DOI: 10.3897/jucs.145075

Authors: Jorge Arthur Schneider Aranda, Ricardo dos Santos Costa, Vitor Werner de Vargas, Paulo Ricardo da Silva Pereira, Jorge Luis Victória Barbosa, Marcelo Pinto Vianna, Eleandro Luis Marques da Silva

Abstract: Power utilities demand large volumes of data used in power distribution networks. Among them are parameters representing possible technical failures, such as network’s short circuit current and voltage sag. Specialists find these parameters and detect technical failures. However, this process can become time-consuming. Thus, this article proposes an ontology called OntoFreya, which classifies voltage, current, or any electric metric, following the definitions of the regulatory agencies and reducing the time spent on this task. A series of 4402 axioms, 132 classes, and 40 data properties comprises OntoFreya. The ontology automatically inferred classifications for four hundred readings from energy samples, validating OntoFreya across three scenarios. The first and second scenarios classified current in amperes, and the third classified voltage in per-unit system (pu). The scenarios showed that OntoFreya automates the classification of electric metrics, reducing specialists’ time in detecting technical failures in a distribution network.

HTML

PDF

DOI: 10.3217/jucs-025-13-1761

Authors: Estêvão Saleme, Celso A. S. Santos, Ricardo Falbo, Gheorghita Ghinea, Frederic Andres

Abstract: Designing a mulsemedia|multiple sensorial media|system entails first and foremost comprehending what it is beyond the ordinary understanding that it engages users in digital multisensory experiences that stimulate other senses in addition to sight and hearing, such as smell, touch, and taste. A myriad of programs that comprise a software system, several output devices to deliver sensory effects, computer media, among others, dwell deep in the realm of mulsemedia systems, making it a complex task for newcomers to get acquainted with their concepts and terms. Although there have been many technological advances in this field, especially for multisensory devices, there is a shortage of work that tries to establish common ground in terms of formal and explicit representation of what mulsemedia systems encompass. This might be useful to avoid the design of feeble mulsemedia systems that can be barely reused owing to misconception. In this paper, we extend our previous work by proposing to establish a common conceptualization about mulsemedia systems through a domain reference ontology named MulseOnto to aid the design of them. We applied ontology verification and validation techniques to evaluate it, including assessment by humans and a data-driven approach whereby the outcome is three successful instantiations of MulseOnto for distinct cases, making evident its ability to accommodate heterogeneous mulsemedia scenarios.

HTML

XML

PDF

DOI: 10.3217/jucs-025-10-1373

Authors: Khaled Halimi, Hassina Seridi-Bouchelaghem

Abstract: The aim of the paper is to describe the design of a Web 3.0-based Intelligent Learning System (ILS) that addressing the students' needs in the 21st century. The design is based theoretically, on the principles of the connectivism theory and technically, it implements the semantic web representations combining with the use of learning analytics techniques. The work emphasises that implementing a learning analytics approach that uses: text classification, sentiment analysis, topics extraction, and text clustering on the basis of a semantic web and ontologies can support the connectivist learning. The semantic learning analytics process, represents the key element of the proposed intelligent learning analytics system to infer and deduce hidden data in the massive learning data thanks to semantic models of i-SoLearn. The aim is to guide students to understand through recommendations, charts and visualisations their learning behaviour and to give teachers feedbacks, enabling them to examine both students' learning and activities. An experimental study using i-SoLearn (an intelligent social learning environment), indicates that designing an ILS based on Web 3.0 techniques is effective and expected to show a great advantage in enhancing the connectivist learning of students in the digital age.

HTML

XML

PDF

DOI: 10.3217/jucs-024-11-1627

Authors: Laura Po, Davide Malvezzi

Abstract: The Linked Open Data (LOD) Cloud has more than tripled its sources in just six years (from 295 sources in 2011 to 1163 datasets in 2017). The actual Web of Data contains more then 150 Billions of triples. We are assisting at a staggering growth in the production and consumption of LOD and the generation of increasingly large datasets. In this scenario, providing researchers, domain experts, but also businessmen and citizens with visual representations and intuitive interactions can significantly aid the exploration and understanding of the domains and knowledge represented by Linked Data. Various tools and web applications have been developed to enable the navigation, and browsing of the Web of Data. However, these tools lack in producing high level representations for large datasets, and in supporting users in the exploration and querying of these big sources. Following this trend, we devised a new method and a tool called H-BOLD (High level visualizations on Big Open Linked Data). H-BOLD enables the exploratory search and multilevel analysis of Linked Open Data. It offers different levels of abstraction on Big Linked Data. Through the user interaction and the dynamic adaptation of the graph representing the dataset, it will be possible to perform an effective exploration of the dataset, starting from a set of few classes and adding new ones. Performance and portability of H-BOLD have been evaluated on the SPARQL endpoint listed on SPARQL ENDPOINT STATUS. The effectiveness of H-BOLD as a visualization tool is described through a user study.

HTML

XML

PDF

DOI: 10.3217/jucs-022-07-0921

Authors: Héctor Amado-Salvatierra, José Hilera, Salvador Tortosa, Rocael Rizzardini, Nelson Piedra

Abstract: The growth of education faces a constant evolution, and the adoption of new technologies for education is reflected in the inclusion of virtual courses in the educational process. However, accessibility in cloud-based applications, virtual platforms and online courses has not been widely taken into account in the educational process. In this sense, the inclusion of accessibility features for online applications and digital content represents a very important benefit for everyone, but in the context of e-learning, it is imperative for students with disabilities. The lack of interest and awareness in online accessibility for education is especially evident in developing countries that do not have legislation that encourages stakeholders to bear in mind accessibility features for web-based applications and contents. This paper proposes a methodological framework to take into account accessibility in the different processes of the life cycle of a virtual educational project. In this work, a semantic definition based on a conceptual model of the identified components for this methodology is presented. The proposed methodology has been prepared under an iterative design process, based on an international standard and complemented with online resources for dissemination. In order to validate and improve the methodological framework, seven accessible virtual training courses were prepared following the phases and components defined in the methodology. The seven courses were promoted in an open call for participation launched in Latin America with the support of a cooperation initiative between European and Latin American universities called ESVI-AL. At the end of the experience, a total of 748 teachers and 937 students from 150 different educational institutions were enrolled. The participants in the experience provided comments and suggestions for further improvement. The proposed work is intended to be used as a reference for educational institutions to identify the necessary changes needed to incorporate accessibility into their own production processes for virtual courses.

HTML

XML

PDF

DOI: 10.3217/jucs-021-08-1042

Authors: Maria José Angélico Gonçalves, Álvaro Rocha, Manuel Pérez Cota

Abstract: This research work was carried out in the areas of Higher Education, Teaching Technology and Web Information Management with the aim of developing a model for identifying and classifying competences and learning outcomes (MICRA) and an ontology of the information management model (SICRA). The MICRA model was applied in a case study, whereas the verification and validation of its previously defined functionalities led to ontology validation. MICRA shows to be an innovative model, based on a thorough, organized and systematic analysis of the educational context. In addition, SICRA goes beyond other ontologies as it not only defines reusable competences, classified according to Bloom's taxonomy, but also defines and establishes a correspondence among Computer Science Knowledge Areas. We have thus contributed to making learning institutions' training curricula widely available, allowing for their contrastive analysis in order to promote student and teacher mobility within the European Higher Education Area and in other countries.

HTML

XML

PDF

DOI: 10.3217/jucs-021-06-0856

Authors: Alejandro Zambrano, Carlos Toro, Marcos Nieto, Ricardo Sotaquira, Cesar Sanín, Edward Szczerbicki

Abstract: This paper proposes a service-oriented architecture for video analysis which separates object detection from event recognition. Our aim is to introduce new tools to be considered in the pathway towards Cognitive Vision as a support for classical Computer Vision techniques that have been broadly used by the scientific community. In the article, we particularly focus in solving some of the reported scalability issues found in current Computer Vision approaches by introducing an experience based approximation based on the Set of Experience Knowledge Structure (SOEKS). In our proposal, object detection takes place client-side, while event recognition takes place server-side. In order to implement our approach, we introduce a novel architecture that aims at recognizing events defined by a user using production rules (a part of the SOEKS model) and the detections made by the client using their own algorithms for visual recognition. In order to test our methodology, we present a case study, showing the scalability enhancements provided.

HTML

XML

PDF

DOI: 10.3217/jucs-021-05-0679

Authors: Nelson Piedra, Janneth Chicaiza, Jorge López, Edmundo Tovar

Abstract: The OER movement has tended to define "openness" in terms of access to use and reuse educational materials, and to address the geographical and financial barriers among students, teachers and self-learners with open access to high quality digital educational resources. MOOCs are the continuation of this trend of openness, innovation, and use of technology to provide learning opportunities for large numbers of learners. In the last years, the amount of Open Educational Resources on the Web has increased dramatically, especially thanks to initiatives like OpenCourseWare and other Open Educational Resources movements. The potential of this vast amount of resources is enormous. In this paper an architecture based on Semantic Web technologies and the Linked Data guidelines to support the inclusion of open materials in massive online courses is presented. Linked Data is considered as one of the most effective alternatives for creating global shared information spaces, it has become an interesting approach for discovering and enriching open educational resources data, as well as achieving semantic interoperability and re-use between multiple Open Educational Resources repositories. The notion of Linked Data refers to a set of best practices for publishing, sharing and interconnecting data in RDF format. Educational repositories managers are, in fact, realizing the potential of using Linked Data for describing, discovering, linking and publishing educational data on the Web. This work shows a data architecture based on semantic web technologies that support the discovery and inclusion of open educational materials in massive online courses in engineering education. The authors focus on a type of openness: open of contents as regards re-use and re-mix, i.e. freedom to reuse the material, to combine it with other materials, to adapt and to share it further under an open license.

HTML

XML

PDF

DOI: 10.3217/jucs-021-05-0656

Authors: Rocael Rizzardini

Abstract: MOOC adoption is growing, and several challenges are presented with it. One of them is the use of innovative tools for learning, with a special emphasis in having learners to represent their acquired knowledge in creative forms; therefore, some experiences in that regard will be introduced. Thus, orchestrating the learning experience with cloud-based external tools (realized as Web 2.0 tools) brings interoperability issues such as automated management of tools and interoperability scalability. This paper presents a new version of an architecture that is capable of interoperability with external tools by defining a semantic description of the tools' Web API using linked data. This creates the next generation of tool interoperability for educational environments. Furthermore, it makes machine discovery of the Web API possible; therefore, it does not require custom system interfaces to interoperate. It simplifies the plugging in of new external tools and maintenance of integrated services. Additionally, the architecture makes it possible to automate simple and complex tasks to be performed with the external tools, such as creating thousands of tool instances to be used by MOOC learners. The results are very promising and demonstrate that this approach is innovative, scalable and highly accurate. Currently, no standard, specification or framework has the same type of flexibility, integration simplicity and robust management for external tools.

HTML

XML

PDF

DOI: 10.3217/jucs-021-04-0561

Authors: Norton Roman, Paul Piwek, Ariadne Maria Brito Rizzoni Carvalho, Alexandre Alvares

Abstract: This paper proposes a scheme for sentiment annotation. We show how the task can be made tractable by focusing on one of the many aspects of sentiment: sentiment as it is recorded in behaviour reports of people and their interactions. Together with a number of measures for supporting the reliable application of the scheme, this allows us to obtain sufficient to good agreement scores (in terms of Krippendorf's alpha) on three key dimensions: polarity, evaluated party and type of clause. Evaluation of the scheme is carried out through the annotation of an existing corpus of dialogue summaries (in English and Portuguese) by nine annotators. Our contribution to the field is twofold: (i) a reliable multi-dimensional annotation scheme for sentiment in behaviour reports; and (ii) an annotated corpus that was used for testing the reliability of the scheme and which is made available to the research community.

HTML

XML

PDF

DOI: 10.3217/jucs-020-10-1418

Authors: Eugenijus Kurilovas, Anita Juskeviciene, Svetlana Kubilinskiene, Silvija Serikoviene

Abstract: The aim of the paper is to investigate and propose Semantic Web approaches to improving the adaptation quality of Virtual Learning Environments (VLEs). These approaches are the method for semantic search for Web 2.0 tools in VLEs, and the method for curriculum mapping and semantic search for Learning Objects (LOs) in VLEs. In the paper, a special attention is paid to improving the adaptation capabilities of VLE, e.g. its suitability for different learning styles such as VARK. Web 2.0 tools ontology based on VARK model learning activities gives the possibility to develop adaptive learning environment with better access to specific learning content managing tools (i.e. Web 2.0 tools). The learner will only need to enter the name of learning activity into the search system field and the machine offers the appropriate tools to perform this activity. The engine facilitates the search process by optimizing workloads, thereby improving learner's satisfaction and improving the efficiency and effectiveness of the learning process. Presented curriculum mapping approach makes interoperability and LOs semantic search possible by making use of two smaller controlled vocabularies instead of a very large one on competencies which would be more volatile. One could exchange information on competencies in a multi-lingual and multi-cultural environment by: (1) breaking down competencies, and (2) relating these competency components to multilingual controlled vocabularies. The research results have shown that, in order to improve the adaptation quality of VLEs, it is very important to improve semantic search for both LOs and Web 2.0 tools in VLEs.

HTML

XML

PDF

DOI: 10.3217/jucs-020-06-0859

Authors: Goran Putnik, Maria Cruz-Cunha

Abstract: The purpose of this paper is to present a taxonomy able to contribute to building a framework within the domain of Virtual Enterprises (VE), to facilitate the sharing of knowledge and contributions to knowledge, as well as for trust building among VE stakeholders. A VE taxonomy currently does not exist, and this lack is felt in the ambiguous way that some concepts are addressed, leading to a fragment understanding that hinders the development of the science of VE integration and management. The structure of the taxonomy developed is based on the view of the system as a 5-tuple consisting of Input, Control, Output, Mechanism, and Process, which is the underlying system-view in the well-know IDEF0 diagramming technique. In particular, this taxonomy addresses the VE extended lifecycle that implies the use of a meta-organization called Market of Resources, as an original contribution to the VE theory and practice. The taxonomy presented does not repeat what the literature already includes, or the commonplaces, and it is constructed in a way to be easily complemented with other VE partial taxonomies that may be found in literature. Some suggestions for extensions to other interrelated domains (as evolution leaves taxonomies in an open or incompleteness state) are given in the text.

HTML

XML

PDF

DOI: 10.3217/jucs-019-14-2150

Authors: Sylvana Kroop

Abstract: Instead of using traditional learning environments which contain tools and content of a single provider that are often owned by one specific educational organization, the presented idea of Widget- and Cloud-based Personal Learning Environments (PLEs) exploits a variety of existing and developing open educational sources including popular Web2.0 resources such as YouTube, Flickr or Wikipedia. The main contribution of this paper is the analysis of teachers’ and students’ attitudes and reasons for acceptance of widget- and cloud-computing based PLE technology. A quantitative and qualitative comparison of three widget-based PLE scenarios reveals the benefits as well as barriers of the new PLE technology regarding a) learning outcome and b) (cognitive, technical, time-wise) ease of the personal learning process. Findings show that a systematic cloud computing approach - software as a service (SaaS) where users do not need to install and run tools locally - is preferred. It saves time and meets the needs to keep the personal environment flexible and up to date. But while users have to manage a broad range of tools and content their most essential request is to be efficiently supported by the system in regard to their individual learning needs, e.g. in the decision making process of selecting and evaluating relevant tools.

HTML

XML

PDF

DOI: 10.3217/jucs-019-11-1638

Authors: Michalis Feidakis, Thanasis Daradoumis, Santi Caballe, Jordi Conesa, David Gañán

Abstract: Endowing learning systems with emotion awareness features (capture user's affective state and provide affective feedback), seems quite promising. This paper describes a system implementation that provides emotion awareness, both explicitly, by self-reporting of emotions through a usable web tool, and implicitly, via sentiment analysis. Prominent theories, models and techniques of emotion, emotion learning, emotion detection and affective feedback are reviewed. We also present findings from our experiment with university students, validating the explicit mechanism in real education settings. Finally, we set open issues for future experimentation, contributing to the research agenda.

HTML

XML

PDF

DOI: 10.3217/jucs-019-11-1500

Authors: Ángel Fidalgo, María Sein-Echaluce, Dolores Lerís, Oscar Castañeda

Abstract: The education project presented in this paper endeavors to study the feasibility of incorporating adaptive systems into LMS systems, by using them both in training & learning process and at work. This case study is aimed at employability and job post improvement. For this purpose, we have created a process that is flexible both to the student pattern (and to the job pattern. The developed process is adaptable both to the student (via the incorporation of an adaptable system with an LMS system) and to the job model (via an adaptable system to the knowledge management). The evaluation was qualitative and measured the process (feasibility to apply adaptive systems) and the efficiency of the method (applicability and employability). The functionality of the specific developed tools allowed us to grade the degree of adaptability in the training process, to dynamically vary the training plan from the student's actions and to identify the resources that best met the job needs.

HTML

XML

PDF

DOI: 10.3217/jucs-015-12-2387

Authors: Linkai Weng, Yaoxue Zhang, Yuezhi Zhou, Laurence Yang, Pengwei Tian, Ming Zhong

Abstract: Personalized recommendation is valuable in various web applications, such as e-commerce, music sharing, and news releasing, etc. Most existing recommendation methods require users to register and provide their private information before gaining access to any services, whereas a majority of users are reluctant to do so, which greatly limits the range of application of such recommendation methods. In the non-register environments, the only available information is the content or attributes of resources and the click-through chains of user sessions, so that many recommendation methods fail to work effectively due to the rating sparsity [Adomavicius and Tuzhilin, 2005] and illegibility of user identity, collaborative filtering [Goldberg et al. 1992] is an example of this case. In this paper we propose a joint recommendation method combining together two approaches, namely the domain category tree and the associate graph, to make full use of all available information. Further, an associate graph propagation method is designed to improve the traditional associate filtering method by integrating additional graphical considerations into them. Experiment results show that our method outperforms either the single category tree approach or the single associate graph approach, and it can provide acceptable recommendation services even in the non-register environment.

HTML

XML

PDF

DOI: 10.3217/jucs-015-04-0840

Authors: Jun Zhang, Kwok-Wing Chau

Abstract: Recently, classifier ensemble methods are gaining more and more attention in the machine-learning and data-mining communities. In most cases, the performance of an ensemble is better than a single classifier. Many methods for creating diverse classifiers were developed during the past decade. When these diverse classifiers are generated, it is important to select the proper base classifier to join the ensemble. Usually, this selection process is called pruning the ensemble. In general, the ensemble pruning is a selection process in which an optimal combination will be selected from many existing base classifiers. Some base classifiers containing useful information may be excluded in this pruning process. To avoid this problem, the multilayer ensemble pruning model is used in this paper. In this model, the pruning of one layer can be seen as a multimodal optimization problem. A novel multi-sub-swarm particle swarm optimization (MSSPSO) is used here to find multi-solutions for this multilayer ensemble pruning model. In this model, each base classifier will generate an oracle output. Each layer will use MSSPSO algorithm to generate a different pruning based on previous oracle output. A series of experiments using UCI dataset is conducted, the experimental results show that the multilayer ensemble pruning via MSSPSO algorithm can improve the generalization performance of the multi-classifiers ensemble system. Besides, the experimental results show a relationship between the diversity and the pruning technique.

HTML

XML

PDF

DOI: 10.3217/jucs-014-17-2758

Authors: Brent Martin, Antonija Mitrovic, Pramuditha Suraweera

Abstract: Authoring ITS domain models is a difficult task requiring many skills. We explored whether modeling ontology reduces the problem by giving the students of an e-learning summer school the task of developing the model for a simple domain in under sixty minutes using ontology. Some students also used our tool to develop a complete tutor in around eight hours, which is much faster than they could be expected to author the system without the tool. The results suggest this style of authoring can lead to very rapid ITS development. We further extend the ontological approach with domain schema: high-level abstractions that describe the semantics of the domain model for a class of domains. Using domain schema reduces the authoring effort to one of describing only those aspects that are unique to this particular domain, and enables the ontology-based approach to model domains with different semantic requirements.

HTML

XML

PDF