Henrique Dinis dos Santos

Prediction of Abnormal Behaviors for Intelligent Video Surveillance Systems

The OBSERVER is a video surveillance system that detects and predicts abnormal behaviors aiming at the intelligent surveillance concept. The system acquires color images from a stationary video camera and applies state of the art algorithms to segment, track and classify moving objects. In this paper we present the behavior analysis module of the system. A novel method, called dynamic oriented graph (DOG) is used to detect and predict abnormal behaviors, using real-time unsupervised learning. The DOG method characterizes observed actions by means of a structure of unidirectional connected nodes, each one defining a region in the hyperspace of attributes measured from the observed moving objects and having assigned a probability to generate an abnormal behavior. An experimental evaluation with synthetic data was held, where the DOG method outperforms the previously used N-ary trees classifier

Moving object detection unaffected by cast shadows, highlights and ghosts

This paper describes a new approach to perform segmentation of moving objects in real-time from images acquired by a fixed color video camera and is the first tool of a major project that aspires to recognize abnormal human behavior in public areas. The moving objects detection is based on background subtraction and it is unaffected by changes in illumination, i.e., cast shadows and highlights. Furthermore it does not require a special attention during the initialization process, due to its ability to detect and rectify ghosts. The results show that with image resolutions of 380/spl times/280 at 24 bits per pixel, the time spent in the segmentation process is around 80 ms, in a 32 bits 3 GHz processor based computer.

The OBSERVER: an intelligent and automated video surveillance system

In this work we present a new approach to learn, detect and predict unusual and abnormal behaviors of people, groups and vehicles in real-time. The proposed OBSERVER video surveillance system acquires images from a stationary color video camera and applies state-of-the-art algorithms to segment and track moving objects. The segmentation is based in a background subtraction algorithm with cast shadows, highlights and ghost’s detection and removal. To robustly track objects in the scene, a technique based on appearance models was used. The OBSERVER is capable of identifying three types of behaviors (normal, unusual and abnormal actions). This achievement was possible due to the novel N-ary tree classifier, which was successfully tested on synthetic data.

Podcasts in Higher Education: Students’ and Lecturers’ Perspectives

This paper reports the use of podcasts in blended-learning at the University of Minho, in Portugal. Six lecturers created their own podcasts with different purposes in order to support their undergraduate and graduate courses and their students’ (n=318) learning. The reported study belongs to a broader project about the impact of podcasts in blended-learning and it reports data from two semesters. Results give evidence of students’ acceptance regarding podcasts although they do not yet make use of the advantages of media and mobile technologies. The lecturers considered podcasts worthwhile for teaching and for students to learn, but they are time-consuming and there is no institutional recognition. In spite of this, they intend to continue using podcasts in their courses.

Supervised learning classifier systems for grid data mining

This paper explores parallel and distributed implementation of the Learning Classifier System (LCS) technology. Specifically, the adaptation of supervised LCS to the grid data mining requisites, using the agent paradigm, is studied. The paper also examines the competitive data mining model induction possibility with homogeneous and heterogeneous data. A distributed framework is proposed using the grid computing architecture to make Supervised Classifier Systems (UCS) a more efficient distributed environment. This framework allows each local site (or agent) to employ a completely independent UCS. Local models (or UCSs populations) are transmitted occasionally to the global model for combination. The global model then represents a complete knowledge base of the overall classification problem.

Grid data mining by means of learning classifier systems and distributed model induction

This paper introduces a distributed data mining approach suited to grid computing environments based on a supervised learning classifier system. Different methods of merging data mining models generated at different distributed sites are explored. Centralized Data Mining (CDM) is a conventional method of data mining in distributed data. In CDM, data that is stored in distributed locations have to be collected and stored in a central repository before executing the data mining algorithm. CDM method is reliable; however it is expensive (computational, communicational and implementation costs are high). Alternatively, Distributed Data Mining (DDM) approach is economical but it has limitations in combining local models. In DDM, the data mining algorithm has to be executed at each one of the sites to induce a local model. Those induced local models are collected and combined to form a global data mining model. In this work six different tactics are used for constructing the global model in DDM: Generalized Classifier Method (GCM); Specific Classifier Method (SCM); Weighed Classifier Method (WCM); Majority Voting Method (MVM); Model Sampling Method (MSM); and Centralized Training Method (CTM). Preliminary experimental tests were conducted with two synthetic data sets (eleven multiplexer and monks3) and a real world data set (intensive care medicine). The initial results demonstrate that the performance of DDM methods is competitive when compared with the CDM methods.

Information Security Management: A Case Study in a Portuguese Military Organization

The authors present a Case Study conducted in a Portuguese military organization, to answer the following research questions: (1) what are the most relevant dimensions and categories of information security controls applied in military organizations? (2) What are the main scenarios of information security incidents that are expected to occur? (3) What is the decision process used for planning and selection information security controls? This study reveals that: (1) information security within the military organization is built on the basis of physical and human attack vectors, and targeting the infrastructure that supports the flow of information in the organization; (2) the information security controls applied in the military organization are included in ISO/IEC 27001; (3) planning and selection of applied information security controls are made by decision makers and information security specialists. It appears that specialists impose their planning options essentially seeking to select and retrieve past successful information security cases.

Framework de Gestão de Segurança da Informação para Organizações Militares Orientada pelos Principais Vetores de Ataque

Os sistemas distribuidos de âmbito alargado em modo inter-organizacional tem como requisitos base escalabilidade e paradigmas de controlo de acesso dinâmicos de gestao de utilizadores. Neste trabalho abordam-se cenarios de gestao de controlo de aceso numa perspectiva da gestao de confianca. Agregam-se e avaliam-se niveis de confianca a partir de dimensoes de confianca e e sugerido um esboco de uma framework para controlo de acessos baseados em confianca (TBAC - trust based access control) atraves de componentes standard.Este artigo tem por objetivo apresentar um Modelo para Recomendacao Personalizada de conteudos de aprendizagem, baseado numa estrategia de recomendacao hibrida e no perfil de cada aluno. Incluimos uma proposta para a similaridade entre alunos que reflete os seus interesses em termos das avaliacoes pretendidas e da proximidade das sequencias de atividades de aprendizagem dos diversos alunos. Este modelo preve, igualmente, a inclusao de novos conteudos por parte dos alunos e a definicao de relacionamentos com os conteudos existentes. Sao abordadas as motivacoes que nos levaram a presente proposta, alguns conceitos e trabalhos relacionados, assim como a arquitetura e desenho da solucao, entretanto alvo de prototipo. Por fim sao tecidas algumas conclusoes.A utilizacao de Sistemas de Informacao Geografica em processos de Participacao Publica (PPGIS) e uma area de estudo que tem vindo a assumir uma importância crescente no âmbito da Ciencia de Informacao Geografica. Passados 15 anos desde as primeiras referencias ao PPGIS, ocorreram profundas transformacoes, quer na forma como a Academia discute o tema, quer nas condicoes tecnologicas de desenvolvimento de aplicacoes, estas ultimas relacionadas com alteracoes ocorridas nas tecnologias de rede e com o surgimento de novas abordagens a Informacao Geografica no contexto da Neo-Geografia. No entanto, continua a existir um profundo hiato entre os modelos teoricos e a sua aplicacao nas praticas de Participacao Publica. Os resultados conhecidos da utilizacao de PPGIS em Portugal, nomeadamente em processos de Discussao Publica de PDM, sao desanimadores. Neste artigo apresenta-se uma reflexao sobre o tema, sustentada numa revisao do estado da arte, constituindo uma primeira abordagem para a descoberta de linhas de investigacao que possibilitem a identificacao e supressao de fragilidades dos modelos de integracao de aplicacoes PPGIS nos processos de Participacao Publica e contribuam para uma efetiva realizacao do seu potencial. Num momento da Historia em que os modelos de desenvolvimento e de organizacao social das democracias ocidentais sao questionados por cidadaos afetados por uma crise economica que ameaca transformar a sociedade, a recuperacao da credibilidade das instituicoes representativas podera passar por uma efetiva redistribuicao de poder atraves da incorporacao de mecanismos de democracia participativa. O PPGIS podera desempenhar, neste contexto, um importante papel.O desenvolvimento da internet e a expansao das redes sociais online introduziram mudancas significativas no modo como as pessoas se relacionam e comunicam. Estas mudancas, se refletidas ao nivel da educacao, poderao tambem ter o potencial de introduzir mudancas significativas a varios niveis. Entre estes destacam-se as possiveis alteracoes no processo de aprendizagem onde o uso dos servicos da Web 2.0 tem vindo a introduzir novas formas e metodos de trabalho, estimulando a comunicacao e a partilha de informacao e conhecimento abertamente ou em contextos definidos por grupos. Neste cenario de mudanca tem surgido plataformas integradas de servicos Web 2.0 com o objetivo de promover e disseminar a utilizacao deste tipo de servicos em contextos de Ensino Superior fomentando competencias sociais e de aprendizagem ao longo do percurso academico de uma comunidade academica de Ensino Superior. Este artigo tem por objetivo avaliar o reconhecimento de uma dessas plataformas, o SAPO Campus, apresentando os resultados de um estudo quantitativo e qualitativo no que respeita a sua notoriedade e utilizacao pelos varios elementos da comunidade academica da Instituicao de Ensino Superior em que se encontra instalada a referida plataforma. Os resultados apresentados permitem obter indicadores, a partir do interior da comunidade, sobre o seu conhecimento por parte dos elementos da comunidade academica e em que medida a utilizam. A partir da informacao recolhida pretende-se ainda estabelecer e delinear estrategias para melhorar a utilizacao e despertar o interesse para a sua utilizacao por parte dos elementos da comunidade que desconhecem este servico.No atual contexto da sociedade da informacao, muitas organizacoes procuram novas abordagens de producao, organizacao, circulacao e recuperacao da informacao, com recurso as novas Tecnologias de Informacao e Comunicacao (TIC). O presente trabalho procurou seguir esta abordagem, concretizando-se num projeto-piloto de desmaterializacao de processos que foi conduzido num departamento de uma instituicao de ensino superior (IES), ao mesmo tempo que se averiguavam as potencialidades das tecnologias open-source para aquele proposito. A desmaterializacao de processos implica a identificacao dos circuitos e fluxos de informacao, tipologias documentais envolvidas e responsabilidades associadas a cada atividade, no sentido de simplificar e racionalizar os procedimentos e consequentemente reajustar os fluxos de informacao. Foram estes alguns dos prossupostos que estiveram na origem do presente trabalho, tendo o mesmo sido operacionalizado com base numa abordagem de desenvolvimento estruturada, suportado em evidencias/Fatores Criticos de Sucesso (FCS) observadas em entidades com experiencia neste tipo de projetos e implementado com recurso a tecnologias open-source - Bonita Open Solution (BOS 5.6).

Methods of Organizational Information Security

The principle objective of this article is to present a literature review for the methods used in the security of information at the level of organizations. Some of the principle problems are identified and a first group of relevant di- mensions is presented for an efficient management of information security. The study is based on the literature review made, using some of the more relevant certified articles of this theme, in international reports and in the principle norms of management of information security. From the readings that were done, we identified some of the methods oriented for risk management, norms of certification and good practice of security of information. Some of the norms are oriented for the certification of the product or system and others oriented to the processes of the business. There are also studies with the proposal of Frameworks that suggest the integration of different approaches with the foun- dation of norms focused on technologies, in processes and taking into consid- eration the organizational and human environment of the organizations. In our perspective, the biggest contribute to the security of information is the devel- opment of a method of security of information for an organization in a conflict- ing environment. This should make available the security of information, against the possible dimensions of attack that the threats could exploit, through the vulnerability of the organizational actives. This method should support the new concepts of Network centric warfare, Information superiority and In- formation warfare especially developed in this last decade, where information is seen simultaneously as a weapon and as a target.