DP. OF SIGNAL THEORY, COMM AND TELEMATIC ENG.

A neural architecture for texture classification running on the Graphics Processing Unit (GPU) under a stream processing model is presented in this paper. Textural features extraction is done in three different scales, it is based on the computations that take place on the mammalian primary visual pathway and incorporates both structural and color information. Feature vectors classification is done using a fuzzy neural network which introduces pattern analysis for orientation invariant texture recognition. Performance tests are done over a varying number of textures and the entire VisTex database. The intrinsic parallelism of the neural system led us to implement the whole architecture to run on GPUs, providing a speed-up between ×16 and × 25 for classifying textures of sizes 128 × 128 and 512 × 512 px with respect to an implementation on the CPU. A comparison of classification rates obtained with other methods is included and shows the great performance of the architecture. An average classification rate of 85.2% is obtained for 167 textures of size 512 × 512 px.

The aim of this paper is to outline a multiple scale neural model to recognise colour images of textured scenes. This model combines colour and textural information in order to recognise colour texture images through the operation of two main components: a segmentation component composed of the colour opponent system (COS) and the chromatic segmentation system (CSS); and a recognition component formed by an ARTMAP-based neural network with scale and orientation-invariance properties. Segmentation is achieved by perceptual contour extraction and diffusion processes on the colour opponent channels based on the human psychophysical theory of colour perception. This colour regions enhancement along with their local textural features constitutes the recognition pattern to be sent to the supervised neural classifier. The CSS accomplishes the colour region enhancement through a multiple scale loop of oriented filters and competition-cooperation mechanisms. Afterwards, the neural architecture performs an attentive recognition of the scene using those oriented filters responses and the chromatic diffusions. Some comparative tests with other models are included in order to prove the recognition capabilities of this neural architecture and how the use of colour information encourages the texture classification and the accuracy of the boundary detection.

In this paper, we present a real time ellipse detector in gray scale images with a new multiple stage architecture based on a 3 accumulator version of the Fast Hough Transform with a previous Canny edge extraction. The system can be applied to detect different elliptical objects and is robust to incomplete ellipses, cluttered backgrounds and illumination changes. It achieves 12 frames per second on a PC Pen tium 4, 2.80 GHz. Experimental results, focusing on faces, with both static and video images are showed. The presented ellipse detector can be used as a preprocessing module in a face tracking or recognition appli cation.

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.

This paper describes the adaptation process to the European Credit Transfer System requirements of several subjects aiming at the Information and Communication Technologies (ICT) learning. Specifically, these subjects are sited at the Telecommunications Engineering studies lectured in the University of Valladolid. In a first step two first grade subjects have been established, while in a second and final step, coinciding with the new degrees beginning, it will be extended to five subjects placed in consecutive semesters.

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.

This paper introduces an Intelligent Transport System we called SigFlot, which is specially designed for fleet management, using dynamic information. Its main objective is to optimally manage the resources of a transport enterprise in order to achieve a safer and more efficient transport. The system consists of one set of modules which perform different jobs: communications (GSM/SMS), location (GPS), hiring / info through the Web, geographic information (GIS), route optimizing (Dijkstra algorithm and Taboo search). This application is fully developed in Java so it eases its portability to other platforms and OS.

Information theory allows us to investigate information processing in neural systems in terms of information transfer, storage and modification. Especially the measure of information transfer, transfer entropy, has seen a dramatic surge of interest in neuroscience. Estimating transfer entropy from two processes requires the observation of multiple realizations of these processes to estimate associated probability density functions. To obtain these necessary observations, available estimators typically assume stationarity of processes to allow pooling of observations over time. This assumption however, is a major obstacle to the application of these estimators in neuroscience as observed processes are often non-stationary. As a solution, Gomez-Herrero and colleagues theoretically showed that the stationarity assumption may be avoided by estimating transfer entropy from an ensemble of realizations. Such an ensemble of realizations is often readily available in neuroscience experiments in the form of experimental trials. Thus, in this work we combine the ensemble method with a recently proposed transfer entropy estimator to make transfer entropy estimation applicable to non-stationary time series. We present an efficient implementation of the approach that is suitable for the increased computational demand of the ensemble method's practical application. In particular, we use a massively parallel implementation for a graphics processing unit to handle the computationally most heavy aspects of the ensemble method for transfer entropy estimation. We test the performance and robustness of our implementation on data from numerical simulations of stochastic processes. We also demonstrate the applicability of the ensemble method to magnetoencephalographic data. While we mainly evaluate the proposed method for neuroscience data, we expect it to be applicable in a variety of fields that are concerned with the analysis of information transfer in complex biological, social, and artificial systems. Citation: Wollstadt P, Martínez-Zarzuela M, Vicente R, Díaz-Pernas FJ, Wibral M (2014) Efficient Transfer Entropy Analysis of Non-Stationary Neural Time Series. PLoS ONE 9(7): e102833.

In this paper we introduce, to the best of our knowledge, the first adaptation of the Fuzzy ARTMAP neural network for its execution on a GPU, together with a self-designed neural network based on ART models called SOON. The full VisTex database, containing 167 texture images, is proved to be classified in a very short time using these GPU-based neural networks. The Fuzzy ARTMAP neural network implemented on the GPU performs up to ×100 times faster than the equivalent CPU version, while the SOON neural network is speeded-up by ×70 times. Also, using the same texture patterns the Fuzzy ARTMAP neural network obtains a success rate of 48% and SOON of 82% for texture classification.

When tracking a human body, action recognition tasks can be performed to determine what kind of movement the person is performing. Although a lot of implementations have emerged, state-of-the-art technology such as depth cameras and intelligent systems can be used to b uild a robust system. This paper describes the process of building a system of this type, from the construction of the dataset to o btain the tracked motion information in the front-end, to the pattern classification backend. The tracking process is performed using the Microsoft(R) Kinect hardware, which allows a reliable way t o store the trajectories of subjects. Then, signal processing techniques are applied on these trajectories to build action patterns, which feed a Fuzzy-based Neural Network adapted to this purpose. Two different tests were conducted using the proposed system. Recognition among 5 whole body actions executed by 9 humans achieves 91.1% of success rate, while recognition among 10 actions is done with an accuracy of 81.1%.