Recognition of online handwritten music symbols

Paper submitted to MML 2013, 6th International Workshop on Machine Learning and Music, Prague, September 23, 2013.

Los medios online y la ¿crisis? de la planificación de medios publicitarios

Los medios online representan actualmente una gran apuesta para la publicidad. Desde la planificación de medios publicitarios, los nuevos medios ofrecen otros caminos para llegar al público, pero añaden mayor complejidad. La capacidad comunicativa de los medios online y el mayor consumo de esos medios por parte de la población abre el debate de la necesidad de replantear el enfoque de la planificación de medios, digamos, tradicional, cuya estructura y procesos de trabajo se desarrollaron cuando los medios eran offline. Así, este artículo proporciona una panorámica general de la influencia de los nuevos medios en la planificación. Para ello, en primer lugar, describe el escenario actual, analizando la penetración y las inversiones publicitarias en Internet. Además, expone los principales soportes online según su proximidad a la concepción de la planificación de medios offline. En segundo lugar, aborda los retos actuales en la medición de los nuevos medios como síntoma del impulso del cambio de modelo. Finalmente, el artículo termina exponiendo algunas tendencias que se presentan como motores de cambio. Sin embargo, tras este análisis se advierte que tales aspectos no modificarían la esencia de la planificación de medios, por lo que cabe cuestionarse si se puede hablar de crisis, o si los nuevos medios están mostrando la necesidad de que la investigación y planificación se comprometa con este nuevo escenario.

Online Media and Crisis? of Advertising Media Planning

Nowadays, online media represent a great choice for advertising. From de advertising media planning, new media give new ways to reach the consumers, but they also add more complexity. The communication capacity of online media and the greater use of that media by part of the users open up the debate about the necessity of rethinking the approach of the ‘traditional’ advertising media planning, which structure and work processes were developed when media were offline. So, this article gives a panoramic view about the influence of new media in advertising media planning. To do this, in first place, describes the current scenario, analyzing the penetration and advertising expenditure in Internet. Also, it shows the main online media according to their proximity to the offline advertising media planning conception. In second place, this article addresses the current challenges at measuring new media as a symptom of the impulse at the change of model. Finally, the article ends up showing some trends that are presented as drivers of change. However, after this analysis, comes up the point that those aspects would not change the essence of advertising media planning, so it is questionable if we can speak of a crisis or, instead, if new media are showing the necessity that media planning have to be involved with this new scenario.

Uso de Internet y prácticas políticas de los jóvenes españoles

A partir de un análisis secundario de los microdatos procedentes del estudio 2.889 del Centro de Investigaciones Sociológicas de España, pretendemos observar la posible relación entre el uso de Internet por parte de los jóvenes y sus prácticas políticas. En concreto, las variables disponibles permiten estudiar tres aspectos fundamentales: si existe relación entre la frecuencia de uso de Internet y la participación política; si el grado de participación política en el espacio virtual se correlaciona con la participación fuera de este espacio; y si se observan diferencias en términos de participación política online según variables sociodemográficas. Entre los resultados obtenidos podemos destacar la existencia de una relación estadísticamente significativa entre una mayor frecuencia de uso de Internet y una mayor implicación política tanto en el espacio virtual como offline.

Publicidad en medios online: investigación, estrategia y planificación

En el marco del programa de redes de investigación en docencia universitaria del Instituto de Ciencias de la Educación (ICE) del curso 2014-2015, se propuso la red “Publicidad en medios online: investigación, estrategia y planificación”. Tras los resultados del trabajo de la red del curso anterior se detectaron necesidades formativas que podrían ser estudiadas y cubiertas al año siguiente. Los medios digitales cambian la manera de hacer publicidad. Están presentes en muchas campañas, combinados con los offline o, incluso, siendo los únicos en la estrategia de medios. Adquieren, así, suficiente importancia en las fases de investigación, estrategia y planificación para que ocupen un lugar en los estudios de publicidad. En cambio, abordar la comunicación y publicidad online requeriría más dedicación de la que puede ser asumida en el Grado sin comprometer materia fundamental. Por ello, los MOOC se presentan como instrumentos útiles para complementar y reforzar los conocimientos trabajados en las clases. El propósito, por tanto, de la red es la adaptacion de los contenidos elaborados, resultado de la red del curso anterior, a las particularidades de un MOOC, partiendo de la investigación y del criterio académico para tratar de evitar condicionar la metodología docente a la tecnología desarrollada.

A three-dimensional representation method for noisy point clouds based on growing self-organizing maps accelerated on GPUs

The research described in this thesis was motivated by the need of a robust model capable of representing 3D data obtained with 3D sensors, which are inherently noisy. In addition, time constraints have to be considered as these sensors are capable of providing a 3D data stream in real time. This thesis proposed the use of Self-Organizing Maps (SOMs) as a 3D representation model. In particular, we proposed the use of the Growing Neural Gas (GNG) network, which has been successfully used for clustering, pattern recognition and topology representation of multi-dimensional data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models, without considering time constraints. It is proposed a hardware implementation leveraging the computing power of modern GPUs, which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). The proposed methods were applied to different problem and applications in the area of computer vision such as the recognition and localization of objects, visual surveillance or 3D reconstruction.

Contributions to 3D Data Registration and Representation

Nowadays, new computers generation provides a high performance that enables to build computationally expensive computer vision applications applied to mobile robotics. Building a map of the environment is a common task of a robot and is an essential part to allow the robots to move through these environments. Traditionally, mobile robots used a combination of several sensors from different technologies. Lasers, sonars and contact sensors have been typically used in any mobile robotic architecture, however color cameras are an important sensor due to we want the robots to use the same information that humans to sense and move through the different environments. Color cameras are cheap and flexible but a lot of work need to be done to give robots enough visual understanding of the scenes. Computer vision algorithms are computational complex problems but nowadays robots have access to different and powerful architectures that can be used for mobile robotics purposes. The advent of low-cost RGB-D sensors like Microsoft Kinect which provide 3D colored point clouds at high frame rates made the computer vision even more relevant in the mobile robotics field. The combination of visual and 3D data allows the systems to use both computer vision and 3D processing and therefore to be aware of more details of the surrounding environment. The research described in this thesis was motivated by the need of scene mapping. Being aware of the surrounding environment is a key feature in many mobile robotics applications from simple robotic navigation to complex surveillance applications. In addition, the acquisition of a 3D model of the scenes is useful in many areas as video games scene modeling where well-known places are reconstructed and added to game systems or advertising where once you get the 3D model of one room the system can add furniture pieces using augmented reality techniques. In this thesis we perform an experimental study of the state-of-the-art registration methods to find which one fits better to our scene mapping purposes. Different methods are tested and analyzed on different scene distributions of visual and geometry appearance. In addition, this thesis proposes two methods for 3d data compression and representation of 3D maps. Our 3D representation proposal is based on the use of Growing Neural Gas (GNG) method. This Self-Organizing Maps (SOMs) has been successfully used for clustering, pattern recognition and topology representation of various kind of data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models without considering time constraints. Self-organising neural models have the ability to provide a good representation of the input space. In particular, the Growing Neural Gas (GNG) is a suitable model because of its flexibility, rapid adaptation and excellent quality of representation. However, this type of learning is time consuming, specially for high-dimensional input data. Since real applications often work under time constraints, it is necessary to adapt the learning process in order to complete it in a predefined time. This thesis proposes a hardware implementation leveraging the computing power of modern GPUs which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). Our proposed geometrical 3D compression method seeks to reduce the 3D information using plane detection as basic structure to compress the data. This is due to our target environments are man-made and therefore there are a lot of points that belong to a plane surface. Our proposed method is able to get good compression results in those man-made scenarios. The detected and compressed planes can be also used in other applications as surface reconstruction or plane-based registration algorithms. Finally, we have also demonstrated the goodness of the GPU technologies getting a high performance implementation of a CAD/CAM common technique called Virtual Digitizing.