The usefulness of ultrasound in the classification of chronic liver disease

Chronic Liver Disease is a progressive, most of the time asymptomatic, and potentially fatal disease. In this paper, a semi-automatic procedure to stage this disease is proposed based on ultrasound liver images, clinical and laboratorial data. In the core of the algorithm two classifiers are used: a k nearest neighbor and a Support Vector Machine, with different kernels. The classifiers were trained with the proposed multi-modal feature set and the results obtained were compared with the laboratorial and clinical feature set. The results showed that using ultrasound based features, in association with laboratorial and clinical features, improve the classification accuracy. The support vector machine, polynomial kernel, outperformed the others classifiers in every class studied. For the Normal class we achieved 100% accuracy, for the chronic hepatitis with cirrhosis 73.08%, for compensated cirrhosis 59.26% and for decompensated cirrhosis 91.67%.

Fatty liver characterization and classification by ultrasound

Steatosis, also known as fatty liver, corresponds to an abnormal retention of lipids within the hepatic cells and reflects an impairment of the normal processes of synthesis and elimination of fat. Several causes may lead to this condition, namely obesity, diabetes, or alcoholism. In this paper an automatic classification algorithm is proposed for the diagnosis of the liver steatosis from ultrasound images. The features are selected in order to catch the same characteristics used by the physicians in the diagnosis of the disease based on visual inspection of the ultrasound images. The algorithm, designed in a Bayesian framework, computes two images: i) a despeckled one, containing the anatomic and echogenic information of the liver, and ii) an image containing only the speckle used to compute the textural features. These images are computed from the estimated RF signal generated by the ultrasound probe where the dynamic range compression performed by the equipment is taken into account. A Bayes classifier, trained with data manually classified by expert clinicians and used as ground truth, reaches an overall accuracy of 95% and a 100% of sensitivity. The main novelties of the method are the estimations of the RF and speckle images which make it possible to accurately compute textural features of the liver parenchyma relevant for the diagnosis.

eTourismGUI - Adaptative Interface

Mestrado em Engenharia Informática. Área de Especialização em Tecnologias do Conhecimento e Decisão.

Facebook vs moodle : Surveying university students on the use of learning management systems to support learning activities outside the classroom

CISTI'2015 - 10ª Conferência Ibérica de Sistemas e Tecnologias de Informação, 17 a 20 de junho de 2015, Águeda, Aveiro, Portugal.

Integração de reacção e deliberação em agentes inteligentes

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia de Redes de Comunicação e Multimédia

Análise do sistema de tratamento de efluentes gasosos de uma central de valorização energética de resíduos sólidos urbanos

Trabalho Final de Mestrado para obtenção do grau de Mestre Em Engenharia Química e Biológica Ramo de processos Químicos

Controlo e optimização de sistemas AVAC recorrendo a técnicas de inteligência artificial

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia Mecânica

Mining protein structure data

The principal topic of this work is the application of data mining techniques, in particular of machine learning, to the discovery of knowledge in a protein database. In the first chapter a general background is presented. Namely, in section 1.1 we overview the methodology of a Data Mining project and its main algorithms. In section 1.2 an introduction to the proteins and its supporting file formats is outlined. This chapter is concluded with section 1.3 which defines that main problem we pretend to address with this work: determine if an amino acid is exposed or buried in a protein, in a discrete way (i.e.: not continuous), for five exposition levels: 2%, 10%, 20%, 25% and 30%. In the second chapter, following closely the CRISP-DM methodology, whole the process of construction the database that supported this work is presented. Namely, it is described the process of loading data from the Protein Data Bank, DSSP and SCOP. Then an initial data exploration is performed and a simple prediction model (baseline) of the relative solvent accessibility of an amino acid is introduced. It is also introduced the Data Mining Table Creator, a program developed to produce the data mining tables required for this problem. In the third chapter the results obtained are analyzed with statistical significance tests. Initially the several used classifiers (Neural Networks, C5.0, CART and Chaid) are compared and it is concluded that C5.0 is the most suitable for the problem at stake. It is also compared the influence of parameters like the amino acid information level, the amino acid window size and the SCOP class type in the accuracy of the predictive models. The fourth chapter starts with a brief revision of the literature about amino acid relative solvent accessibility. Then, we overview the main results achieved and finally discuss about possible future work. The fifth and last chapter consists of appendices. Appendix A has the schema of the database that supported this thesis. Appendix B has a set of tables with additional information. Appendix C describes the software provided in the DVD accompanying this thesis that allows the reconstruction of the present work.

Meta-heuristics self-parameterization in a multi-agent scheduling system using case-based reasoning

This paper proposes a novel agent-based approach to Meta-Heuristics self-configuration. Meta-heuristics are algorithms with parameters which need to be set up as efficient as possible in order to unsure its performance. A learning module for self-parameterization of Meta-heuristics (MH) in a Multi-Agent System (MAS) for resolution of scheduling problems is proposed in this work. The learning module is based on Case-based Reasoning (CBR) and two different integration approaches are proposed. A computational study is made for comparing the two CBR integration perspectives. Finally, some conclusions are reached and future work outlined.

Crossing genetic and swarm intelligence algorithms to generate logic circuits

Genetic Algorithms (GAs) are adaptive heuristic search algorithm based on the evolutionary ideas of natural selection and genetic. The basic concept of GAs is designed to simulate processes in natural system necessary for evolution, specifically those that follow the principles first laid down by Charles Darwin of survival of the fittest. On the other hand, Particle swarm optimization (PSO) is a population based stochastic optimization technique inspired by social behavior of bird flocking or fish schooling. PSO shares many similarities with evolutionary computation techniques such as GAs. The system is initialized with a population of random solutions and searches for optima by updating generations. However, unlike GA, PSO has no evolution operators such as crossover and mutation. In PSO, the potential solutions, called particles, fly through the problem space by following the current optimum particles. PSO is attractive because there are few parameters to adjust. This paper presents hybridization between a GA algorithm and a PSO algorithm (crossing the two algorithms). The resulting algorithm is applied to the synthesis of combinational logic circuits. With this combination is possible to take advantage of the best features of each particular algorithm.

Recomendação de conteúdos multimédia

A quantidade e variedade de conteúdos multimédia actualmente disponíveis cons- tituem um desafio para os utilizadores dado que o espaço de procura e escolha de fontes e conteúdos excede o tempo e a capacidade de processamento dos utilizado- res. Este problema da selecção, em função do perfil do utilizador, de informação em grandes conjuntos heterogéneos de dados é complexo e requer ferramentas específicas. Os Sistemas de Recomendação surgem neste contexto e são capazes de sugerir ao utilizador itens que se coadunam com os seus gostos, interesses ou necessidades, i.e., o seu perfil, recorrendo a metodologias de inteligência artificial. O principal objectivo desta tese é demonstrar que é possível recomendar em tempo útil conteúdos multimédia a partir do perfil pessoal e social do utilizador, recorrendo exclusivamente a fontes públicas e heterogéneas de dados. Neste sen- tido, concebeu-se e desenvolveu-se um Sistema de Recomendação de conteúdos multimédia baseado no conteúdo, i.e., nas características dos itens, no historial e preferências pessoais e nas interacções sociais do utilizador. Os conteúdos mul- timédia recomendados, i.e., os itens sugeridos ao utilizador, são provenientes da estação televisiva britânica, British Broadcasting Corporation (BBC), e estão classificados de acordo com as categorias dos programas da BBC. O perfil do utilizador é construído levando em conta o historial, o contexto, as preferências pessoais e as actividades sociais. O YouTube é a fonte do histo- rial pessoal utilizada, permitindo simular a principal fonte deste tipo de dados - a Set-Top Box (STB). O historial do utilizador é constituído pelo conjunto de vídeos YouTube e programas da BBC vistos pelo utilizador. O conteúdo dos vídeos do YouTube está classificado segundo as categorias de vídeo do próprio YouTube, sendo efectuado o mapeamento para as categorias dos programas da BBC. A informação social, que é proveniente das redes sociais Facebook e Twit- ter, é recolhida através da plataforma Beancounter. As actividades sociais do utilizador obtidas são filtradas para extrair os filmes e séries que são, por sua vez, enriquecidos semanticamente através do recurso a repositórios abertos de dados interligados. Neste caso, os filmes e séries são classificados através dos géneros da IMDb e, posteriormente, mapeados para as categorias de programas da BBC. Por último, a informação do contexto e das preferências explícitas, através da classificação dos itens recomendados, do utilizador são também contempladas. O sistema desenvolvido efectua recomendações em tempo real baseado nas actividades das redes sociais Facebook e Twitter, no historial de vídeos Youtube e de programas da BBC vistos e preferências explícitas. Foram realizados testes com cinco utilizadores e o tempo médio de resposta do sistema para criar o conjunto inicial de recomendações foi 30 s. As recomendações personalizadas são geradas e actualizadas mediante pedido expresso do utilizador.

Uso de Interfaces Cérebro-computador na comunicação de pessoas com Síndrome de Encarceramento

Os avanços nas Interfaces Cérebro-máquina, resultantes dos avanços no tratamento de sinal e da inteligência artificial, estão a permitir-nos aceder à atividade cerebral, descodificá-la, e usála para comandar dispositivos, sejam eles braços artificiais ou computadores. Isto é muito mais importante quando os utilizadores são pessoas que perderam a capacidade de comunicar, embora mantenham as suas capacidades cognitivas intactas. O caso mais extremo desta situação é o das pessoas afetadas pela Síndrome de Encarceramento. Este trabalho pretende contribuir para a melhoria da qualidade de vida das pessoas afetadas por esta síndrome, disponibilizando-lhes um meio de comunicação adaptado às suas limitações. É essencialmente um estudo de usabilidade aplicada a um tipo de utilizador extremamente diminuído na sua capacidade de interação. Nesta investigação começamos por compreender a Síndrome de Encarceramento e as limitações e capacidades das pessoas afetadas por ela. Abordamos a neuroplasticidade, o que é, e em que medida é importante para a utilização das Interfaces Cérebro-máquina. Analisamos o funcionamento destas interfaces, e os fundamentos científicos que o suportam. Finalmente, com todo este conhecimento em mãos, investigamos e desenvolvemos métodos que nos permitissem otimizar as limitadas capacidades do utilizador na sua interação com o sistema, minimizando o esforço e maximizando o desempenho. Foi para o efeito desenhado e implementado um protótipo que nos permitisse validar as soluções encontradas.

Towards Active Course Marks for Autonomous Sailing Competitions

This paper describes the environmental monitoring / regatta beacon buoy under development at the Laboratory of Autonomous Systems (LSA) of the Polytechnic Institute of Porto. On the one hand, environmentalmonitoring of open water bodies in real or deferred time is essential to assess and make sensible decisions and, on the other hand, the broadcast in real time of position, water and wind related parameters allows autonomous boats to optimise their regatta performance. This proposal, rather than restraining the boats autonomy, fosters the development of intelligent behaviour by allowing the boats to focus on regatta strategy and tactics. The Nautical and Telemetric Application (NAUTA) buoy is a dual mode reconfigurable system that includes communications, control, data logging, sensing, storage and power subsystems. In environmental monitoring mode, the buoy gathers and stores data from several underwater and above water sensors and, in regatta mode, the buoy becomes an active course mark for the autonomous sailing boats in the vicinity. During a race, the buoy broadcasts its position, together with the wind and the water current local conditions, allowing autonomous boats to navigate towards and round the mark successfully. This project started with the specification of the requirements of the dual mode operation, followed by the design and building of the buoy structure. The research is currently focussed on the development of the modular, reconfigurable, open source-based control system. The NAUTA buoy is innovative, extensible and optimises the on board platform resources.

Consistency and Context Management in a Multi Agent Belief Revision Testbed

Multi-agent architectures are well suited for complex inherently distributed problem solving domains. From the many challenging aspects that arise within this framework, a crucial one emerges: how to incorporate dynamic and conflicting agent beliefs? While the belief revision activity in a single agent scenario is concentrated on incorporating new information while preserving consistency, in a multi-agent system it also has to deal with possible conflicts between the agents perspectives. To provide an adequate framework, each agent, built as a combination of an assumption based belief revision system and a cooperation layer, was enriched with additional features: a distributed search control mechanism allowing dynamic context management, and a set of different distributed consistency methodologies. As a result, a Distributed Belief Revision Testbed (DiBeRT) was developed. This paper is a preliminary report presenting some of DiBeRT contributions: a concise representation of external beliefs; a simple and innovative methodology to achieve distributed context management; and a reduced inter-agent data exchange format.

Intelligent Distributed Environmental Decision Support System

This article discusses the development of an Intelligent Distributed Environmental Decision Support System, built upon the association of a Multi-agent Belief Revision System with a Geographical Information System (GIS). The inherent multidisciplinary features of the involved expertises in the field of environmental management, the need to define clear policies that allow the synthesis of divergent perspectives, its systematic application, and the reduction of the costs and time that result from this integration, are the main reasons that motivate the proposal of this project. This paper is organised in two parts: in the first part we present and discuss the developed Distributed Belief Revision Test-bed — DiBeRT; in the second part we analyse its application to the environmental decision support domain, with special emphasis on the interface with a GIS.