Statistical Models for Co-occurrence Data

Modeling and predicting co-occurrences of events is a fundamental problem of unsupervised learning. In this contribution we develop a statistical framework for analyzing co-occurrence data in a general setting where elementary observations are joint occurrences of pairs of abstract objects from two finite sets. The main challenge for statistical models in this context is to overcome the inherent data sparseness and to estimate the probabilities for pairs which were rarely observed or even unobserved in a given sample set. Moreover, it is often of considerable interest to extract grouping structure or to find a hierarchical data organization. A novel family of mixture models is proposed which explain the observed data by a finite number of shared aspects or clusters. This provides a common framework for statistical inference and structure discovery and also includes several recently proposed models as special cases. Adopting the maximum likelihood principle, EM algorithms are derived to fit the model parameters. We develop improved versions of EM which largely avoid overfitting problems and overcome the inherent locality of EM--based optimization. Among the broad variety of possible applications, e.g., in information retrieval, natural language processing, data mining, and computer vision, we have chosen document retrieval, the statistical analysis of noun/adjective co-occurrence and the unsupervised segmentation of textured images to test and evaluate the proposed algorithms.

MapFish. A WebGIS 2.0 Framework: toolkit to build rich client WebGIS

MapFish is an open-source development framework for building webmapping applications. MapFish is based on the OpenLayers API and the Geo extension of Ext library, and extends the Pylons general-purpose web development framework with geo-specific functionnalities. This presentation first describes what the MapFish development framework provides and how it can help developers implement rich web-mapping applications. It then demonstrates through real web-mapping realizations what can be achieved using MapFish : Geo Business Intelligence applications, 2D/3D data visualization, on/off line data edition, advanced vectorial print functionnalities, advanced administration suite to build WebGIS applications from scratch, etc. In particular, the web-mapping application for the UN Refugee Agency (UNHCR) and a Regional Spatial Data Infrastructure will be demonstrated

Recommender System Based on Consumer Product Reviews

Consumer reviews, opinions and shared experiences in the use of a product is a powerful source of information about consumer preferences that can be used in recommender systems. Despite the importance and value of such information, there is no comprehensive mechanism that formalizes the opinions selection and retrieval process and the utilization of retrieved opinions due to the difficulty of extracting information from text data. In this paper, a new recommender system that is built on consumer product reviews is proposed. A prioritizing mechanism is developed for the system. The proposed approach is illustrated using the case study of a recommender system for digital cameras

Modelo de segmentación : estudio, aplicación, ejecución y desarrollo de estrategias para la implementación de un modelo de clustering en el Sector Financiero

A finales de 2009 se emprendió un nuevo modelo de segmentación de mercados por conglomeraciones o clústers, con el cual se busca atender las necesidades de los clientes, advirtiendo el ciclo de vida en el cual se encuentran, realizando estrategias que mejoren la rentabilidad del negocio, por medio de indicadores de gestión KPI. Por medio de análisis tecnológico se desarrolló el proceso de inteligencia de la segmentación, por medio del cual se obtuvo el resultado de clústers, que poseían características similares entre sí, pero que diferían de los otros, en variables de comportamiento. Esto se refleja en el desarrollo de campañas estratégicas dirigidas que permitan crear una estrecha relación de fidelidad con el cliente, para aumentar la rentabilidad, en principio, y fortalecer la relación a largo plazo, respondiendo a la razón de ser del negocio

WAIS seminar: Alan Walks Wales: Data and Challenges

Abstract This seminar is a research discussion around a very interesting problem, which may be a good basis for a WAISfest theme. A little over a year ago Professor Alan Dix came to tell us of his plans for a magnificent adventure:to walk all of the way round Wales - 1000 miles 'Alan Walks Wales'. The walk was a personal journey, but also a technological and community one, exploring the needs of the walker and the people along the way. Whilst walking he recorded his thoughts in an audio diary, took lots of photos, wrote a blog and collected data from the tech instruments he was wearing. As a result Alan has extensive quantitative data (bio-sensing and location) and qualitative data (text, images and some audio). There are challenges in analysing individual kinds of data, including merging similar data streams, entity identification, time-series and textual data mining, dealing with provenance, ontologies for paths, and journeys. There are also challenges for author and third-party annotation, linking the data-sets and visualising the merged narrative or facets of it.

Evaluación Psicológica de la Toma de Decisiones Éticas de Riesgo en Entorno Organizacional: Revisión Teórica

Este trabajo de investigación explora el proceso de toma de decisiones fundamentado desde la perspectiva psicológica. El campo de interés está centrado en la toma de decisiones éticas a nivel organizacional y las consecuencias que las zonas grises o las conductas de riesgo repercuten en las dinámicas económicas y sociales. Con base en el análisis de los escándalos financieros más importantes de Europa, Estados Unidos y Colombia, y la literatura ofrecida por las ciencias sociales, la ética y las ciencias económicas se reconstruye una recopilación teórica de los aportes que los modelos psicológicos aplicados pueden dar al campo de la consultoría y el funcionamiento organizacional como también al estudio y análisis de los comportamientos anti éticos en empresas.

El Outsourcing en la dinámica de sistemas hacia mercados extranjeros

Este trabajo recopila literatura académica relevante sobre estrategias de entrada y metodologías para la toma de decisión sobre la contratación de servicios de Outsourcing para el caso de empresas que planean expandirse hacia mercados extranjeros. La manera en que una empresa planifica su entrada a un mercado extranjero, y realiza la consideración y evaluación de información relevante y el diseño de la estrategia, determina el éxito o no de la misma. De otro lado, las metodologías consideradas se concentran en el nivel estratégico de la pirámide organizacional. Se parte de métodos simples para llegar a aquellos basados en la Teoría de Decisión Multicriterio, tanto individuales como híbridos. Finalmente, se presenta la Dinámica de Sistemas como herramienta valiosa en el proceso, por cuanto puede combinarse con métodos multicriterio.

Gestão e trabalhadores do conhecimento em Tecnologias da informação (UML)

RESUMO: O conhecimento existe desde sempre, mesmo num estado latente condicionado algures e apenas à espera de um meio (de uma oportunidade) de se poder manifestar. O conhecimento é duplamente um fenómeno da consciência: porque dela procede num dado momento da sua vida e da sua história e porque só nela termina, aperfeiçoando-a e enriquecendo-a. O conhecimento está assim em constante mudança. À relativamente pouco tempo começou-se a falar de Gestão do Conhecimento e na altura foi muito associada às Tecnologias da Informação, como meio de colectar, processar e armazenar cada vez mais, maiores quantidades de informação. As Tecnologias da Informação têm tido, desde alguns anos para cá, um papel extremamente importante nas organizações, inicialmente foram adoptadas com o propósito de automatizar os processos operacionais das organizações, que suportam as suas actividades quotidianas e nestes últimos tempos as Tecnologias da Informação dentro das organizações têm evoluído rapidamente. Todo o conhecimento, mesmo até o menos relevante de uma determinada área de negócio, é fundamental para apoiar o processo de tomada de decisão. As organizações para atingirem melhores «performances» e conseguirem transcender as metas a que se propuseram inicialmente, tendem a munir-se de mais e melhores Sistemas de Informação, assim como, à utilização de várias metodologias e tecnologias hoje em dia disponíveis. Por conseguinte, nestes últimos anos, muitas organizações têm vindo a demonstrar uma necessidade crucial de integração de toda a sua informação, a qual está dispersa pelos diversos departamentos constituintes. Para que os gestores de topo (mas também para outros funcionários) possam ter disponível em tempo útil, informação pertinente, verdadeira e fiável dos negócios da organização que eles representam, precisam de ter acesso a bons Sistemas de Tecnologias de Informação. Numa acção de poderem agir mais eficazmente e eficientemente nas tomadas de decisão, por terem conseguido tirar por esses meios o máximo de proveito possível da informação, e assim, apresentarem melhores níveis de sucesso organizacionais. Também, os Sistemas de «Business Intelligence» e as Tecnologias da Informação a ele associadas, utilizam os dados existentes nas organizações para disponibilizar informação relevante para as tomadas de decisão. Mas, para poderem alcançar esses níveis tão satisfatórios, as organizações necessitam de recursos humanos, pois como podem elas serem competitivas sem Luís Miguel Borges – Gestão e Trabalhadores do Conhecimento em Tecnologias da Informação (UML) ULHT – ECATI 6 trabalhadores qualificados. Assim, surge a necessidade das organizações em recrutar os chamados hoje em dia “Trabalhadores do Conhecimento”, que são os indivíduos habilitados para interpretar as informações dentro de um domínio específico. Eles detectam problemas e identificam alternativas, com os seus conhecimentos e discernimento, eles trabalham para solucionar esses problemas, ajudando consideravelmente as organizações que representam. E, usando metodologias e tecnologias da Engenharia do Conhecimento como a modelação, criarem e gerirem um histórico de conhecimento, incluindo conhecimento tácito, sobre várias áreas de negócios da organização, que podem estar explícitos em modelos abstractos, que possam ser compreendidos e interpretados facilmente, por outros trabalhadores com níveis de competência equivalentes. ABSTRACT: Knowledge has always existed, even in a latent state conditioning somewhere and just waiting for a half (an opportunity) to be able to manifest. Knowledge is doubly a phenomenon of consciousness: because proceeds itself at one point in its life and its history and because solely itself ends, perfecting it and enriching it. The knowledge is so in constant change. In the relatively short time that it began to speak of Knowledge Management and at that time was very associated with Information Technologies, as a means to collect, process and store more and more, larger amounts of information. Information Technologies has had, from a few years back, an extremely important role in organizations, were initially adopted in order to automate the operational processes of organizations, that support their daily activities and in recent times Information Technologies within organizations has evolved rapidly. All the knowledge, even to the least relevant to a particular business area, is fundamental to support the process of decision making. The organizations to achieve better performances and to transcend the goals that were initially propose, tend to provide itself with more and better Information Systems, as well as, the use of various methodologies and technologies available today. Consequently, in recent years, many organizations have demonstrated a crucial need for integrating all their information, which is dispersed by the diver constituents departments. For top managers (but also for other employees) may have ready in time, pertinent, truthful and reliable information of the organization they represent, need access to good Information Technology Systems. In an action that they can act more effectively and efficiently in decision making, for having managed to get through these means the maximum possible advantage of the information, and so, present better levels of organizational success. Also, the systems of Business Intelligence and Information Technologies its associated, use existing data on organizations to provide relevant information for decision making. But, in order to achieve these levels as satisfactory, organizations need human resources, because how can they be competitive without skilled workers. Thus, arises the need for organizations to recruit called today “Knowledge Workers”, they are the individuals enable to interpret the information within a specific domain. They detect problems and identify alternatives, with their knowledge and discernment they work to solve these problems, helping considerably the organizations that represent. And, using Luís Miguel Borges – Gestão e Trabalhadores do Conhecimento em Tecnologias da Informação (UML) ULHT – ECATI 8 methodologies and technologies of Knowledge Engineering as modeling, create and manage a history of knowledge, including tacit knowledge, on various business areas of the organization, that can be explicit in the abstract models, that can be understood and interpreted easily, by other workers with equivalent levels of competence.

Implementação de um CRM analítico na Fundação INATEL

As soluções informáticas de Customer Relationship Management (CRM) e os sistemas de suporte à informação, designados por Business Intelligence (BI), permitem a recolha de dados e a sua transformação em informação e em conhecimento, vital para diferenciação das organizações num Mundo globalizado e em constante mudança. A construção de um Data Warehouse corporativo é fundamental para as organizações que utilizam vários sistemas operacionais de modo a ser possível a agregação da informação. A Fundação INATEL – uma fundação privada de interesse público, 100% estatal – é um exemplo deste tipo de organização. Com uma base de dados de clientes superior a 250.000, atuando em áreas tão diferentes como sejam o Turismo, a Cultura e o Desporto, sustentado em mais de 25 sistemas informáticos autónomos. A base de estudo deste trabalho é a procura de identificação dos benefícios da implementação de um CRM Analítico na Fundação INATEL. Apresentando-se assim uma metodologia para a respetiva implementação e sugestão de um modelo de dados para a obtenção de uma visão única do cliente, acessível a toda a organização, de modo a garantir a total satisfação e consequente fidelização à marca INATEL. A disponibilização desta informação irá proporcionar um posicionamento privilegiado da Fundação INATEL e terá um papel fundamental na sua sustentabilidade económica.

Context-aware visual exploration of molecular databases

Facilitating the visual exploration of scientific data has received increasing attention in the past decade or so. Especially in life science related application areas the amount of available data has grown at a breath taking pace. In this paper we describe an approach that allows for visual inspection of large collections of molecular compounds. In contrast to classical visualizations of such spaces we incorporate a specific focus of analysis, for example the outcome of a biological experiment such as high throughout screening results. The presented method uses this experimental data to select molecular fragments of the underlying molecules that have interesting properties and uses the resulting space to generate a two dimensional map based on a singular value decomposition algorithm and a self organizing map. Experiments on real datasets show that the resulting visual landscape groups molecules of similar chemical properties in densely connected regions.

Scalability of efficient parallel K-Means

Clustering is defined as the grouping of similar items in a set, and is an important process within the field of data mining. As the amount of data for various applications continues to increase, in terms of its size and dimensionality, it is necessary to have efficient clustering methods. A popular clustering algorithm is K-Means, which adopts a greedy approach to produce a set of K-clusters with associated centres of mass, and uses a squared error distortion measure to determine convergence. Methods for improving the efficiency of K-Means have been largely explored in two main directions. The amount of computation can be significantly reduced by adopting a more efficient data structure, notably a multi-dimensional binary search tree (KD-Tree) to store either centroids or data points. A second direction is parallel processing, where data and computation loads are distributed over many processing nodes. However, little work has been done to provide a parallel formulation of the efficient sequential techniques based on KD-Trees. Such approaches are expected to have an irregular distribution of computation load and can suffer from load imbalance. This issue has so far limited the adoption of these efficient K-Means techniques in parallel computational environments. In this work, we provide a parallel formulation for the KD-Tree based K-Means algorithm and address its load balancing issues.

Dynamic load balancing in parallel KD-tree k-means

One among the most influential and popular data mining methods is the k-Means algorithm for cluster analysis. Techniques for improving the efficiency of k-Means have been largely explored in two main directions. The amount of computation can be significantly reduced by adopting geometrical constraints and an efficient data structure, notably a multidimensional binary search tree (KD-Tree). These techniques allow to reduce the number of distance computations the algorithm performs at each iteration. A second direction is parallel processing, where data and computation loads are distributed over many processing nodes. However, little work has been done to provide a parallel formulation of the efficient sequential techniques based on KD-Trees. Such approaches are expected to have an irregular distribution of computation load and can suffer from load imbalance. This issue has so far limited the adoption of these efficient k-Means variants in parallel computing environments. In this work, we provide a parallel formulation of the KD-Tree based k-Means algorithm for distributed memory systems and address its load balancing issue. Three solutions have been developed and tested. Two approaches are based on a static partitioning of the data set and a third solution incorporates a dynamic load balancing policy.

Adaptive modelling, estimation and fusion from data: a neurofuzzy approach

In a world of almost permanent and rapidly increasing electronic data availability, techniques of filtering, compressing, and interpreting this data to transform it into valuable and easily comprehensible information is of utmost importance. One key topic in this area is the capability to deduce future system behavior from a given data input. This book brings together for the first time the complete theory of data-based neurofuzzy modelling and the linguistic attributes of fuzzy logic in a single cohesive mathematical framework. After introducing the basic theory of data-based modelling, new concepts including extended additive and multiplicative submodels are developed and their extensions to state estimation and data fusion are derived. All these algorithms are illustrated with benchmark and real-life examples to demonstrate their efficiency. Chris Harris and his group have carried out pioneering work which has tied together the fields of neural networks and linguistic rule-based algortihms. This book is aimed at researchers and scientists in time series modeling, empirical data modeling, knowledge discovery, data mining, and data fusion.