Search

Producción Científica, Driver’s gaze information can be crucial in driving research because of its relation to driver attention. Particularly, the inclusion of gaze data in driving simulators broadens the scope of research studies as they can relate drivers’ gaze patterns to their features and performance. In this paper, we present two gaze region estimation modules integrated in a driving simulator. One uses the 3D Kinect device and another uses the virtual reality Oculus Rift device. The modules are able to detect the region, out of seven in which the driving scene was divided, where a driver is gazing at in every route processed frame. Four methods were implemented and compared for gaze estimation, which learn the relation between gaze displacement and head movement. Two are simpler and based on points that try to capture this relation and two are based on classifiers such as MLP and SVM. Experiments were carried out with 12 users that drove on the same scenario twice, each one with a different visualization display, first with a big screen and later with Oculus Rift. On the whole, Oculus Rift outperformed Kinect as the best hardware for gaze estimation. The Oculus-based gaze region estimation method with the highest performance achieved an accuracy of 97.94%. The information provided by the Oculus Rift module enriches the driving simulator data and makes it possible a multimodal driving performance analysis apart from the immersion and realism obtained with the virtual reality experience provided by Oculus., Dirección General de Tráfico y Ministerio del Interior - (Proyecto SPIP2015-01801)

Producción Científica, Many of the next generation of adaptive optics systems on large and extremely large telescopes require tomographic techniques in order to correct for atmospheric turbulence over a large field of view. Multi-object adaptive optics is one such technique. In this paper, different implementations of a tomographic reconstructor based on a machine learning architecture named “CARMEN” are presented. Basic concepts of adaptive optics are introduced first, with a short explanation of three different control systems used on real telescopes and the sensors utilised. The operation of the reconstructor, along with the three neural network frameworks used, and the developed CUDA code are detailed. Changes to the size of the reconstructor influence the training and execution time of the neural network. The native CUDA code turns out to be the best choice for all the systems, although some of the other frameworks offer good performance under certain circumstances., Ministerio de Economía y Competitividad through grant AYA2014-57648-P, Gobierno del Principado de Asturias (Consejería de Economía y Empleo), through grant FC-15-GRUPIN14-017, This work is also funded by the UK Science and Technology Facilities Council, grant ST/K003569/1, and a consolidated grant ST/L00075X/1

In recent years, both growth of urban areas and trade expansion have increased freight traffic on the public roads. This increase in traffic affects transport companies, which suffers long delays in delivery of goods. Therefore, they experience degradation in service quality while increasing operating costs. Intelligent transportation systems have shown their potential to improve significantly the management and the operation of existing transportation systems (Siwek, 1998). Transport companies can benefit from using this technology to improve the quality of their services and to optimize the use of their resources. In order to increase the safety of their workers, these systems may also include the monitoring of the driver fatigue level, an important aspect considering that driver fatigue causes 60% of fatal accidents in which trucks are involved (AWAKE Consortium, 2004). The developed system meets these requirements by means of a corporative web site application where the whole telematics infrastructure of the service provider is hosted. The system has a fully customizable friendly-user interface based on Joomla!, which integrates a real-time geographic information system, in addition to other functions such as both customer management and dispatching scheduling for different user profiles (administrators, operators, managers, ...) in a company and different company profiles (backbone, retail, multimodal, etc.). Besides the usual real-time route guidance and communication functions, the on-board system incorporates an intelligent security control, which monitors driver fatigue and alertness level in real time. This functionality is accomplished by a computer vision system based on both face tracking and gesture recognition techniques. Collected data are processed to avoid accidents caused by driver distractions or sleepiness.

Mobile communication systems in clinical routine have the potential to greatly improve communication, facilitate healthcare information access (e.g. to Electronic Health Records (EHRs)), and increase the quality of patient attention (Ammenwerth, et al., 2000). Even more important with the advantage of mobility in the pocket, patients and physicians are able to carry with them their personal health records as they move across states or countries. Mobile health management seeks to extend the benefits of mobility to patients who are geographically mobile (Chan, 2000), but the development and use of mobile devices in health care is still rare; studies evaluating prototypes have revealed that the acceptance of such tools was rather low, although physicians principally would like to use a mobile EHR system (Reusss, et al., 2004). Mobile EHRs with high usability as outlined here would make a substantial contribution to reach this aim. Moreover, the development of mobile medical information systems is having significant impact on remote medical monitoring, home healthcare, outpatient service, and patient safety making healthcare more flexible and convenient. Mobile medical care services are gradually spreading in hospitals and with the maturity of mobile technology, the time has come for employing mobile healthcare in different school-based health centers (Jen, 2009). In this context, EHRs system contains information about the type of treatment that a patient has received from a healthcare provider, such as the patient’s medical history, etc. They are not just record-keeping tools but also play an important role in quality improvement and data exchange (Esper, et al., 2010). One major barrier to the adoption of such systems is the concern that EHRs may take longer for physicians to use than paper-based systems (Pizziferri, 2005). But, as the authors showed, EHRs did not require additional physician time during a primary care clinic session. Moreover, an EHR is a fundamental part of health information technology and its use is growing quickly. It can be defined as a set of relevant patient data stored in digital format that allows adequate medical assistance delivered to the patient even in different places and scenarios (Furuie, et al., 2007). It can be organized either on a document-based backbone, or on a structured database system. EHRs system fall under the purview of health informatics. It is a combination of computation, computer science and medical record keeping. In recognizing the advantages of EHRs, health information systems are being rapidly deployed. Some recent technological advances have enabled the introduction of an important number of e-health applications in healthcare computing (Hung and Zhang, 2003). Moreover, EHRs are increasingly being implemented by care

Understanding the brain functioning in visual process is one of the more active areas within neuroscience, modeling and computation. This great interest is due to the fact that vision provides us with the more important information about the surroundings. Oriented early filtering processes, perceptual clustering through emerging features, form and depth perception, figure-ground separation, and object recognition are all involved in the brain visual activity. Important researches have been undertaken to develop models simulating this brain behavior. So, neural models of visual perception biologically motivated in early vision tasks have been arisen versus others not biologically motivated computer vision algorithms. The knowledge about the early vision is notable and, accordingly, the neural modeling of the early vision tasks has been very scientifically productive. There are numerous visual models of the early visual perception (Kokkinos et al., 2007) (Neumann et al., 2007). One of the more significant is the BCS/FCS model of Grossberg and Mingolla (Grossberg & Mingolla, 1985). This model is composed of two systems, boundary contour system (BCS) and feature contour system (FCS), modeling processes given in the interactions among V1, V2 and V4 visual areas. Features so important in the human vision like illusory perception, emergent segmentations, diffusive filling-in are integrated in a coherent way in the BCS/FCS network. This system has experiment an important evolution in its modeling, integrating spatial and orientational competitive processes in a same stage (Mingolla et al., 1999). This model has been the framework of many other researchers in the development of their approaches. Kokkinos et al. (Kokkinos et al., 2008) have recently developed a computational simplification of the BCS/FCS model. They propound a threestage structure incorporating feature extraction with contrast normalization, boundary formation through a competitive stage of information of feature extraction, cooperative signal, anisotropic image smoothing and large scale signal. In their proposal, they include a comparison to Canny’s detector, a classical computer vision algorithm. Kokkinos’ architecture shows better results than Canny’s algorithm. Main contribution of Kokkinos’ is its simplification of the BCS/FCS model more than its evolution as it is somewhat complex.

This paper introduces the development of a customized virtual reality system based on a serious game which allows the user to carry out physical and cognitive rehabilitation therapies using a natural user interface based on Microsoft© Kinect. Within these serious games you can find the exergames. It is a type of serious game which aims to stimulate body mobility through an immersive experience that situates the user inside virtual interactive landscapes. This type of game has become popular in recent years thanks to the creation of consoles like Nintendo Wii, Playstation or Xbox, which use gestural interaction game interfaces. Likewise, these technologies have become extremely useful tools in rehabilitation, and they are expected to permit a reduction of costs in socio-sanitary environments. The proposed virtual reality platform consists of different types of exercises by which the user is able to train or rehabilitate several aspects such as strength, aerobic or cognitive capacities. The system has been modelled so that the physical presence of a therapist is not required during the course of the session and there is no need to wear any kind of marker or sensor. Moreover, all parameters of the different exercises can be configured without the physical presence of a therapist. The reports of each session can also be read offline, therefore, the therapist will always know if a user has performed the session in a good way and act accordingly modifying whatever he deems necessary in the patient's therapy. Due to these facts the system developed and presented in this article is a rehabilitation system based on remote assistance. It is important that this type of serious games accomplish all the functionalities a videogame fulfils at the same time that accomplish specific functionalities in its therapeutic environment. Remarkably, it is required an adaptation to the patient's abilities to avoid frustration and provide immediate feedback to the user during the exercises. In our system, the users are monitored and receive an audio-visual feedback during the session, so that they know in real-time if they are correctly doing the exercises of the specific therapy that was designed for them.