Navegación

Búsqueda

Búsqueda avanzada

El autor David Mera ha publicado 3 artículo(s):

1 - Diseño de Servidores de Adquisicíon y Publicacíon de Datos de Sensores

En este artículo proponemos el diseño e implementación de un framework para el desarrollo de servidores de adquisición y publicacíon de datos llamado DADIS. La estructura de DADIS está dividida en tres capas: i) una capa inferior de adquisicíon de datos que se encarga de la comunicacíon con los diferentes sensores, ii) una capa intermedia que constituye el núcleo del sistema y se encarga de proporcionar funcionalidad de propósito general, y iii) una capa superior de comunicacíon con aplicaciones de usuario. El uso extensivo del patrón de diseño Adapter (Wrapper) convierte a DADIS en una herramienta de propósito general extremadamente flexible en la incorporación tanto de nuevos canales síncronos y asíncronos de adquisicíon de datos como de nuevos servicios de publicacíon. Además, el uso del patrón Observer en la capa de comunicacíon con las aplicaciones de usuario permite que los servicios de publicacíon que se quieran incorporar puedan implementar tanto el modelo cliente/servidor como el modelo publicador/suscriptor.

Autores: Sebastían Villarroya / David Mera / Manuel A. Regueiro / José M. Cotos / 
Palabras Clave: Adquisicíon de Datos - Almacenamiento de Datos - Arquitectura de Sistemas - Control Distribuido - Monitorización - SCADA

2 - GeoHbbTV: A framework for the development and evaluation of geographic interactive TV contents

Synchronizing TV contents with applications is a topic thathas gained much interest during the last years. Reaching the viewers throughvarious channels (TV, web, mobile devices, etc.) has shown to bea means for increasing the audience. Related to the above, the hybridTV standard HbbTV (Hybrid Broadcast Broadband TV) synchronizesthe broadcast of video and audio with applications that may be deliveredthrough either the broadcast channel or a broadband network. Thus,HbbTV applications may be developed to provide contextual informationfor emitted TV shows and advertisements. This paper reports onthe integration of the automatic generation of geographic focus of textcontent with interactive TV. In particular it describes a framework forthe incorporation of geographic context to TV shows and its visualizationthrough HbbTV. To achieve this, geographic named entities are rstextracted from the available subtitles and next the spatial extension ofthose entities is used for the production of context maps. An evaluationstrategy has been devised and used to test alternative prototype implementationsfor TV newscast in Spanish language. Finally, to go beyondthe initial solution proposed, some challenges for future research are alsodiscussed.

Autores: David Luaces Cachaza / José R.R. Viqueira / Pablo Gamallo / David Mera / Julian Flores / 
Palabras Clave: Geographic annotation - Geographic tagging - Geographic visualization - HbbTV - Interactive TV

3 - Towards a Fast and Accurate EIT Inverse Problem Solver: A Machine Learning Approach

Different industrial and medical situations require the non-invasive extraction of information from the inside of bodies. This is usually done through tomographic methods that generate images based oninternal body properties. However, the image reconstruction involves a mathematical inverse problem, which accurate resolution demands large computation time and capacity. In this paper we explore the use of Machine Learning to develop an accurate solver for reconstructing Electrical Impedance Tomography images on real-time. We compare the results with the Iterative Gauss-Newton and the Primal Dual Interior Point Method, which are both largely used and well-validated solvers. The approaches were compared from the qualitative as well as the quantitative viewpoints. The former was focused on correctly detecting the internal body features. The latter was based on accurately predicting internalproperty distributions. Experiments revealed that our approach achieved better accuracy and Cohen’s kappa coefficient (97.57% and 94.60% respectively) from the qualitative viewpoint. Moreover, it also obtained better quantitative metrics with a Mean Absolute Percentage Error of 18.28%. Experiments confirmed that Neural Networks algorithms can reconstruct internal body properties with high accuracy, so they would be able to replace more complex and slower alternatives.

Autores: Xosé Fernández-Fuentes / David Mera / Andrés Gómez / Ignacio Vidal-Franco / 
Palabras Clave: Artificial neural networks - Conductivity - Electrical Impedance Tomography - Inverse Problems - Machine Learning