaining for human players. The particular shortcomings of the examples are discussed in re- gard to the generative process to be able to generate quality games

Stoichiometry in Context: Inquiry-Guided Problems of Chemistry for Encouraging Critical Thinking in Engineering Students

This paper focuses on examples of educational tools concerning the learning of chemistry for engineering students through different daily life cases. These tools were developed during the past few years for enhancing the active role of students. They refer to cases about mineral water, medicaments, dentifrices and informative panels about solar power, where an adequate quantitative treatment through stoichiometry calculations allows the interpretation of data and values announced by manufacturers. These cases were developed in the context of an inquiry-guided instruction model. By bringing tangible chemistry examples into the classroom we provide an opportunity for engineering students to apply this science to familiar products in hopes that they will appreciate chemistry more, will be motivated to study concepts in greater detail, and will connect the relevance of chemistry to everyday life.

A study on the lateralization of the effect of musical imagery on spontaneous otoacoustic emissions

It has been suggested that different pathways through the brain are followed depending on the type of information that is being processed. Although it is now known that there is a continuous exchange of information through both hemispheres, language is considered to be processed by the left hemisphere, where Broca?s and Wernicke?s areas are located. On the other hand, music is thought to be processed mainly by the right hemisphere. According to Sininger Y.S. & Cone- Wesson, B. (2004), there is a similar but contralateral specialization of the human ears; due to the fact that auditory pathways cross-over at the brainstem. A previous study showed an effect of musical imagery on spontaneous otoacoustic emissions (SOAEs) (Perez-Acosta and Ramos-Amezquita, 2006), providing evidence of an efferent influence from the auditory cortex on the basilar membrane. Based on these results, the present work is a comparative study between left and right ears of a population of eight musicians that presented SOAEs. A familiar musical tune was chosen, and the subjects were trained in the task of evoking it after having heard it. Samples of ear-canal signals were obtained and processed in order to extract frequency and amplitude data on the SOAEs. This procedure was carried out before, during and after the musical image creation task. Results were then analyzed to compare the difference between SOAE responses of left and right ears. A clear asymmetrical SOAEs response to musical imagery tasks between left and right ears was obtained. Significant changes of SOAE amplitude related to musical imagery tasks were only observed on the right ear of the subjects. These results may suggest a predominant left hemisphere activity related to a melodic image creation task.

Modeling the shape hierarchy for visually guided grasping

The monkey anterior intraparietal area (AIP) encodes visual information about three-dimensional object shape that is used to shape the hand for grasping. We modeled shape tuning in visual AIP neurons and its relationship with curvature and gradient information from the caudal intraparietal area (CIP). The main goal was to gain insight into the kinds of shape parameterizations that can account for AIP tuning and that are consistent with both the inputs to AIP and the role of AIP in grasping. We first experimented with superquadric shape parameters. We considered superquadrics because they occupy a role in robotics that is similar to AIP , in that superquadric fits are derived from visual input and used for grasp planning. We also experimented with an alternative shape parameterization that was based on an Isomap dimension reduction of spatial derivatives of depth (i.e., distance from the observer to the object surface). We considered an Isomap-based model because its parameters lacked discontinuities between similar shapes. When we matched the dimension of the Isomap to the number of superquadric parameters, the superquadric model fit the AIP data somewhat more closely. However, higher-dimensional Isomaps provided excellent fits. Also, we found that the Isomap parameters could be approximated much more accurately than superquadric parameters by feedforward neural networks with CIP-like inputs. We conclude that Isomaps, or perhaps alternative dimension reductions of visual inputs to AIP, provide a promising model of AIP electrophysiology data. Further work is needed to test whether such shape parameterizations actually provide an effective basis for grasp control.

Foreground segmentation in depth imagery using depth and spatial dynamic models for video surveillance applications

Low-cost systems that can obtain a high-quality foreground segmentation almostindependently of the existing illumination conditions for indoor environments are verydesirable, especially for security and surveillance applications. In this paper, a novelforeground segmentation algorithm that uses only a Kinect depth sensor is proposedto satisfy the aforementioned system characteristics. This is achieved by combininga mixture of Gaussians-based background subtraction algorithm with a new Bayesiannetwork that robustly predicts the foreground/background regions between consecutivetime steps. The Bayesian network explicitly exploits the intrinsic characteristics ofthe depth data by means of two dynamic models that estimate the spatial and depthevolution of the foreground/background regions. The most remarkable contribution is thedepth-based dynamic model that predicts the changes in the foreground depth distributionbetween consecutive time steps. This is a key difference with regard to visible imagery,where the color/gray distribution of the foreground is typically assumed to be constant.Experiments carried out on two different depth-based databases demonstrate that theproposed combination of algorithms is able to obtain a more accurate segmentation of theforeground/background than other state-of-the art approaches.

Juan Navarro Baldeweg : el dibujo de la mano como herramienta en el proceso creativo

Esta investigación es una incursión en el tránsito de Juan Navarro desde sus “habitaciones y horizontes”, las manifestaciones espontáneas de la mano y el proyectar, a la obra que nos devuelve a la experiencia física y corporal del mundo. Juan Navarro debe a sus manos gran parte de sus inquietudes y capacidades. Sus manos están presentes en su obra como materia –piezas de manos-, como herramienta -el dibujo por la mano- y como desencadenante en los procesos creativos de su obra de arquitectura. Las distintas obras remiten a una preocupación común: la de visualizar el espacio a través de un imaginario personal. Sin embargo, el proceso creativo en cada disciplina se desarrolla teniendo en cuenta la especificidad del medio y la experiencia que provoca en el espectador. La obra, como concreción del proceso creativo, se explica por las continuidades y discontinuidades entre las herramientas, mecanismos y estrategias utilizadas en los distintos medios. La tesis se estructura en dos partes, en la primera se estudia cómo se producen los procesos creativos, sus mecanismos en los distintos medios plásticos y el dibujo como herramienta transversal. Se identifican los conceptos y temas que dan lugar a la obra profundizando en el papel de la mano como presencia orgánica, biológica y responsable de una forma de representación personal. La segunda parte se articula en dos capítulos que, a través del dibujo, muestran la arquitectura como modelo e identifican los mecanismos utilizados en su forma de proyectar y su relación con la obra en distintos proyectos. El texto se estructura como una secuencia de ideas articuladas alrededor de un universo gráfico que nos conduce por múltiples itinerarios desde los que atisbar los procesos creativos de Juan Navarro. Estos caminos son hilos con los que se teje una visión personal de la relación entre las herramientas y mecanismos utilizados por Juan Navarro y su obra. La manera cómo se produce el proceso creativo, los mecanismos y las herramientas que los ponen en marcha constituyen una forma de abordar la obra, que hasta la fecha, se ha tratado aisladamente sin una intención de construir un cuerpo estructurado de conocimiento. En la arquitectura Juan Navarro existe un vacío de conocimiento teórico y gráfico sobre el propio proceso y su forma de proyectar. Se ha persistido en la explicación de la obra, sus referencias, temas abordados, relaciones y trasvases sin ahondar en la especificidad del medio. Estos vacíos establecen la necesidad y justificación de esta tesis doctoral. La investigación comienza descifrando una obra que desde sus inicios trabaja con la dualidad de lo gestual y lo conceptual. Plantea una forma de ordenación del mundo, de la sensación sometida a la medida en la que finalmente la obra se recibe como signo que desencadena sentimientos y te devuelve al mundo. Propone la recuperación de los sentidos a través de una arquitectura como vivencia no reductible al espacio geométrico. Identifica los mecanismos y herramientas que se establecen en este proceso y termina concluyendo que el dibujo es la herramienta doblemente transversal porque atiende de forma desigual a las distintas disciplinas y a los dos extremos en que se presenta la actividad creatividad en el trabajo de Juan Navarro. Estos extremos se corresponden con un conocimiento corporal inconsciente y un trabajo constante guiado por la motivación, la predeterminación y la conceptualización. El dibujo por la mano es el espacio de encuentro entre lo que representa la mano y la posibilidad de expresión proyectual codificada. Se produce en un territorio que se extiende desde lo analógico subyacente –que se nutre de imágenes complejas- y el dominio simbólico construido. Abstract. This research is a foray into Juan Navarro’s transition from his "Rooms and Horizons", -spontaneous demonstrations of the hand-, to the project, -the work that brings us back to experiencing the physical world-. Juan Navarro owes his hands much of his capacities and inquisitiveness. His hands are present in his work as the subject –“Hand Pieces”-, as a tool -through hand-drawing - and as a trigger in the creative processes of his work of architecture. The various works refer to a common theme: the viewing space through a personal imagery. However, the creative process in each discipline develops taking into account the specificity of the medium and the experience that arouses in the observer. The work, as completion of the creative process, is explained by the continuities and discontinuities between the tools, mechanisms and strategies used in the different media. The thesis is structured in two parts, the first studies how the creative processes are iniciated, their mechanisms in the different plastic art media, as well as drawing as a transversal tool. In this section the investigation identifies the concepts and themes that give rise to the art work, exploring the role of the hand as the organic, biological presence responsible for a way of personal representation. The second part is divided into two chapters, which, via the drawing, show the architecture as a model and identify the mechanisms used in the his way of projecting form of the project and its the relationship of hand-drawing to with his work ilustrated with different projects. The text is structured as a sequence of ideas, articulated around a graphic universe that leads us by multiple paths, letting us glimpse into the creative processes of Juan Navarro. These paths are threads that weave a personal vision of the relationship between the tools and mechanisms used by Juan Navarro in his work. The way the creative process takes place, the mechanisms and tools that set it in action, constitutes a way of dealing with the work, that, hithergo, has been treated in isolation without an intention to build a structured body of knowledge. In Navarro Baldeweg’s architecture there is a vacuum of theoretical and graphic knowledge of the process itself and his way of projecting. So far, emphasis has been placed mainly on his work’s explanation, its references, the subjects covered, connections and transfers, without delving into the specificity of each medium. These academic gaps justify the need for this doctoral thesis. The investigation begins deciphering a work that, since its very beginning, deals with the duality of the gesture and the concept. It poses a way of managing the world and the sensations which are submitted until it finally detects the work as a sign that triggers feelings and returns the observer to the real world. It proposes the recovery of the senses through an architecture that is sensed as an experience and not merely reduced to geometric space. It identifies the mechanisms and tools that are set out in this process and concludes that drawing is a core tool working in two directions, because it caters unevenly to the various disciplines and to both ends of the creative activity presented in the work of Juan Navarro. These ends correspond with an unconscious physical knowledge and a continuous work guided by motivation, predetermination and conceptualization. Hand-drawing is the meeting space between what the hand represents, and the possibility of an encoded, projectual expression. Thus, hand-drawing takes place in a territory that covers the underlying analogue - which feeds on complex images - to the symbolic built domain.