this book constitutes the refereed proceedings of the 15thinternationalconference on Discovery Science, DS 2012, held in Lyon, France, in October 2012. the 22 papers presented in this volume were carefully reviewed ...
ISBN:
(数字)9783642334924
ISBN:
(纸本)9783642334917
this book constitutes the refereed proceedings of the 15thinternationalconference on Discovery Science, DS 2012, held in Lyon, France, in October 2012. the 22 papers presented in this volume were carefully reviewed and selected from 46 submissions. the field of discovery science aims at inducing and validating new scientific hypotheses from data. the scope of this conference includes the development and analysis of methods for automatic scientific knowledge discovery, machinelearning, intelligent data analysis, theory of learning, tools for supporting the human process of discovery in science, as well as their application to knowledge discovery.
In many domains, such as Telecom, various scenarios necessitate the processing of large amounts of data using statistical and machinelearning algorithms. A noticeable effort has been made to move the data management ...
详细信息
ISBN:
(纸本)9781467345101;9781467345118
In many domains, such as Telecom, various scenarios necessitate the processing of large amounts of data using statistical and machinelearning algorithms. A noticeable effort has been made to move the data management systems into MapReduce parallel processing environments, such as Hadoop, and Pig. Nevertheless, these systems lack the features of advanced machinelearning and statistical analysis. Frameworks such as Mahout, on top of Hadoop, support machinelearning, but their implementations are at the preliminary stage. For example, Mahout does not provide Support Vector machine (SVM) algorithms and it is difficult to use. On the other hand, traditional statistical software tools, such as R, containing comprehensive statistical algorithms for advanced analysis, are widely used. But such software can only run on a single computer, and therefore it is not scalable. In this paper, we propose an integrated solution RPig, which takes the advantages of R (for machinelearning and statistical analysis capabilities) and parallel data processing capabilities of Pig. the RPig framework offers a scalable, advanced data analysis solution for machinelearning and statistical analysis. Analysis jobs can be easily developed with RPig script in high level languages. We describe the design, implementation and an eclipse-based RPigEditor for the RPig framework. Using application scenarios from the Telecom domain we show the usage of RPig and how the framework can significantly reduce the development effort. the results demonstrate the scalability of our framework and the simplicity of deployment for analysis jobs.
the conventional algorithm of the BP neural network has some disadvantages such as in the vicinity of the target, if the learning factor is too small, the convergence may be too slow, and if the learning factor is too...
详细信息
the objective of the current research is to develop a mobile learning model for smart phones which will be used by educational institutions for learning and training purposes but also for on-the-go communication for s...
详细信息
ISBN:
(纸本)9789898565068
the objective of the current research is to develop a mobile learning model for smart phones which will be used by educational institutions for learning and training purposes but also for on-the-go communication for students and academics and information sharing. It would determine the important elements of mobile applications as a medium to facilitate m-learning both in assembling responses from students and for reporting feedback to individual students. the mobile application would also integrate capabilities so the students would be able to access presentations by professionals through the 3G application in their mobile devices. they could also interact by posting their comments and sharing photos, images, voice and video though this application. the lecturer could facilitate and moderate debates while students could respond and learn without being in front of a computer. the application would also be used as a digital marketing channel for promoting Educational Programmes to potential candidates.
In order to overcome the limitations of piecewise constant phenomenon and computational burden which exist in Markov Random Field (MRF) with pair wise neighborhood and traditional learning style respectively, this pap...
详细信息
As a typical Internet application, an m-learning system is an innovative approach for delivering well-designed, learner-centred, interactive and facilitated learning environments to anyone, anywhere at any time. Cloud...
详细信息
ISBN:
(纸本)9789898565068
As a typical Internet application, an m-learning system is an innovative approach for delivering well-designed, learner-centred, interactive and facilitated learning environments to anyone, anywhere at any time. Cloud computing is a technology and a business model that allows access to an extensible set of storage and computing facilities with a provision and pay as you go model. this position paper discusses the problem of content adaptation for mobile devices in a cloud context. A device independent model is presented in order to achieve automatic adaptation of the content based on its semantics and the capabilities of the target device. An m-learning software as a service cloud framework is presented for adapting, displaying and manipulating learning documents on smart devices. Some aspects of services integration in the cloud for m-learning are also discussed.
the proceedings contain 358 papers. the topics discussed include: study on three-dimensional visual simulation technology and its application in surface coal mine;numerical computation of wellbore dynamic pressure dur...
ISBN:
(纸本)9780769547893
the proceedings contain 358 papers. the topics discussed include: study on three-dimensional visual simulation technology and its application in surface coal mine;numerical computation of wellbore dynamic pressure during perforating;study of 3D geological structure modeling and visualization application based on computer technology;an image hiding scheme based on 3D skew tent map and discrete wavelet transform;anisotropic mechanical-hydraulic coupling for deep buried tunnel in soft rock with rich water;research on ontology instance learning based on maximum entropy model;modeling and simulation system design of tactical ballistic missile interception based on UML;effects analysis based on computer simulation of autonomous underwater vehicle throw limiting period on the initial trajectory;a study on vehicle routing problem with fuzzy demands based on improved Tabu search;and finite element analysis of normal contact stiffness between real rough surfaces based on ANSYS.
the Supercritical Main Steam has a large inertia, delay and nonlinear and dynamic characteristics change withthe operating conditions, it is difficult to establish the precise mathematical model, this algorithm based...
详细信息
ISBN:
(纸本)9780819490254
the Supercritical Main Steam has a large inertia, delay and nonlinear and dynamic characteristics change withthe operating conditions, it is difficult to establish the precise mathematical model, this algorithm based on RBF neural network GGAP posed a direct neural network predictive controller, the combination of online learning and control to a supercritical power plant main stream temperature as the research object, MATLAB simulation results show that the superheated steam temperature system can achieve effective control, performance than the conventional PID control has greatly improved.
Prevention of work stress is among the priorities of the European Commission as stated in the Health and Safety policy published in March 2002. the case of the road transport drivers (freights and passengers) is worth...
详细信息
ISBN:
(纸本)9789898565068
Prevention of work stress is among the priorities of the European Commission as stated in the Health and Safety policy published in March 2002. the case of the road transport drivers (freights and passengers) is worthy to be considered separately, since their work accidents might affect not only their own health but also other people's - road traffic participants, service personnel, etc. Aim of this paper is to analyze current situation and to propose a methodological dossier of virtual learning environmental (VLE) for stress prevention activities of road transport drivers and SME on the base of achievements in areas such as elearning and risk prevention. It is proposed the VLE to be composed of 6 learning modules: What is stress? Causes of stress (stress related hazards);Effects of stress;Stress risk assessment;Stress management;Prevention of work stress. the training content will be complemented with examples on Physical and Physiological exercises and techniques. there is short a description of VLE organization, as well.
To provide the expertise to apply learned knowledge in practice is one main challenge of higher education. Especially, the engineering graduates need to solve complex problems in their profession and apply specific ex...
详细信息
ISBN:
(纸本)9789898565068
To provide the expertise to apply learned knowledge in practice is one main challenge of higher education. Especially, the engineering graduates need to solve complex problems in their profession and apply specific expertise in various contexts. these demands encompass less recalling of factual knowledge, but more comprehensive key competencies like problem-solving expertise. In this paper, the Adaptive Assessment System askme! is used to address this challenge. the authors discuss the general conditions of the education of a course in theoretical computer science offered for students of a Bachelor degree program. Furthermore, this paper provides an application scenario in which the applied learning platform Moodle will be extended by adaptive methods of assessment.
暂无评论