695 research outputs found
Deep Learning Approaches in Pandemic and Disaster Management
No full textA quick decision-making process in response and management of epidemics has been the most common approach, as accurate and relevant decisions have been demonstrated to have beneficial impacts on life preservation as well as on global and local economies. However, any disaster or epidemic is rarely represented by a set of single and linear parameters, as they often exhibit highly complex and chaotic behaviours, where interconnected unknowns rapidly evolve. As a consequence, any such decision-making approach must be computationally robust and able to process large amounts of data, whilst evaluating the potential outcomes based on specific decisions in real time
Utilizing next generation emerging technologies for enabling collective computational intelligence in disaster management
No full textMuch work is underway within the broad next generation emerging technologies community on issues associated with the development of services to foster synergies and collaboration via the integration of distributed and heterogeneous resources, systems and technologies. In this chapter, we discuss how these could help coin and prompt future direction of their fit-to-purpose use in various real-world scenarios including the proposed case of disaster management. Within this context, we start with a brief overview of these technologies highlighting their applicability in various settings. In particular, we review the possible combination of next generation emerging technologies such as ad-hoc and sensor networks, grids, clouds, crowds and peer to peer with intelligence techniques such as multi-agents, evolutionary computation and swarm intelligence for augmenting computational intelligence in a collective manner for the purpose of managing disasters. We then conclude by illustrating a relevant model architecture and by presenting our future implementation strategy. © 2011 Springer-Verlag Berlin Heidelberg
Internet of Things and Inter-cooperative Computational Technologies for Collective Intelligence
No full textOver the past two decades, we have witnessed unprecedented innovations in the development of miniaturized electromechanical devices and low-power wireless communication making practical the embedding of networked computational devices into a rapidly widening range of material entities. This trend has enabled the coupling of physical objects and digital information into cyber-physical systems and it is widely expected to revolutionize the way resource computational consumption and provision will occur. Specifically, one of the core ingredients of this vision, the so-called Internet of Things (IoT), demands the provision of networked services to support interaction between conventional IT systems with both physical and artificial objects. In this way, IoT is seen as a combination of several emerging technologies, which enables the transformation of everyday objects into smart objects. It is also perceived as a paradigm that connects real world with digital world. The focus of this book is on the novel collective and computational intelligence technologies that will be required to achieve this goal. While, one of the aims of this book is to discuss the progress made, it also prompts future directions on the utilization of inter-operable and cooperative next generation computational technologies, which supports the IoT approach, that being an advanced functioning towards an integrated collective intelligence approach for the benefit of various organizational settings.
Automated extraction of fragments of Bayesian networks from textual sources
No full textMining large amounts of unstructured data for extracting meaningful, accurate, and actionable information, is at the core of a variety of research disciplines including computer science, mathematical and statistical modelling, as well as knowledge engineering. In particular, the ability to model complex scenarios based on unstructured datasets is an important step towards an integrated and accurate knowledge extraction approach. This would provide a significant insight in any decision making process driven by Big Data analysis activities. However, there are multiple challenges that need to be fully addressed in order to achieve this, especially when large and unstructured data sets are considered. In this article we propose and analyse a novel method to extract and build fragments of Bayesian networks (BNs) from unstructured large data sources. The results of our analysis show the potential of our approach, and highlight its accuracy and efficiency. More specifically, when compared with existing approaches, our method addresses specific challenges posed by the automated extraction of BNs with extensive applications to unstructured and highly dynamic data sources. The aim of this work is to advance the current state-of-the-art approaches to the automated extraction of BNs from unstructured datasets, which provide a versatile and powerful modelling framework to facilitate knowledge discovery in complex decision scenarios
A Comparison of Two Different Approaches to Cloud Monitoring
No full textMonitoring is a relevant issues above all for customers of Public Clouds. In fact they need to detect under-utilization, overload conditions, and check SLA fulfillment. However they cannot trust twice the provider for the SLA and for its checking, and have limited knowledge about the infrastructure to understand the reasons of real bottlenecks. They can only access the virtual resources. In this Chapter we provide a comparison of two different approaches to the monitoring of Clouds Infrastructure, developed within the research activities of two European FP7-ICT projects. The first one has been developed by the VISION Cloud project and it is based on asynchronous message delivery mechanism for the collection, propagation and delivery of all events to their respective recipients. The second one is based on , the mobile agents framework of the mOSAIC project, for provisioning and managements of heterogeneous Cloud resources
Designing optimal peer support to alleviate learner cognitive load in Learning Networks
No full textHsiao, Y. P., Brouns, F., & Sloep, P. B. (2012). Designing optimal peer support to alleviate learner cognitive load in Learning Networks. In P. Kommers, & N. Bessis (Eds.), Proceedings of IADIS International Conference Web-Based Communities and Social Media 2012 (pp. 73-80). July, 19-21, 2012, Lisbon, Portugal.In Learning Networks, learners have to engage in social interactions for sharing knowledge to achieve their personalized learning goals. When working on complex tasks, self-organized knowledge sharing imposes too much cognitive load and this is detrimental to learning. According to pedagogical guidelines of cognitive load theory, learning environments should not only avoid activities that distract learner attention but also focus learner attention on relevant activities that contribute to learning. This paper applied these guidelines in two studies, both meant to explore how to design an optimal peer support system. Study 1 aimed to alleviate learner cognitive load by using an automated peer tutor selection system. However, the results could not support our assumption that finding available peers for those who need knowledge sharing alleviates learner cognitive load. Study 2 explored how to support the interaction process of knowledge sharing by enhancing different competencies, namely content knowledge and tutoring skills. The results showed that supporting learners with different competencies alleviates cognitive load on different dimensions. Interestingly, students supported with content knowledge felt significantly more frustrated than those with tutoring skills. Our future research aims to design an optimal peer support system by 1) alleviating learner cognitive load through refining selection criteria to find suitable peers for knowledge sharing and 2) optimizing interaction process by designing support structures based on content knowledge and tutoring skills during knowledge sharing
Project team formation support for self-directed learners in social learning networks
No full textSpoelstra, H., Van Rosmalen, P., & Sloep, P. B. (2012). Project team formation support for self-directed learners in social learning networks. In P. Kommers, P. Isaias, & N. Bessis (Eds.), Proceedings of the IADIS International Conference on Web Based Communities and Social Media (ICWBC & SM 2012) (pp. 89-96). July, 21-23, 2012, Lisbon, Portugal.Despite their name, social learning networks often lack explicit support for collaborative learning, even though collaborative learning offers benefits over individual learning. The outcomes of collaborative, project-based learning can be optimized when team formation experts assemble the project teams. This paper addresses the question of how to provide team formation services to individual, self-directed learners in a social learning network so they can make use of and profit from project-based learning opportunities. A model of a team formation process is presented, based on current team formation theory. It is used to design an automated team formation service that can be used by self-directed learners to form teams for project-based learning. Starting from a project description situated in a knowledge domain, the model defines three categories of variables that govern the team formation process: (I) knowledge, (II) personality and (III) preferences. Learner data on these categories are combined in a measure of fit, which calculates the best team for a project. A novelty introduced is that, depending on the desired project outcomes the relative weight of the categories can be altered to optimise the project formation process. The feasibility of the approach is demonstrated in an example in which the proposed algorithm is used to determine the most productive team for a project. Finally, future work and research are indicated
International Activity of NIK in the European Union – New Article 12a of the Act on NIK
No full textIn his article, the author presents: (1) the participation of NIK in international audits (interpretation of new Article 12a of the Act on NIK that clearly sets out the right to conduct such audits; types and examples of such audits; advantages of international auditing); (2) the cooperation of NIK with the European Court of Auditors – ECA (participation of NIK auditors in ECA missions in Poland; NIK’s attempts to initiate collaboration with the ECA in conducting audits of the use of EU funds; cooperation with the Polish member of the ECA); (3) the activity of NIK in the forum of the Contact Committee of the Heads of the EU SAIs. In conclusions, the article emphasises that NIK should, as best as possible, perform its tasks related to a Supreme Audit Institution of an EU Member State
- …
