PDM 2006: Proceedings of the International Workshop on Data Mining

Recently major processor manufacturers have announced a dramatic shift in their paradigm to increase computing power over the coming years. Instead of focusing on faster clock speeds and more powerful single core CPUs, the trend clearly goes towards multi core systems. This will also result in a paradigm shift for the development of algorithms for computationally expensive tasks, such as data mining applications. Obviously, work on parallel algorithms is not new per se but concentrated efforts in the many application domains are still missing. Multi-core systems, but also clusters of workstations and even large-scale distributed computing infrastructures provide new opportunities and pose new challenges for the design of parallel and distributed algorithms. Since data mining and machine learning systems rely on high performance computing systems, research on the corresponding algorithms must be on the forefront of parallel algorithm research in order to keep pushing data mining and machine learning applications to be more powerful and, especially for the former, interactive. To bring together researchers and practitioners working in this exciting field, a workshop on parallel data mining was organized as part of PKDD/ECML 2006 (Berlin, Germany). The six contributions selected for the program describe various aspects of data mining and machine learning approaches featuring low to high degrees of parallelism: The first contribution focuses the classic problem of distributed association rule mining and focuses on communication efficiency to improve the state of the art. After this a parallelization technique for speeding up decision tree construction by means of thread-level parallelism for shared memory systems is presented. The next paper discusses the design of a parallel approach for dis- tributed memory systems of the frequent subgraphs mining problem. This approach is based on a hierarchical communication topology to solve issues related to multi-domain computational envi- ronments. The forth paper describes the combined use and the customization of software packages to facilitate a top down parallelism in the tuning of Support Vector Machines (SVM) and the next contribution presents an interesting idea concerning parallel training of Conditional Random Fields (CRFs) and motivates their use in labeling sequential data. The last contribution finally focuses on very efficient feature selection. It describes a parallel algorithm for feature selection from random subsets. Selecting the papers included in this volume would not have been possible without the help of an international Program Committee that has provided detailed reviews for each paper. We would like to also thank Matthew Otey who helped with publicity for the workshop.

Abstract platforms of computation

Computational formalisms have been pushing the boundaries of the field of computing for the last 80 years and much debate has surrounded what computing entails; what it is, and what it is not. This paper seeks to explore the boundaries of the ideas of computation and provide a framework for enabling a constructive discussion of computational ideas. First, a review of computing is given, ranging from Turing Machines to interactive computing. Then, a variety of natural physical systems are considered for their computational qualities. From this exploration, a framework is presented under which all dynamical systems can be considered as instances of the class of abstract computational platforms. An abstract computational platform is defined by both its intrinsic dynamics and how it allows computation that is meaningful to an external agent through the configuration of constraints upon those dynamics. It is asserted that a platform’s computational expressiveness is directly related to the freedom with which constraints can be placed. Finally, the requirements for a formal constraint description language are considered and it is proposed that Abstract State Machines may provide a reasonable basis for such a language.

Prediction of dynamical, nonlinear, and unstable process behavior

Process scheduling techniques consider the current load situation to allocate computing resources. Those techniques make approximations such as the average of communication, processing, and memory access to improve the process scheduling, although processes may present different behaviors during their whole execution. They may start with high communication requirements and later just processing. By discovering how processes behave over time, we believe it is possible to improve the resource allocation. This has motivated this paper which adopts chaos theory concepts and nonlinear prediction techniques in order to model and predict process behavior. Results confirm the radial basis function technique which presents good predictions and also low processing demands show what is essential in a real distributed environment.

Uma arquitetura para detecção online de transientes em sinais de eletrocardiograma sobre o protocolo IEEE 802.3 com PM-AH

The occurrence of transients in electrocardiogram (ECG) signals indicates an electrical phenomenon outside the heart. Thus, the identification of transients has been the most-used methodology in medical analysis since the invention of the electrocardiograph (device responsible for benchmarking of electrocardiogram signals). There are few papers related to this subject, which compels the creation of an architecture to do the pre-processing of this signal in order to identify transients. This paper proposes a method based on the signal energy of the Hilbert transform of electrocardiogram, being an alternative to methods based on morphology of the signal. This information will determine the creation of frames of the MP-HA protocol responsible for transmitting the ECG signals through an IEEE 802.3 network to a computing device. That, in turn, may perform a process to automatically sort the signal, or to present it to a doctor so that he can do the sorting manually

Macro Monte Carlo for dose calculation of proton beams

Although the Monte Carlo (MC) method allows accurate dose calculation for proton radiotherapy, its usage is limited due to long computing time. In order to gain efficiency, a new macro MC (MMC) technique for proton dose calculations has been developed. The basic principle of the MMC transport is a local to global MC approach. The local simulations using GEANT4 consist of mono-energetic proton pencil beams impinging perpendicularly on slabs of different thicknesses and different materials (water, air, lung, adipose, muscle, spongiosa, cortical bone). During the local simulation multiple scattering, ionization as well as elastic and inelastic interactions have been taken into account and the physical characteristics such as lateral displacement, direction distributions and energy loss have been scored for primary and secondary particles. The scored data from appropriate slabs is then used for the stepwise transport of the protons in the MMC simulation while calculating the energy loss along the path between entrance and exit position. Additionally, based on local simulations the radiation transport of neutrons and the generated ions are included into the MMC simulations for the dose calculations. In order to validate the MMC transport, calculated dose distributions using the MMC transport and GEANT4 have been compared for different mono-energetic proton pencil beams impinging on different phantoms including homogeneous and inhomogeneous situations as well as on a patient CT scan. The agreement of calculated integral depth dose curves is better than 1% or 1 mm for all pencil beams and phantoms considered. For the dose profiles the agreement is within 1% or 1 mm in all phantoms for all energies and depths. The comparison of the dose distribution calculated using either GEANT4 or MMC in the patient also shows an agreement of within 1% or 1 mm. The efficiency of MMC is up to 200 times higher than for GEANT4. The very good level of agreement in the dose comparisons demonstrate that the newly developed MMC transport results in very accurate and efficient dose calculations for proton beams.

Coping resources in a sample of chronic low back pain patients: Evaluation of the questionnaire for back pain

BACKGROUND The coping resources questionnaire for back pain (FBR) uses 12 items to measure the perceived helpfulness of different coping resources (CRs, social emotional support, practical help, knowledge, movement and relaxation, leisure and pleasure, spirituality and cognitive strategies). The aim of the study was to evaluate the instrument in a clinical patient sample assessed in a primary care setting. SAMPLE AND METHODS The study was a secondary evaluation of empirical data from a large cohort study in general practices. The 58 participating primary care practices recruited patients who reported chronic back pain in the consultation. Besides the FBR and a pain sketch, the patients completed scales measuring depression, anxiety, resilience, sociodemographic factors and pain characteristics. To allow computing of retested parameters the FBR was sent to some of the original participants again after 6 months (90% response rate). We calculated consistency and retest reliability coefficients as well as correlations between the FBR subscales and depression, anxiety and resilience scores to account for validity. By means of a cluster analysis groups with different resource profiles were formed. Results. RESULTS For the study 609 complete FBR baseline data sets could be used for statistical analysis. The internal consistency scores ranged fromα=0.58 to α=0.78 and retest reliability scores were between rTT=0.41 and rTT=0.63. Correlation with depression, fear and resilience ranged from r=-0.38 to r=0.42. The cluster analysis resulted in four groups with relatively homogenous intragroup profiles (high CRs, low spirituality, medium CRs, low CRs). The four groups differed significantly in fear and depression (the more inefficient the resources the higher the difference) as well as in resilience (the more inefficient the lower the difference). The group with low CRs also reported permanent pain with no relief. The groups did not otherwise differ. CONCLUSIONS The FBR is an economic instrument that is suitable for practical use e.g. in primary care practices to identify strengths and deficits in the CRs of chronic pain patients that can then be specified in face to face consultation. However, due to the rather low reliability, the use of subscales for profile differentiation and follow-up measurement in individual diagnoses is limited.

Virtual Infrastructures as a Service enabling Converged Optical Networks and Data Centres

Abstract Cloud computing service emerged as an essential component of the Enterprise {IT} infrastructure. Migration towards a full range and large-scale convergence of Cloud and network services has become the current trend for addressing requirements of the Cloud environment. Our approach takes the infrastructure as a service paradigm to build converged virtual infrastructures, which allow offering tailored performance and enable multi-tenancy over a common physical infrastructure. Thanks to virtualization, new exploitation activities of the physical infrastructures may arise for both transport network and Data Centres services. This approach makes network and Data Centres’ resources dedicated to Cloud Computing to converge on the same flexible and scalable level. The work presented here is based on the automation of the virtual infrastructure provisioning service. On top of the virtual infrastructures, a coordinated operation and control of the different resources is performed with the objective of automatically tailoring connectivity services to the Cloud service dynamics. Furthermore, in order to support elasticity of the Cloud services through the optical network, dynamic re-planning features have been provided to the virtual infrastructure service, which allows scaling up or down existing virtual infrastructures to optimize resource utilisation and dynamically adapt to users’ demands. Thus, the dynamic re-planning of the service becomes key component for the coordination of Cloud and optical network resource in an optimal way in terms of resource utilisation. The presented work is complemented with a use case of the virtual infrastructure service being adopted in a distributed Enterprise Information System, that scales up and down as a function of the application requests.

MEIA SYSTEMS: Membrane Encrypted Information Applications Systems

Membrane computing is a recent area that belongs to natural computing. This field works on computational models based on nature's behavior to process the information. Recently, numerous models have been developed and implemented with this purpose. P-systems are the structures which have been defined,developed and implemented to simulate the behavior and the evolution of membrane systems which we find in nature. What we show in this paper is a new model that deals with encrypted information which provides security the membrane systems communication. Moreover we find non deterministic and random applications in nature that are suitable to MEIA systems. The inherent parallelism and non determinism make this applications perfect object to implement MEIA systems.

Linewidth influence in photonics logic device

Photonics logic devices are currently finding applications in most of the fields where optical signals are employed. These areas range from optical communications to optical computing, covering as well as other applications in photonics sensing and metrology. Most of the proposed configurations with photonics logic devices are based on semiconductor laser structures with “on/off” behaviors, operating in an optical amplifier configuration. They are able to offer non-linear gain or bistable operation, being these properties the basis for their applications in these fields. Moreover, their large number of potential affecting parameters onto their behavior offers the possibility to choose the best solution for each case.

Supporting pruning in tabled LP

This paper analyzes issues which appear when supporting pruning operators in tabled LP. A version of the once/1 control predicate tailored for tabled predicates is presented, and an implementation analyzed and evaluated. Using once/1 with answer-on-demand strategies makes it possible to avoid computing unneeded solutions for problems which can benefit from tabled LP but in which only a single solution is needed, such as model checking and planning. The proposed version of once/1 is also directly applicable to the efficient implementation of other optimizations, such as early completion, cut-fail loops (to, e.g., prune at the top level), if-then-else, and constraint-based branch-and-bound optimization. Although once/1 still presents open issues such as dependencies of tabled solutions on program history, our experimental evaluation confirms that it provides an arbitrarily large efficiency improvement in several application areas.

Uncertainties in the modal estimation from output-only data in civil structures

Cualquier estructura vibra según unas frecuencias propias definidas por sus parámetros modales (frecuencias naturales, amortiguamientos y formas modales). A través de las mediciones de la vibración en puntos clave de la estructura, los parámetros modales pueden ser estimados. En estructuras civiles, es difícil excitar una estructura de manera controlada, por lo tanto, las técnicas que implican la estimación de los parámetros modales sólo registrando su respuesta son de vital importancia para este tipo de estructuras. Esta técnica se conoce como Análisis Modal Operacional (OMA). La técnica del OMA no necesita excitar artificialmente la estructura, atendiendo únicamente a su comportamiento en servicio. La motivación para llevar a cabo pruebas de OMA surge en el campo de la Ingeniería Civil, debido a que excitar artificialmente con éxito grandes estructuras no sólo resulta difícil y costoso, sino que puede incluso dañarse la estructura. Su importancia reside en que el comportamiento global de una estructura está directamente relacionado con sus parámetros modales, y cualquier variación de rigidez, masa o condiciones de apoyo, aunque sean locales, quedan reflejadas en los parámetros modales. Por lo tanto, esta identificación puede integrarse en un sistema de vigilancia de la integridad estructural. La principal dificultad para el uso de los parámetros modales estimados mediante OMA son las incertidumbres asociadas a este proceso de estimación. Existen incertidumbres en el valor de los parámetros modales asociadas al proceso de cálculo (internos) y también asociadas a la influencia de los factores ambientales (externas), como es la temperatura. Este Trabajo Fin de Máster analiza estas dos fuentes de incertidumbre. Es decir, en primer lugar, para una estructura de laboratorio, se estudian y cuantifican las incertidumbres asociadas al programa de OMA utilizado. En segundo lugar, para una estructura en servicio (una pasarela de banda tesa), se estudian tanto el efecto del programa OMA como la influencia del factor ambiental en la estimación de los parámetros modales. Más concretamente, se ha propuesto un método para hacer un seguimiento de las frecuencias naturales de un mismo modo. Este método incluye un modelo de regresión lineal múltiple que permite eliminar la influencia de estos agentes externos. A structure vibrates according to some of its vibration modes, defined by their modal parameters (natural frequencies, damping ratios and modal shapes). Through the measurements of the vibration at key points of the structure, the modal parameters can be estimated. In civil engineering structures, it is difficult to excite structures in a controlled manner, thus, techniques involving output-only modal estimation are of vital importance for these structure. This techniques are known as Operational Modal Analysis (OMA). The OMA technique does not need to excite artificially the structure, this considers its behavior in service only. The motivation for carrying out OMA tests arises in the area of Civil Engineering, because successfully artificially excite large structures is difficult and expensive. It also may even damage the structure. The main goal is that the global behavior of a structure is directly related to their modal parameters, and any variation of stiffness, mass or support conditions, although it is local, is also reflected in the modal parameters. Therefore, this identification may be within a Structural Health Monitoring system. The main difficulty for using the modal parameters estimated by an OMA is the uncertainties associated to this estimation process. Thus, there are uncertainties in the value of the modal parameters associated to the computing process (internal) and the influence of environmental factors (external), such as the temperature. This Master’s Thesis analyzes these two sources of uncertainties. That is, firstly, for a lab structure, the uncertainties associated to the OMA program used are studied and quantified. Secondly, for an in-service structure (a stress-ribbon footbridge), both the effect of the OMA program and the influence of environmental factor on the modal parameters estimation are studied. More concretely, a method to track natural frequencies of the same mode has been proposed. This method includes a multiple linear regression model that allows to remove the influence of these external agents.

Enhancing regression models for complex systems using evolutionary techniques for feature engineering

This work proposes an automatic methodology for modeling complex systems. Our methodology is based on the combination of Grammatical Evolution and classical regression to obtain an optimal set of features that take part of a linear and convex model. This technique provides both Feature Engineering and Symbolic Regression in order to infer accurate models with no effort or designer's expertise requirements. As advanced Cloud services are becoming mainstream, the contribution of data centers in the overall power consumption of modern cities is growing dramatically. These facilities consume from 10 to 100 times more power per square foot than typical office buildings. Modeling the power consumption for these infrastructures is crucial to anticipate the effects of aggressive optimization policies, but accurate and fast power modeling is a complex challenge for high-end servers not yet satisfied by analytical approaches. For this case study, our methodology minimizes error in power prediction. This work has been tested using real Cloud applications resulting on an average error in power estimation of 3.98%. Our work improves the possibilities of deriving Cloud energy efficient policies in Cloud data centers being applicable to other computing environments with similar characteristics.

Mobile assisted language learning : prototipo de la aplicación UP2B2

La forma de consumir contenidos en Internet ha cambiado durante los últimos años. Inicialmente se empleaban webs estáticas y con contenidos pobres visualmente. Con la evolución de las redes de comunicación, esta tendencia ha variado. A día de hoy, deseamos páginas agradables, accesibles y que nos presenten temas variados. Todo esto ha cambiado la forma de crear páginas web y en todos los casos se persigue el objetivo de atraer a los usuarios. El gran auge de los smartphones y las aplicaciones móviles que invaden el mercado actual han revolucionado el mundo del estudio de los idiomas permitiendo compatibilizar los recursos punteros con el aprendizaje tradicional. La popularidad de los dispositivos móviles y de las aplicaciones ha sido el principal motivo de la realización de este proyecto. En él se realizará un análisis de las diferentes tecnologías existentes y se elegirá la mejor opción que se ajuste a nuestras necesidades para poder desarrollar un sistema que implemente el enfoque llamado Mobile Assisted Language Learning (MALL) que supone una aproximación innovadora al aprendizaje de idiomas con la ayuda de un dispositivo móvil. En este documento se va a ofrecer una panorámica general acerca del desarrollo de aplicaciones para dispositivos móviles en el entorno del e-learning. Se estudiarán características técnicas de diferentes plataformas seleccionando la mejor opción para la implementación de un sistema que proporcione los contenidos básicos para el aprendizaje de un idioma, en este caso del inglés, de forma intuitiva y divertida. Dicho sistema permitirá al usuario mejorar su nivel de inglés mediante una interfaz web de forma dinámica y cercana empleando los recursos que ofrecen los dispositivos móviles y haciendo uso del diseño adaptativo. Este proyecto está pensado para los usuarios que dispongan de poco tiempo libre para realizar un curso de forma presencial o, mejor aún, para reforzar o repasar contenidos ya aprendidos por otros medios más tradicionales o no. La aplicación ofrece la posibilidad de que se haga uso del sistema de forma fácil y sencilla desde cualquier dispositivo móvil del que se disponga como es un smartphone, tablet o un ordenador personal, compitiendo con otros usuarios o contra uno mismo y mejorando así el nivel de partida a través de las actividades propuestas. Durante el proyecto se han comparado diversas soluciones, la mayoría de código abierto y de libre distribución que permiten desplegar servicios de almacenamiento accesibles mediante Internet. Se concluirá con un caso práctico analizando los requisitos técnicos y llevando a cabo las fases de análisis, diseño, creación de la base de datos, implementación y pruebas dentro del ciclo de vida del software. Finalmente, se migrará la aplicación con toda la información a un servidor en la nube. ABSTRACT. The way of consuming content on the Internet has changed over the past years. Initially, static websites were used with poor visual contents. Nevertheless, with the evolution of communication networks this trend has changed. Nowadays, we expect pleasant, accessible and varied topic pages and such expectations have changed the way to create web pages generally aiming at appealing and therefore, attracting users. The great boom of smartphones and mobile applications in the current market, have revolutionized the world of language learning as they make it possible to combine computing with traditional learning resources. The popularity of mobile devices and applications has been the main reason for the development of this project. Here, the different existing technologies will be examined and we will try to select the best option that adapts to our needs in order to develop a system that implements Mobile Assisted Language Learning (MALL) that in broad terms implies an approach to language learning with the help of a mobile device. This report provides an overview of the development of applications for mobile devices in the e-learning environment. We will study the technical characteristics of different platforms and we will select the best option for the implementation of a system that provide the basic content for learning a language, in this case English, by means of an intuitive and fun method. This system will allow the user to improve their level of English with a web interface in a dynamic and close way employing the resources offered by mobile devices using the adaptive design. This project is intended for users who do not have enough free time to make a classroom course or to review contents from more traditional courses as it offers the possibility to make use of the system quickly and easily from any mobile device available such as a smartphone, a tablet or a personal computer, competing with other users or against oneself and thus improving their departing level through different activities. During the project, different solutions have been compared. Most of them, open source and free distribution that allow to deploy storage services accessible via the Internet. It will conclude with a case study analyzing the technical requirements and conducting phases of analysis, design and creation of a database, implementation and testing in the software lifecycle. Finally, the application will be migrated with all the information to a server in the cloud.

On ANOVA Decompositions of Kernels and Gaussian Random Field Paths

The FANOVA (or “Sobol’-Hoeffding”) decomposition of multivariate functions has been used for high-dimensional model representation and global sensitivity analysis. When the objective function f has no simple analytic form and is costly to evaluate, computing FANOVA terms may be unaffordable due to numerical integration costs. Several approximate approaches relying on Gaussian random field (GRF) models have been proposed to alleviate these costs, where f is substituted by a (kriging) predictor or by conditional simulations. Here we focus on FANOVA decompositions of GRF sample paths, and we notably introduce an associated kernel decomposition into 4 d 4d terms called KANOVA. An interpretation in terms of tensor product projections is obtained, and it is shown that projected kernels control both the sparsity of GRF sample paths and the dependence structure between FANOVA effects. Applications on simulated data show the relevance of the approach for designing new classes of covariance kernels dedicated to high-dimensional kriging.

Semantic linking through spaces for cyber-physical-socio intelligence:a methodology

Humans consciously and subconsciously establish various links, emerge semantic images and reason in mind, learn linking effect and rules, select linked individuals to interact, and form closed loops through links while co-experiencing in multiple spaces in lifetime. Machines are limited in these abilities although various graph-based models have been used to link resources in the cyber space. The following are fundamental limitations of machine intelligence: (1) machines know few links and rules in the physical space, physiological space, psychological space, socio space and mental space, so it is not realistic to expect machines to discover laws and solve problems in these spaces; and, (2) machines can only process pre-designed algorithms and data structures in the cyber space. They are limited in ability to go beyond the cyber space, to learn linking rules, to know the effect of linking, and to explain computing results according to physical, physiological, psychological and socio laws. Linking various spaces will create a complex space — the Cyber-Physical-Physiological-Psychological-Socio-Mental Environment CP3SME. Diverse spaces will emerge, evolve, compete and cooperate with each other to extend machine intelligence and human intelligence. From multi-disciplinary perspective, this paper reviews previous ideas on various links, introduces the concept of cyber-physical society, proposes the ideal of the CP3SME including its definition, characteristics, and multi-disciplinary revolution, and explores the methodology of linking through spaces for cyber-physical-socio intelligence. The methodology includes new models, principles, mechanisms, scientific issues, and philosophical explanation. The CP3SME aims at an ideal environment for humans to live and work. Exploration will go beyond previous ideals on intelligence and computing.