Structured output SVM for remote sensing image classification

In the recent years, kernel methods have revealed very powerful tools in many application domains in general and in remote sensing image classification in particular. The special characteristics of remote sensing images (high dimension, few labeled samples and different noise sources) are efficiently dealt with kernel machines. In this paper, we propose the use of structured output learning to improve remote sensing image classification based on kernels. Structured output learning is concerned with the design of machine learning algorithms that not only implement input-output mapping, but also take into account the relations between output labels, thus generalizing unstructured kernel methods. We analyze the framework and introduce it to the remote sensing community. Output similarity is here encoded into SVM classifiers by modifying the model loss function and the kernel function either independently or jointly. Experiments on a very high resolution (VHR) image classification problem shows promising results and opens a wide field of research with structured output kernel methods.

An efficient use of virtualization in grid/cloud environments

Grid is a hardware and software infrastructure that provides dependable, consistent, pervasive, and inexpensive access to high-end computational resources. Grid enables access to the resources but it does not guarantee any quality of service. Moreover, Grid does not provide performance isolation; job of one user can influence the performance of other user’s job. The other problem with Grid is that the users of Grid belong to scientific community and the jobs require specific and customized software environment. Providing the perfect environment to the user is very difficult in Grid for its dispersed and heterogeneous nature. Though, Cloud computing provide full customization and control, but there is no simple procedure available to submit user jobs as in Grid. The Grid computing can provide customized resources and performance to the user using virtualization. A virtual machine can join the Grid as an execution node. The virtual machine can also be submitted as a job with user jobs inside. Where the first method gives quality of service and performance isolation, the second method also provides customization and administration in addition. In this thesis, a solution is proposed to enable virtual machine reuse which will provide performance isolation with customization and administration. The same virtual machine can be used for several jobs. In the proposed solution customized virtual machines join the Grid pool on user request. Proposed solution describes two scenarios to achieve this goal. In first scenario, user submits their customized virtual machine as a job. The virtual machine joins the Grid pool when it is powered on. In the second scenario, user customized virtual machines are preconfigured in the execution system. These virtual machines join the Grid pool on user request. Condor and VMware server is used to deploy and test the scenarios. Condor supports virtual machine jobs. The scenario 1 is deployed using Condor VM universe. The second scenario uses VMware-VIX API for scripting powering on and powering off of the remote virtual machines. The experimental results shows that as scenario 2 does not need to transfer the virtual machine image, the virtual machine image becomes live on pool more faster. In scenario 1, the virtual machine runs as a condor job, so it easy to administrate the virtual machine. The only pitfall in scenario 1 is the network traffic.

Regional Advisory Committee on Cancer - Second Report 2002 (PDF 132 KB)

Regional Advisory Committee on Cancer (RACC) was established in 1997 to carry forward the recommendations of the Campbell Report of 1996 and to provide advice to the Department of Health and Social Services on the future development of cancer services. The Committee meets twice a year and its membership (Appendix I) is an indication of the wide range of interests involved in Cancer Care across the community. This report records some of the key developments in cancer services over the last 3 years. åÊ Significant progress has been made toward developing a high quality and integrated cancer care network. All five Cancer Units are now operational with chemotherapy and outpatient services for the most common forms of cancer are delivered from these locations. Agreement to the start of the new Cancer Centre, at the Belfast City Hospital, currently estimated to cost å£58m, is expected shortly. As a temporary expedient two additional therapy machines will be installed in Belvoir Park Hospital to increase capacity while the building of the new Cancer Centre proceeds. åÊ To deliver high quality cancer care the workforce needs to continue to expand. This requires increasing investment in the training of professional staff in the context of an already difficult HPSS labour market. The development of the five Cancer Units has increased staff mobility in the short-term, drawing skilled staff away from the centre who have been difficult to replace. At the same time increasing numbers of patients are being offered effective therapies at both the Cancer Units and the Centre. åÊ This report contains a review of selected developments in cancer care. The first section introduces the Memorandum of Understanding and the Tripartite Agreement between the National Cancer Institute of the USA and the Health Departments both North and South. This is a unique international partnership, which promises to bring very significant advantages to both the service and research communities across the Island. åÊ åÊ åÊ

Cinéma, machine à mondes : essai sur les films à univers multiples

Dans cet ouvrage, l'auteur propose une conceptualisation théorique de la coprésence en un même film de mondes multiples en abordant différents paramètres (hétérogénéité de la facture de l'image, pratiques du montage alterné, typologie des enchâssements, expansion sérielle, etc.) sur la base d'un corpus de films de fiction récents qui appartiennent pour la plupart au genre de la science-fiction (Matrix, Dark City, Avalon, Resident Evil, Avatar,...). Issue de la filmologie, la notion de « diégèse » y est développée à la fois dans le potentiel d'autonomisation dont témoigne la conception mondaine qui semble dominer aujourd'hui à l'ère des jeux vidéo, dans ses liens avec le récit et dans une perspective intermédiale. Les films discutés ont la particularité de mettre en scène des machines permettant aux personnages de passer d'un monde à l'autre : les modes de figuration de ces technologies sont investigués en lien avec les imaginaires du dispositif cinématographique et les potentialité du montage. La comparaison entre les films (Tron et son récent sequel, Totall Recall et son remake) et entre des oeuvres filmiques et littéraires (en particulier les nouvelles de Philip K. Dick et Simlacron 3 de Galouye) constitue un outil d'analyse permettant de saisir la contemporanéité de cette problématique, envisagée sur le plan esthétique dans le contexte de l'imagerie numérique.

Active Learning of Very-High Resolution Optical Imagery with SVM: Entropy vs Margin Sampling

An active learning method is proposed for the semi-automatic selection of training sets in remote sensing image classification. The method adds iteratively to the current training set the unlabeled pixels for which the prediction of an ensemble of classifiers based on bagged training sets show maximum entropy. This way, the algorithm selects the pixels that are the most uncertain and that will improve the model if added in the training set. The user is asked to label such pixels at each iteration. Experiments using support vector machines (SVM) on an 8 classes QuickBird image show the excellent performances of the methods, that equals accuracies of both a model trained with ten times more pixels and a model whose training set has been built using a state-of-the-art SVM specific active learning method

Ultrasound monitoring of structural urinary tract disease in Schistosoma haematobium infection

A major advance in our understanding of the natural history of Schistosoma haematobium-related morbidity has come through the introduction of the portable ultrasound machines for non-invasive examination of the kidneys and bladder. With the use of generators or battery packs to supply power in non-clinical field settings, and with the use of instant photography or miniaturized thermal printers to record permanent images, it is possible to examine scores of individuals in endemic communities every day. Broad-based ultrasound screening has allowed better definition of age-specific disease risks in urinary schistosomiasis. Results indicate that urinary tract abnormalities are common (18% overall prevalence) in S. haematobium transmission areas, with a 2-4% risk of either severe bladder abnormality or advanced ureteral obstruction. In longitudinal surveys, ultrasound studies have shown that praziquantel and metrifonate therapy are rapidly effective in reversing urinary tract abnormalities among children. The benefits of treating adults are less well known, but research in progress should help to define this issue. Similarly, the prognosis of specific ultrasound findings needs to be clarified, and the ease of sonographic examination will make such long-term follow-up studies feasible. In summary, the painless, quick, and reproducible ultrasound examination has become an essential tool in the study of urinary schistosomiasis.

Machine learning algorithms for spatial data. Case studies: Environmental pollution, natural hazards, renewable resources

This paper presents general problems and approaches for the spatial data analysis using machine learning algorithms. Machine learning is a very powerful approach to adaptive data analysis, modelling and visualisation. The key feature of the machine learning algorithms is that they learn from empirical data and can be used in cases when the modelled environmental phenomena are hidden, nonlinear, noisy and highly variable in space and in time. Most of the machines learning algorithms are universal and adaptive modelling tools developed to solve basic problems of learning from data: classification/pattern recognition, regression/mapping and probability density modelling. In the present report some of the widely used machine learning algorithms, namely artificial neural networks (ANN) of different architectures and Support Vector Machines (SVM), are adapted to the problems of the analysis and modelling of geo-spatial data. Machine learning algorithms have an important advantage over traditional models of spatial statistics when problems are considered in a high dimensional geo-feature spaces, when the dimension of space exceeds 5. Such features are usually generated, for example, from digital elevation models, remote sensing images, etc. An important extension of models concerns considering of real space constrains like geomorphology, networks, and other natural structures. Recent developments in semi-supervised learning can improve modelling of environmental phenomena taking into account on geo-manifolds. An important part of the study deals with the analysis of relevant variables and models' inputs. This problem is approached by using different feature selection/feature extraction nonlinear tools. To demonstrate the application of machine learning algorithms several interesting case studies are considered: digital soil mapping using SVM, automatic mapping of soil and water system pollution using ANN; natural hazards risk analysis (avalanches, landslides), assessments of renewable resources (wind fields) with SVM and ANN models, etc. The dimensionality of spaces considered varies from 2 to more than 30. Figures 1, 2, 3 demonstrate some results of the studies and their outputs. Finally, the results of environmental mapping are discussed and compared with traditional models of geostatistics.

GMODI : Gestión y mantenimiento Online de departamentos informáticos

La finalitat d'aquest projecte és la d'aconseguir d'una banda la gestió de recanvis per als equips informàtics de l'empresa tals com, tonners d'impressores làser i faxos, cartutxos de tinta, escàners i terminals de fàbrica i finalment impressores d'impressió tèrmica per a etiquetes dels productes de la nostra fàbrica. Per l'altre costat tindrem el manteniment dels equips informàtics de l'empresa, és dir els PC's de feina.

Estudi comparatiu de la gestió de memòria de dues màquines virtuals

En aquest projecte s'han comparat els gestors de memòria de les màquines virtuals de Java i del projecte Mono.

Coevolution of adaptive technology, maladaptive culture and population size in a producer-scrounger game.

Technology (i.e. tools, methods of cultivation and domestication, systems of construction and appropriation, machines) has increased the vital rates of humans, and is one of the defining features of the transition from Malthusian ecological stagnation to a potentially perpetual rising population growth. Maladaptations, on the other hand, encompass behaviours, customs and practices that decrease the vital rates of individuals. Technology and maladaptations are part of the total stock of culture carried by the individuals in a population. Here, we develop a quantitative model for the coevolution of cumulative adaptive technology and maladaptive culture in a 'producer-scrounger' game, which can also usefully be interpreted as an 'individual-social' learner interaction. Producers (individual learners) are assumed to invent new adaptations and maladaptations by trial-and-error learning, insight or deduction, and they pay the cost of innovation. Scroungers (social learners) are assumed to copy or imitate (cultural transmission) both the adaptations and maladaptations generated by producers. We show that the coevolutionary dynamics of producers and scroungers in the presence of cultural transmission can have a variety of effects on population carrying capacity. From stable polymorphism, where scroungers bring an advantage to the population (increase in carrying capacity), to periodic cycling, where scroungers decrease carrying capacity, we find that selection-driven cultural innovation and transmission may send a population on the path of indefinite growth or to extinction.

Ontologías Turísticas Geográficas : creación de una ontología sobre rutas turísticas (a Pie o en Bicicleta) por espacios naturales

El turismo es un área en constante crecimiento en la cual, la aparición de las nuevas tecnologías y, fundamentalmente, de Internet, ha tenido un gran impacto en los procedimientos internos de los agentes turísticos y en los métodos de contratación y de búsqueda de información por parte de los usuarios. Por otro lado, la cantidad ingente de información disponible en Internet y el gran desorden existente, provoca la aparición del concepto de Web semántica, una tecnología que dota a las máquinas de un nivel de compresión de la Web suficiente como para hacer de la búsqueda y el acceso a la información una tarea sencilla y natural. Este artículo trata, en primer lugar, de analizar el estado del arte de la Web semántica relacionada con el ámbito del turismo, presentando las ontologías turísticas disponibles en la actualidad para, a continuación, describir el desarrollo de una ontología específica dentro del dominio de las rutas turísticas. Con esta ontología, a través de un ejemplo, se trata de demostrar la utilidad de esta tecnología a la hora de catalogar información relacionada, disponible y dispersa por páginas Web en Internet.

Monitorización de la temperatura de un CPD mediante una red de sensores inalámbricos

Con este proyecto se pretende que una organización sea más consciente del estado de sus máquinas y anticiparse a una situación de pérdida de información, parada de servicios o parada por sobrecalentamiento de servidores.

Mejora diagnóstica de hepatopatías de afectación difusa mediante técnicas de inteligencia artificial

The automatic diagnostic discrimination is an application of artificial intelligence techniques that can solve clinical cases based on imaging. Diffuse liver diseases are diseases of wide prominence in the population and insidious course, yet early in its progression. Early and effective diagnosis is necessary because many of these diseases progress to cirrhosis and liver cancer. The usual technique of choice for accurate diagnosis is liver biopsy, an invasive and not without incompatibilities one. It is proposed in this project an alternative non-invasive and free of contraindications method based on liver ultrasonography. The images are digitized and then analyzed using statistical techniques and analysis of texture. The results are validated from the pathology report. Finally, we apply artificial intelligence techniques as Fuzzy k-Means or Support Vector Machines and compare its significance to the analysis Statistics and the report of the clinician. The results show that this technique is significantly valid and a promising alternative as a noninvasive diagnostic chronic liver disease from diffuse involvement. Artificial Intelligence classifying techniques significantly improve the diagnosing discrimination compared to other statistics.

GNU/Linux - Desenvolupaments intel·ligents : migració de sistemes Windows a Linux

L'empresa Desenvolupaments Intel·ligents es dedica a la creació del software financer i borsari. Tot el sistema informàtic esta basat en màquines amb plataformes Microsoft Windows. S'ha decidit implementar un nou sistema informàtic basat en GNU/Linux. Aquest és l'objecte d'aquest treball. El nou sistema informàtic basat en GNU/Linux ha de incloure tots els equips clients (que seran els ordinadors nous) i els servidors (es reaprofitaran els ordinadors antics) cobrint tots els serveis que abans donava el servidors antics mitjançant aquest sistema operatiu i software lliure.