Miriam Antón Rodríguez

Fuzzy ART neural network parallel computing on the GPU

Graphics Processing Units (GPUs) have evolved into powerful programmable processors, faster than Central Processing Units (CPUs) regarding the execution of parallel algorithms. In this paper, an implementation of a Fuzzy ART Neural Network on the GPU is presented. Experimental results show training process is slower on the GPU than on a dual-core Pentium 4 at 3.2 GHz. Once the Neural Network has been trained, the proposed design manages to accelerate Fuzzy ART testing process up to 33 times on a GeForce 7800GT graphics card.

Mobile Serious Game using Augmented Reality for Supporting Children's Learning about Animals

This article introduces a new Serious Game with Augmented Reality for children and handicapped people. A platform based on a zoo has been virtually created. With this application, the users can increase their knowledge about a specific topic, in this case, animals. We have designed several 3D elements according to the theme, including a main scene that leads to the different scenes contained in the game. The user can interact with those elements and scenes through the mobile phone, thanks to the touch screen.

Educational Tourism through a Virtual Reality Platform

Abstract This article presents a Virtual Reality Serious Game that allows the user to increase the knowledge about the city of Valladolid in Spain. With this goal, the Main Square and some of the historic buildings in the downtown have been virtually recreated. We have taken advantage of the characteristic tiled floor of the town hall square to represent a game board. Different tiled floors are squares which hide questions behind. The user plays using a Natural User Interface based on Microsoft® Kinect.

Response Time Estimation of a Web-Based Electronic Health Record EHR System using Queuing Model

Response time measurement of a Web system is critically important to evaluate its performance. This response time is one of the main barriers usually found in the implementation of an effective Electronic Health Records EHRs system. The database selected will affect the system performance. This paper presents a comparison of the response times of a EHRs Web system, TeleOftalWeb, using different databases. In order to calculate these times, M/M/1 queuing models is used. Four databases were selected: Oracle 10g, dbXML 2.0, Xindice 1.2, and eXist 1.1.1. The final objective of the comparison is choosing the database system resulting in the lowest response time to TeleOftalWeb.

Real Time GPU-Based Fuzzy ART Skin Recognition

Graphics Processing Units (GPUs) have evolved into powerful programmable processors, becoming increasingly used in many research fields such as computer vision. For non-intrusive human body parts detection and tracking, skin filtering is a powerful tool. In this paper we propose the use of a GPU-designed implementation of a Fuzzy ART Neural Network for robust real-time skin recognition. Both learning and testing processes are done on the GPU using chrominance components in TSL color space. Within the GPU, classification of several pixels can be made simultaneously, allowing skin recognition at high frame rates. System performance depends both on video resolution and number of neural network committed categories. Our application can process 296 fps or 79 fps at video resolutions of 320x240 and 640x480 pixels respectively.