Projecte de botiga virtual de XsysPC

El projecte es basa en el desenvolupament d'una aplicació web per a la companyia fictícia XsysPC que ha decidit oferir la venta per Internet dels productes que tenen en les seves botigues, tals com ordinadors, components informàtics, perifèrics i altres.

Machine learning for geospatial data : algorithms, software tools and case studies

Résumé Cette thèse est consacrée à l'analyse, la modélisation et la visualisation de données environnementales à référence spatiale à l'aide d'algorithmes d'apprentissage automatique (Machine Learning). L'apprentissage automatique peut être considéré au sens large comme une sous-catégorie de l'intelligence artificielle qui concerne particulièrement le développement de techniques et d'algorithmes permettant à une machine d'apprendre à partir de données. Dans cette thèse, les algorithmes d'apprentissage automatique sont adaptés pour être appliqués à des données environnementales et à la prédiction spatiale. Pourquoi l'apprentissage automatique ? Parce que la majorité des algorithmes d'apprentissage automatiques sont universels, adaptatifs, non-linéaires, robustes et efficaces pour la modélisation. Ils peuvent résoudre des problèmes de classification, de régression et de modélisation de densité de probabilités dans des espaces à haute dimension, composés de variables informatives spatialisées (« géo-features ») en plus des coordonnées géographiques. De plus, ils sont idéaux pour être implémentés en tant qu'outils d'aide à la décision pour des questions environnementales allant de la reconnaissance de pattern à la modélisation et la prédiction en passant par la cartographie automatique. Leur efficacité est comparable au modèles géostatistiques dans l'espace des coordonnées géographiques, mais ils sont indispensables pour des données à hautes dimensions incluant des géo-features. Les algorithmes d'apprentissage automatique les plus importants et les plus populaires sont présentés théoriquement et implémentés sous forme de logiciels pour les sciences environnementales. Les principaux algorithmes décrits sont le Perceptron multicouches (MultiLayer Perceptron, MLP) - l'algorithme le plus connu dans l'intelligence artificielle, le réseau de neurones de régression généralisée (General Regression Neural Networks, GRNN), le réseau de neurones probabiliste (Probabilistic Neural Networks, PNN), les cartes auto-organisées (SelfOrganized Maps, SOM), les modèles à mixture Gaussiennes (Gaussian Mixture Models, GMM), les réseaux à fonctions de base radiales (Radial Basis Functions Networks, RBF) et les réseaux à mixture de densité (Mixture Density Networks, MDN). Cette gamme d'algorithmes permet de couvrir des tâches variées telle que la classification, la régression ou l'estimation de densité de probabilité. L'analyse exploratoire des données (Exploratory Data Analysis, EDA) est le premier pas de toute analyse de données. Dans cette thèse les concepts d'analyse exploratoire de données spatiales (Exploratory Spatial Data Analysis, ESDA) sont traités selon l'approche traditionnelle de la géostatistique avec la variographie expérimentale et selon les principes de l'apprentissage automatique. La variographie expérimentale, qui étudie les relations entre pairs de points, est un outil de base pour l'analyse géostatistique de corrélations spatiales anisotropiques qui permet de détecter la présence de patterns spatiaux descriptible par une statistique. L'approche de l'apprentissage automatique pour l'ESDA est présentée à travers l'application de la méthode des k plus proches voisins qui est très simple et possède d'excellentes qualités d'interprétation et de visualisation. Une part importante de la thèse traite de sujets d'actualité comme la cartographie automatique de données spatiales. Le réseau de neurones de régression généralisée est proposé pour résoudre cette tâche efficacement. Les performances du GRNN sont démontrées par des données de Comparaison d'Interpolation Spatiale (SIC) de 2004 pour lesquelles le GRNN bat significativement toutes les autres méthodes, particulièrement lors de situations d'urgence. La thèse est composée de quatre chapitres : théorie, applications, outils logiciels et des exemples guidés. Une partie importante du travail consiste en une collection de logiciels : Machine Learning Office. Cette collection de logiciels a été développée durant les 15 dernières années et a été utilisée pour l'enseignement de nombreux cours, dont des workshops internationaux en Chine, France, Italie, Irlande et Suisse ainsi que dans des projets de recherche fondamentaux et appliqués. Les cas d'études considérés couvrent un vaste spectre de problèmes géoenvironnementaux réels à basse et haute dimensionnalité, tels que la pollution de l'air, du sol et de l'eau par des produits radioactifs et des métaux lourds, la classification de types de sols et d'unités hydrogéologiques, la cartographie des incertitudes pour l'aide à la décision et l'estimation de risques naturels (glissements de terrain, avalanches). Des outils complémentaires pour l'analyse exploratoire des données et la visualisation ont également été développés en prenant soin de créer une interface conviviale et facile à l'utilisation. Machine Learning for geospatial data: algorithms, software tools and case studies Abstract The thesis is devoted to the analysis, modeling and visualisation of spatial environmental data using machine learning algorithms. In a broad sense machine learning can be considered as a subfield of artificial intelligence. It mainly concerns with the development of techniques and algorithms that allow computers to learn from data. In this thesis machine learning algorithms are adapted to learn from spatial environmental data and to make spatial predictions. Why machine learning? In few words most of machine learning algorithms are universal, adaptive, nonlinear, robust and efficient modeling tools. They can find solutions for the classification, regression, and probability density modeling problems in high-dimensional geo-feature spaces, composed of geographical space and additional relevant spatially referenced features. They are well-suited to be implemented as predictive engines in decision support systems, for the purposes of environmental data mining including pattern recognition, modeling and predictions as well as automatic data mapping. They have competitive efficiency to the geostatistical models in low dimensional geographical spaces but are indispensable in high-dimensional geo-feature spaces. The most important and popular machine learning algorithms and models interesting for geo- and environmental sciences are presented in details: from theoretical description of the concepts to the software implementation. The main algorithms and models considered are the following: multi-layer perceptron (a workhorse of machine learning), general regression neural networks, probabilistic neural networks, self-organising (Kohonen) maps, Gaussian mixture models, radial basis functions networks, mixture density networks. This set of models covers machine learning tasks such as classification, regression, and density estimation. Exploratory data analysis (EDA) is initial and very important part of data analysis. In this thesis the concepts of exploratory spatial data analysis (ESDA) is considered using both traditional geostatistical approach such as_experimental variography and machine learning. Experimental variography is a basic tool for geostatistical analysis of anisotropic spatial correlations which helps to understand the presence of spatial patterns, at least described by two-point statistics. A machine learning approach for ESDA is presented by applying the k-nearest neighbors (k-NN) method which is simple and has very good interpretation and visualization properties. Important part of the thesis deals with a hot topic of nowadays, namely, an automatic mapping of geospatial data. General regression neural networks (GRNN) is proposed as efficient model to solve this task. Performance of the GRNN model is demonstrated on Spatial Interpolation Comparison (SIC) 2004 data where GRNN model significantly outperformed all other approaches, especially in case of emergency conditions. The thesis consists of four chapters and has the following structure: theory, applications, software tools, and how-to-do-it examples. An important part of the work is a collection of software tools - Machine Learning Office. Machine Learning Office tools were developed during last 15 years and was used both for many teaching courses, including international workshops in China, France, Italy, Ireland, Switzerland and for realizing fundamental and applied research projects. Case studies considered cover wide spectrum of the real-life low and high-dimensional geo- and environmental problems, such as air, soil and water pollution by radionuclides and heavy metals, soil types and hydro-geological units classification, decision-oriented mapping with uncertainties, natural hazards (landslides, avalanches) assessments and susceptibility mapping. Complementary tools useful for the exploratory data analysis and visualisation were developed as well. The software is user friendly and easy to use.

Soil compaction by machine traffic and least limiting water range related to soybean yield

The research aimed to evaluate machine traffic effect on soil compaction and the least limiting water range related to soybean cultivar yields, during two years, in a Haplustox soil. The six treatments were related to tractor (11 Mg weight) passes by the same place: T0, no compaction; and T1*, 1; T1, 1; T2, 2; T4, 4 and T6, 6. In the treatment T1*, the compaction occurred when soil was dried, in 2003/2004, and with a 4 Mg tractor in 2004/2005. Soybean yield was evaluated in relation to soil compaction during two agricultural years in completely randomized design (compaction levels); however, in the second year, there was a factorial scheme (compaction levels, with and without irrigation), with four replicates represented by 9 m² plots. In the first year, soybean [Glycine max (L.) Merr.] cultivar IAC Foscarim 31 was cultivated without irrigation; and in the second year, IAC Foscarim 31 and MG/BR 46 (Conquista) cultivars were cultivated with and without irrigation. Machine traffic causes compaction and reduces soybean yield for soil penetration resistance between 1.64 to 2.35 MPa, and bulk density between 1.50 to 1.53 Mg m-3. Soil bulk density from which soybean cultivar yields decrease is lower than the critical one reached at least limiting water range (LLWR =/ 0).

Spanish E-Consumer Segmentation and Positioning in Virtual Supermarkets Sector

This article analyses different factors that influence the purchasing behaviour of online supermarket customers. These factors are related to both the appearance of the website as well as the processes that take place when making the purchase. Based on these analyses, the various groups of consumers with homogenous behaviour are studied and positioned according to their attitudes. The analysis also allows the quality of the service offered by this kind of establishment to be defined, as well as the main dimensions in which it develops. In the conclusions, factors which should influence the manager of an online supermarket to improve the quality of its service are given

Reconocimiento y representación digital de la notación matemática manual

El trabajo muestra un estudio comparativo de las soluciones que plantean diferentes soluciones comerciales y/o libres para la adecuación o no a su integración en un entorno como es el campus virtual de la UOC. Para esto se ha elaborado una lista de indicadores clave y más adelante se ha hecho una valoración de la integración en el entorno UOC, relacionando los indicadores anteriores con los requerimientos de la UOC. Investigando previamente cuales son estos. Por último se ha comprobado y corroborado la posible integración de la solución elegida al campus virtual, con el desarrollo de una pequeña aplicación web.

Moodleando en posgrado: uso del campus virtual y evaluación continuada

[spa] La adaptación al EEES ha implicado una reestructuración de los estudios universitarios promoviendo, entre otros, el uso de una evaluación continuada de los aprendizajes y de herramientas docentes virtuales en los nuevos grados. Estos cambios también pueden aplicarse en el posgrado, aunque hasta el momento, son pocas las experiencias al respecto. El presente trabajo muestra la opinión y los resultados obtenidos de los estudiantes de una asignatura de posgrado de un Máster Oficial Universitario URV-UB en el que se llevó a cabo evaluación continuada y se utilizó el Campus Virtual (CV) como herramienta de aprendizaje y participación activa. La aplicación del proyecto (2007PID/UB-14) se llevó a cabo en 4 fases: elaboración del aula, diseño de encuestas dirigidas a los estudiantes para obtener su opinión sobre la evaluación continuada y sus conocimientos en el uso de plataformas virtuales de forma previa al curso, gestión diaria del aula y seguimiento de las actividades propuestas y finalmente, evaluación del proyecto a través de indicadores cualitativos y cuantitativos derivados de las encuestas y de la propia aplicación virtual. Al inicio del curso la mayoría (93,75%) de los estudiantes prefería evaluación continuada y al final de éste el 100% estuvieron de acuerdo con el tipo de evaluación realizado. Respecto al CV, los estudiantes realizaron todas las actividades de autoevaluación voluntarias. La puntuación sobre la utilidad de todos los recursos del aula del CV fue muy elevada, siendo máxima la obtenida por los ejercicios de autoevaluación. En global, los estudiantes otorgaron al aula una puntuación de 8,1 sobre 10.

Moodleando en posgrado: uso del campus virtual y evaluación continuada

[spa] La adaptación al EEES ha implicado una reestructuración de los estudios universitarios promoviendo, entre otros, el uso de una evaluación continuada de los aprendizajes y de herramientas docentes virtuales en los nuevos grados. Estos cambios también pueden aplicarse en el posgrado, aunque hasta el momento, son pocas las experiencias al respecto. El presente trabajo muestra la opinión y los resultados obtenidos de los estudiantes de una asignatura de posgrado de un Máster Oficial Universitario URV-UB en el que se llevó a cabo evaluación continuada y se utilizó el Campus Virtual (CV) como herramienta de aprendizaje y participación activa. La aplicación del proyecto (2007PID/UB-14) se llevó a cabo en 4 fases: elaboración del aula, diseño de encuestas dirigidas a los estudiantes para obtener su opinión sobre la evaluación continuada y sus conocimientos en el uso de plataformas virtuales de forma previa al curso, gestión diaria del aula y seguimiento de las actividades propuestas y finalmente, evaluación del proyecto a través de indicadores cualitativos y cuantitativos derivados de las encuestas y de la propia aplicación virtual. Al inicio del curso la mayoría (93,75%) de los estudiantes prefería evaluación continuada y al final de éste el 100% estuvieron de acuerdo con el tipo de evaluación realizado. Respecto al CV, los estudiantes realizaron todas las actividades de autoevaluación voluntarias. La puntuación sobre la utilidad de todos los recursos del aula del CV fue muy elevada, siendo máxima la obtenida por los ejercicios de autoevaluación. En global, los estudiantes otorgaron al aula una puntuación de 8,1 sobre 10.

Visual realism enhances realistic response in an immersive virtual environment

Participants in an immersive virtual environment interact with the scene from an egocentric point of view that is, where there bodies appear to be located rather than from outside as if looking through a window. People interact through normal body movements, such as head-turning,reaching, and bending, and within the tracking limitations move through the environment or effect changes within it in natural ways.

A Threat to a Virtual Hand Elicits Motor Cortex Activation

We report an experiment where participants observed an attack on their virtual body as experienced in an immersive virtual reality (IVR) system. Participants sat by a table with their right hand resting upon it. In IVR, they saw a virtual table that was registered with the real one, and they had a virtual body that substituted their real body seen from a first person perspective. The virtual right hand was collocated with their real right hand. Event-related brain potentials were recorded in two conditions, one where the participant"s virtual hand was attacked with a knife and a control condition where the knife only struck the virtual table. Significantly greater P450 potentials were obtained in the attack condition confirming our expectations that participants had a strong illusion of the virtual hand being their own, which was also strongly supported by questionnaire responses. Higher levels of subjective virtual hand ownership correlated with larger P450 amplitudes. Mu-rhythm event-related desynchronization in the motor cortex and readiness potential (C3C4) negativity were clearly observed when the virtual hand was threatened as would be expected, if the real hand was threatened and the participant tried to avoid harm. Our results support the idea that event-related potentials may provide a promising non-subjective measure of virtual embodiment. They also support previous experiments on pain observation and are placed into context of similar experiments and studies of body perception and body ownership within cognitive neuroscience.

Correlations between Vocal Input and Visual Response Apparently Enhance Presence in a Virtual Environment

This work investigates novel alternative means of interaction in a virtual environment (VE).We analyze whether humans can remap established body functions to learn to interact with digital information in an environment that is cross-sensory by nature and uses vocal utterances in order to influence (abstract) virtual objects. We thus establish a correlation among learning, control of the interface, and the perceived sense of presence in the VE. The application enables intuitive interaction by mapping actions (the prosodic aspects of the human voice) to a certain response (i.e., visualization). A series of single-user and multiuser studies shows that users can gain control of the intuitive interface and learn to adapt to new and previously unseen tasks in VEs. Despite the abstract nature of the presented environment, presence scores were generally very high.

The relationship between virtual body ownership and temperature sensitivity.

In the rubber hand illusion tactile stimulation seen on a rubber hand, that is synchronous with tactile stimulation felt on the hidden real hand, can lead to an illusion of ownership over the rubber hand. This illusion has been shown to produce a temperature decrease in the hidden hand, suggesting that such illusory ownership produces disownership of the real hand. Here we apply immersive virtual reality (VR) to experimentally investigate this with respect to sensitivity to temperature change. Forty participants experienced immersion in a VR with a virtual body (VB) seen from a first person perspective. For half the participants the VB was consistent in posture and movement with their own body, and in the other half there was inconsistency. Temperature sensitivity on the palm of the hand was measured before and during the virtual experience. The results show that temperature sensitivity decreased in the consistent compared to the inconsistent condition. Moreover, the change in sensitivity was significantly correlated with the subjective illusion of virtual arm ownership but modulated by the illusion of ownership over the full virtual body. This suggests that a full body ownership illusion results in a unification of the virtual and real bodies into one overall entity - with proprioception and tactile sensations on the real body integrated with the visual presence of the virtual body. The results are interpreted in the framework of a"body matrix" recently introduced into the literature.

The effect of virtual reality on visual vertigo symptoms in patients with peripheral vestibular dysfunction: a pilot study.

Individuals with vestibular dysfunction may experience visual vertigo (VV), in which symptoms are provoked or exacerbated by excessive or disorientating visual stimuli (e.g. supermarkets). VV can significantly improve when customized vestibular rehabilitation exercises are combined with exposure to optokinetic stimuli. Virtual reality (VR), which immerses patients in realistic, visually challenging environments, has also been suggested as an adjunct to VR to improve VV symptoms. This pilot study compared the responses of sixteen patients with unilateral peripheral vestibular disorder randomly allocated to a VR regime incorporating exposure to a static (Group S) or dynamic (Group D) VR environment. Participants practiced vestibular exercises, twice weekly for four weeks, inside a static (Group S) or dynamic (Group D) virtual crowded square environment, presented in an immersive projection theatre (IPT), and received a vestibular exercise program to practice on days not attending clinic. A third Group D1 completed both the static and dynamic VR training. Treatment response was assessed with the Dynamic Gait Index and questionnaires concerning symptom triggers and psychological state. At final assessment, significant betweengroup differences were noted between Groups D (p = 0.001) and D1 (p = 0.03) compared to Group S for VV symptoms with the former two showing a significant 59.2% and 25.8% improvement respectively compared to 1.6% for the latter. Depression scores improved only for Group S (p = 0.01) while a trend towards significance was noted for Group D regarding anxiety scores (p = 0.07). Conclusion: Exposure to dynamic VR environments should be considered as a useful adjunct to vestibular rehabilitation programs for patients with peripheral vestibular disorders and VV symptoms.

Reinforcement learning utilizes proxemics: an avatar learns to manipulate the position of people in immersive virtual reality

A reinforcement learning (RL) method was used to train a virtual character to move participants to a specified location. The virtual environment depicted an alleyway displayed through a wide field-of-view head-tracked stereo head-mounted display. Based on proxemics theory, we predicted that when the character approached within a personal or intimate distance to the participants, they would be inclined to move backwards out of the way. We carried out a between-groups experiment with 30 female participants, with 10 assigned arbitrarily to each of the following three groups: In the Intimate condition the character could approach within 0.38m and in the Social condition no nearer than 1.2m. In the Random condition the actions of the virtual character were chosen randomly from among the same set as in the RL method, and the virtual character could approach within 0.38m. The experiment continued in each case until the participant either reached the target or 7 minutes had elapsed. The distributions of the times taken to reach the target showed significant differences between the three groups, with 9 out of 10 in the Intimate condition reaching the target significantly faster than the 6 out of 10 who reached the target in the Social condition. Only 1 out of 10 in the Random condition reached the target. The experiment is an example of applied presence theory: we rely on the many findings that people tend to respond realistically in immersive virtual environments, and use this to get people to achieve a task of which they had been unaware. This method opens up the door for many such applications where the virtual environment adapts to the responses of the human participants with the aim of achieving particular goals.

Drift and ownership toward a distant virtual body.

In body ownership illusions participants feel that a mannequin or virtual body (VB) is their own. Earlier results suggest that body ownership over a body seen from behind in extra personal space is possible when the surrogate body is visually stroked and tapped on its back, while spatially and temporal synchronous tactile stimulation is applied to the participant's back. This result has been disputed with the claim that the results can be explained by self-recognition rather than somatic body ownership. We carried out an experiment with 30 participants in a between-groups design. They all saw the back of a VB 1.2 m in front, that moved in real-time determined by upper body motion capture. All felt tactile stimulation on their back, and for 15 of them this was spatially and temporally synchronous with stimulation that they saw on the back of the VB, but asynchronous for the other 15. After 3 min a revolving fan above the VB descended and stopped at the position of the VB neck. A questionnaire assessed referral of touch to the VB, body ownership, the illusion of drifting forwards toward the VB, and the VB drifting backwards. Heart rate deceleration (HRD) and the amount of head movement during the threat period were used to assess the response to the threat from the fan. Results showed that although referral of touch was significantly greater in the synchronous condition than the asynchronous, there were no other differences between the conditions. However, a further multivariate analysis revealed that in the visuotactile synchronous condition HRD and head movement increased with the illusion of forward drift and decreased with backwards drift. Body ownership contributed positively to these drift sensations. Our conclusion is that the setup results in a contradiction-somatic feelings associated with a distant body-that the brain attempts to resolve by generating drift illusions that would make the two bodies coincide.