CRACS - Book Chapters

Permanent URI for this collection

http://localhost:4000/handle/123456789/127

Browse

Browsing CRACS - Book Chapters by Title

  • Item
    Automated Diagnosis of Breast Cancer on Medical Images
    ( 2015) Velikova,M ; Inês Dutra ; Burnside,ES
  • Item
    Creating and analysing a social network built from clips of online news
    ( 2013) Álvaro Figueira
    Current online news media are increasingly depending on the participation of readers in their websites while readers increasingly use more sophisticated technology to access online news. In this context, the authors present the Breadcrumbs system and project that aims to provide news readers with tools to collect online news, to create a personal digital library (PDL) of clips taken from news, and to navigate not only on the own PDL, but also on external PDLs that relate to the first one. In this article, the authors present and describe the system and its paradigm for accessing news. We complement the description with the results from several tests which confirm the validity of our approach for clustering of news and for analysing the gathered data.
  • Item
    Design a computer programming learning environment for massive open online courses
    ( 2014) Ricardo Queirós
    Teaching and learning computer programming is as challenging as it is difficult. Assessing the work of students and providing individualised feedback is time-consuming and error prone for teachers and frequently involves a time delay. The existent tools prove to be insufficient in domains where there is a greater need to practice. At the same time, Massive Open Online Courses (MOOC) are appearing, revealing a new way of learning. However, this paradigm raises serious questions regarding the monitoring of student progress and its timely feedback. This chapter provides a conceptual design model for a computer programming learning environment. It uses the portal interface design model, gathering information from a network of services such as repositories, program evaluators, and learning management systems, a central piece in the MOOC realm. This model is not limited to the domain of computer programming and can be adapted to any area that requires evaluation with immediate feedback. © 2015, IGI Global.
  • Item
    Design and implementation of an IDE for learning programming languages using a gamification service
    ( 2016) José Carlos Paiva ; José Paulo Leal ; Ricardo Queirós
    This chapter presents the architecture and design of enki, an Integrated Development Environment (IDE) for learning programming languages on massive open online courses (moocs). this environment can be used as a tool by a learning management system (lms) and a typical lms such as moodle can launch it using the learning tool interoperability (lti) api. student authentication tokens are passed via lti, thus integrating enki in the single sign-on domain of the academic institution. the proposed tool has a web user interface similar to those of reference ides, where the learner has access to different integrated tools, from viewing tutorial videos, to solving programming exercises that are automatically evaluated. enki uses several gamification strategies to engage learners, including generic gamifications services provided by odin and the sequencing of educational resources. the course content (videos, pdfs, programming exercises) is progressively disclosed to the learner as he successfully completes exercises. this is similar to what happens in a game, where new levels are unlocked as the previous are completed, thus contributing to the sense of achievement.
  • Item
    Ensemble: An innovative approach to practice computer programming
    ( 2014) Ricardo Queirós ; José Paulo Leal
    Currently, the teaching-learning process in domains, such as computer programming, is characterized by an extensive curricula and a high enrolment of students. This poses a great workload for faculty and teaching assistants responsible for the creation, delivery, and assessment of student exercises. The main goal of this chapter is to foster practice-based learning in complex domains. This objective is attained with an e-learning framework-called Ensemble-as a conceptual tool to organize and facilitate technical interoperability among services. The Ensemble framework is used on a specific domain: computer programming. Content issues are tacked with a standard format to describe programming exercises as learning objects. Communication is achieved with the extension of existing specifications for the interoperation with several systems typically found in an e-learning environment. In order to evaluate the acceptability of the proposed solution, an Ensemble instance was validated on a classroom experiment with encouraging results. © 2015, IGI Global.
  • Item
    A mobile-based attribute aggregation architecture for user-centric identity management
    ( 2013) Augusto,AB ; Manuel Eduardo Correia
    The massive growth of the Internet and its services is currently being sustained by the mercantilization of users' identities and private data. Traditional services on the Web require the user to disclose many unnecessary sensitive identity attributes like bankcards, geographic position, or even personal health records in order to provide a service. In essence, the services are presented as free and constitute a means by which the user is mercantilized, often without realizing the real value of its data to the market. In this chapter the auhors describe OFELIA (Open Federated Environment for Leveraging of Identity and Authorization), a digital identity architecture designed from the ground up to be user centric. OFELIA is an identity/authorization versatile infrastructure that does not depend upon the massive aggregation of users' identity attributes to offer a highly versatile set of identity services but relies instead on having those attributes distributed among and protected by several otherwise unrelated Attribute Authorities. Only the end user, with his smartphone, knows how to aggregate these scattered Attribute Authorities' identity attributes back into some useful identifiable and authenticated entity identity that can then be used by Internet services in a secure and interoperable way.
  • Item
    Parallel Algorithms for Multirelational Data Mining: Application to Life Science Problems
    ( 2016) Rui Camacho ; Barbosa,JorgeG. ; Sampaio,AltinoM. ; Ladeiras,Joao ; Nuno Fonseca ; Vítor Santos Costa
  • Item
    Predicting Adverse Drug Events from Electronic Medical Records
    ( 2015) Davis,J ; Vítor Santos Costa ; Peissig,PL ; Caldwell,M ; Page,D
  • Item
    Predicting Ramp Events with a Stream-based HMM framework
    ( 2012) João Gama ; Audun Botterud ; Vladimiro Miranda ; Vítor Santos Costa ; Carlos Ferreira
    The motivation for this work is the study and prediction of wind ramp events occurring in a large-scale wind farm located in the US Midwest. In this paper we introduce the SHRED framework, a stream-based model that continuously learns a discrete HMM model from wind power and wind speed measurements. We use a supervised learning algorithm to learn HMM parameters from discretized data, where ramp events are HMM states and discretized wind speed data are HMM observations. The discretization of the historical data is obtained by running the SAX algorithm over the rst order variations in the original signal. SHRED updates the HMM using the most recent historical data and includes a forgetting mechanism to model natural time dependence in wind patterns. To forecast ramp events we use recent wind speed forecasts and the Viterbi algorithm, that incrementally nds the most probable ramp event to occur.
  • Item
    Predictive Sequence Miner in ILP Learning
    ( 2012) Vítor Santos Costa ; Carlos Ferreira ; João Gama
    This work presents an optimized version of XMuSer, an ILP based framework suitable to explore temporal patterns available in multi-relational databases. XMuSer's main idea consists of exploiting frequent sequence mining, an efficient method to learn temporal patterns in the form of sequences. XMuSer framework efficiency is grounded on a new coding methodology for temporal data and on the use of a predictive sequence miner. The frameworks selects and map the most interesting sequential patterns into a new table, the sequence relation. In the last step of our framework, we use an ILP algorithm to learn a classification theory on the enlarged relational database that consists of the original multi-relational database and the new sequence relation. We evaluate our framework by addressing three classification problems and map each one of three different types of sequential patterns: frequent, closed or maximal.
  • Item
    The present and future of privacy-preserving computation in fog computing
    ( 2017) Patrícia Raquel Sousa ; Luís Filipe Antunes ; Rolando Martins
  • Item
    Querying Volatile and Dynamic Networks
    ( 2014) Sarvenaz Choobdar ; Pedro Manuel Ribeiro ; Fernando Silva
  • Item
    Reducing simulation runtime in wireless sensor networks: A simulation framework to reduce wsn simulation runtime by using multiple simultaneous instances
    ( 2015) Pedro Filipe Pinto ; António Pinto ; Manuel Ricardo
    Wireless Sensor Networks (WSNs) can be deployed using available hardware and software. The Contiki is an operative system compatible with a wide range of WSN hardware. A Contiki development environment named InstantContiki is also available and includes the Cooja simulator, useful to test WSN simulation scenarios prior to their deployment. Cooja can provide realistic results since it uses the full Contiki's source code and some motes can be emulated at the hardware level. However this implies extending the simulation runtime, which is heightened since the Cooja is single threaded, i.e, it makes use of a single core per instant of time, not taking advantage of the current multi-core processors. This chapter presents a framework to automate the configuration and execution of Cooja simulations. When a multi-core processor is available, this framework runs multiple simultaneous Cooja instances to reduce simulations runtime in exchange of higher CPU load and RAM usage.
  • Item
    A survey on game backend services
    ( 2016) Ricardo Queirós
    The industry of video games is one of the fastest growing sectors in the worldwide economy. One of the key factors to increase engagement and player retention, was the use of various common game concepts such as leaderboards and achievements. The massive use of this approach and the impressive growth of players led to the concept of gamification as a service, later materialized in Game Backend as a Service (GBaaS). Instead of replicating the implementation of the game features in each version of the game for several platforms, GBaaS adhere to a service oriented architecture providing cross-platform game services that lets you easily integrate popular gaming features such as achievements, leaderboards, remote storage and real-time multiplayer in games. This chapter surveys several GBaaS based on the features they offer and on their openness for the integration with computer programming environments.