检索结果-内蒙古大学图书馆

13th Asian Conference on Machine Learning (ACML)

作者： Zhan, Huixin Zhang, Kun Hu, Chenyi Sheng, Victor S. Texas Tech Univ Dept Comp Sci Lubbock TX 79409 USA Xavier Univ Louisiana Dept Comp Sci New Orleans LA 70125 USA Univ Cent Arkansas Dept Comp Sci Conway AR 72035 USA

Integrating multiple comments into a concise statement for any online products or web services requires a non-trivial understanding of the input. Recently, graph neural networks (GNN) has been successfully applied to learn from highly-structured graph representations to mitigate the relationship between entities, such as co-references. However, current inter-sentence relation extraction cannot leverage discrete reasoning chains over multiple comments. To address this issue, in this paper, we propose a probabilistic K-hop knowledge graph (KKG) to extend existing knowledge graphs with inferred relations via discrete intra-sentence and inter-sentence reasoning chains. KKG associates each inferred relation with a confidence value through Bayesian inference. We further answer how a knowledge graph with inferred relations can help the multiple comments integration through integrating KKG with GNN (K-2-GNN). Our extensive experimental results show that our K2 -GNN outperforms all baseline graph models on multiple comments integration.

关键词： Graph neural networks Knowledge graph web data integration Graph representation

来源：评论

学校读者我要写书评

暂无评论

Normalization of Duplicate Records from Multiple Sources

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2019年第4期31卷 769-782页

作者： Dong, Yongquan Dragut, Eduard C. Meng, Weiyi Jiangsu Normal Univ Sch Comp Sci & Technol Xuzhou 221116 Jiangsu Peoples R China Temple Univ Dept Comp & Informat Sci Philadelphia PA 19022 USA Binghamton Univ Comp Sci Dept Binghamton NY 13902 USA

data consolidation is a challenging issue in data integration. The usefulness of data increases when it is linked and fused with other data from numerous (web) sources. The promise of Big data hinges upon addressing several big data integration challenges, such as record linkage at scale, real-time data fusion, and integrating Deepweb. Although much work has been conducted on these problems, there is limited work on creating a uniform, standard record from a group of records corresponding to the same real-world entity. We refer to this task as record normalization. Such a record representation, coined normalized record, is important for both front-end and back-end applications. In this paper, we formalize the record normalization problem, present in-depth analysis of normalization granularity levels (e.g., record, field, and value-component) and of normalization forms (e.g., typical versus complete). We propose a comprehensive framework for computing the normalized record. The proposed framework includes a suit of record normalization methods, from naive ones, which use only the information gathered from records themselves, to complex strategies, which globally mine a group of duplicate records before selecting a value for an attribute of a normalized record. We conducted extensive empirical studies with all the proposed methods. We indicate the weaknesses and strengths of each of them and recommend the ones to be used in practice.

关键词： Record normalization data quality data fusion web data integration deep web

来源：评论

学校读者我要写书评

暂无评论

RunayaySoft Adaptive system for supporting the selection of enrichment activities in educative environments

引用

INTERNATIONAL JOURNAL OF web INFORMATION SYSTEMS 2019年第1期15卷 103-131页

作者： Gonzalez Vargas, Juan Camilo Carrillo-Ramos, Angela Fabregat, Ramon Camargo, Lizzeth Garcia Cepero, Maria Caridad Pavlich-Mariscal, Jaime A. Pontificia Univ Javeriana Dept Syst Engn Bogota Colombia Univ Girona Inst Informat & Applicat Girona Spain Pontificia Univ Javeriana Dept Syst & Comp Engn Bogota Colombia Pontificia Univ Javeriana Dept Educ Bogota Colombia

Purpose The purpose of this paper is to describe a support system to the selection of enrichment activities in educational environment called RunayaySoft, where Runayay comes from the word Quechua that means develop and Soft as it is an informatics tool that supports the educational institutions and their students, in the selection of activities that allow foster some of their skills based on their interests, learning styles, aptitudes, multiple intelligences, preferences and so on. Moreover, it suggests institutions about the activities that they should make in their building considering student ' s characteristics and the agreements that they have. Design/methodology/approach It does a diagnostic for identifying which characteristics are going to be considered to students and institutions. Then, it generates adaptive profiles with the aim of generating suggestions of enrichment activities that allow to boost some of their skills. For the students were considered their preferences, learning style, aptitude, multiple intelligences and interests. In the case of institutions were the agreements, resources and activities that they develop. Based on this information, it defines the relations for the generation of suggestions of activities toward students, where it does the prioritization of which activities should be considered. Findings For validating the system, it was done as a functional prototype that generates suggestions to students, as well as educative institutions, through a satisfaction test student assess if they agree or disagree with the suggestions given. With that assessment, it is validated the relationship between student's characteristics, activity and institution are related for generating activities suggestions.

关键词： web databases web data integration web-based education

来源：评论

学校读者我要写书评

暂无评论

Automatic recommendation of prognosis measures for mechanical components based on massive text mining

引用

INTERNATIONAL JOURNAL OF web INFORMATION SYSTEMS 2018年第4期14卷 480-494页

作者： Martinez-Gil, Jorge Freudenthaler, Bernhard Natschlaeger, Thomas Software Competence Ctr Hagenberg GmbH Hagenberg Austria

Purpose The purpose of this study is to automatically provide suggestions for predicting the likely status of a mechanical component is a key challenge in a wide variety of industrial domains. Design/methodology/approach Existing solutions based on ontological models have proven to be appropriate for fault diagnosis, but they fail when suggesting activities leading to a successful prognosis of mechanical components. The major reason is that fault prognosis is an activity that, unlike fault diagnosis, involves a lot of uncertainty and it is not always possible to envision a model for predicting possible faults. Findings This work proposes a solution based on massive text mining for automatically suggesting prognosis activities concerning mechanical components. Originality/value The great advantage of text mining is that makes possible to automatically analyze vast amounts of unstructured information to find corrective strategies that have been successfully exploited, and formally or informally documented, in the past in any part of the world.

关键词： web mining web search and information extraction web data integration

来源：评论

学校读者我要写书评

暂无评论

MAMS: Mashup architecture with modeling and simulation as a service

引用

JOURNAL OF COMPUTATIONAL SCIENCE 2017年第Jul.期21卷 113-131页

作者： Wainer, Gabriel Wang, Sixuan Carleton Univ Dept Syst & Comp Engn Ottawa ON K1S 5B6 Canada

The Modeling and Simulation (M&S) community has used web service (WS) technologies to help with the increasing complexity of the applications. Although there are many web APIs that could be useful for M&S applications, they are rarely used. One of the main reasons is that using M&S related WSs and open APIs makes it difficult to consider their integration for building complex M&S applications. Here we show how to simplify the development and integration process of such M&S applications by using a new architecture for web services Mashups, namely the Mashup Architecture for Modeling and Simulation (MAMS). MAMS is the first environment and architecture to integrate mashups and distributed simulation. MAMS provides means for a lightweight life cycle to develop, deploy, identify, select, integrate and execute varied M&S resources as services in the Cloud. We present different case studies showing the utility of the proposed architecture. (C) 2017 Elsevier B.V. All rights reserved.

关键词： Modeling and simulation as a service Cloud-based simulation Mashup web data integration web service composition

来源：评论

学校读者我要写书评

暂无评论

Information Extraction from the web by Matching Visual Presentation Patterns 1

引用

ISWC International Workshops / 1st Workshop on Knowledge Extraction and Knowledge integration (KEKI) / 4th NLP and DBpedia Workshop

作者： Burget, Radek Brno Univ Technol Ctr Excellence IT4Innovat Fac Informat Technol Bozetechova 2 Brno 61266 Czech Republic

ISBN: (数字)9783319687230

ISBN: (纸本)9783319687230;9783319687223

The documents available in the World Wide web contain large amounts of information presented in tables, lists or other visually regular structures. The published information is however usually not annotated explicitly or implicitly and its interpretation is left on a human reader. This makes the information extraction from web documents a challenging problem. Most existing approaches are based on a top-down approach that proceeds from the larger page regions to individual data records, which depends on different heuristics. We present an opposite bottom-up approach. We roughly identify the smallest data fields in the document and later, we refine this approximation by matching the discovered visual presentation patterns with the expected semantic structure of the extracted information. This approach allows to efficiently extract structured data from heterogeneous documents without any kind of additional annotations as we demonstrate experimentally on various application domains.

关键词： web data integration Information extraction Structured record extraction Page segmentation Content classification Ontology mapping

来源：评论

学校读者我要写书评

暂无评论

web Applications and web Services support Therapists in a Multi-Sensor Platform for Therapeutic Gaming 17

Web Applications and Web Services support Therapists in a Mu...

引用

19th International Conference on Information integration and web-Based Applications and Services (iiWAS)

作者： Madeira, Rui Neves Antunes, Andre Postolache, Octavian Inst Telecomunicacoes Setubal Portugal ESTSetubal IPS Setubal Portugal ISCTE IUL Lisbon Portugal

ISBN: (纸本)9781450352994

Serious games based therapeutic approaches create environments that increase the motivation of patients to achieve successful completion of therapy programs that can be demanding. The therapeutic games should be designed and configured by therapists, who should also monitor and evaluate, on a regular basis, the therapy exercises masked by the games to measure the patient's progress in treatment. Thus, there is still a demand for customizable tools by therapists toward specific groups of patients. We are developing a solution that combines serious games, NUI, and sensors, such as Kinect and Leap Motion, to address both physiotherapy and cognitive stimulation therapy. This paper presents the web-based platform that provides the gaming solution, detailing the work in progress on the components responsible for the therapists' supervision.

关键词： web data integration web services Serious games HCI web visualization Kinect Leap Motion Pervasive health

来源：评论

学校读者我要写书评

暂无评论

引用

INTERNATIONAL JOURNAL OF web INFORMATION SYSTEMS 2017年第1期13卷 55-71页

作者： Andrade Ribeiro, Leonardo Haerder, Theo Univ Fed Goias Inst Informat Goiania Go Brazil Tech Univ Kaiserslautern Fachbereich Informat Kaiserslautern Rheinland Pfalz Germany

Purpose - This article aims to explore how to incorporate similarity joins into XML database management systems (XDBMSs). The authors aim to provide seamless and efficient integration of similarity joins on tree-structured data into an XDBMS architecture. Design/methodology/approach - The authors exploit XDBMS-specific features to efficiently generate XML tree representations for similarity matching. In particular, the authors push down a large part of the structural similarity evaluation close to the storage layer. Findings - Empirical experiments were conducted to measure and compare accuracy, performance and scalability of the tree similarity join using different similarity functions and on the top of different storage models. The results show that the authors' proposal delivers performance and scalability without hurting the accuracy. Originality/value - Similarity join is a fundamental operation for data integration. Unfortunately, none of the XDBMS architectures proposed so far provides an efficient support for this operation. Evaluating similarity joins on XML is challenging, because it requires similarity matching on the text and structure. In this work, the authors integrate similarity joins into an XDBMS. To the best of the authors' knowledge, this work is the first to leverage the storage scheme of an XDBMS to support XML similarity join processing.

关键词： Managing and storing XML data web data integration web databases

来源：评论

学校读者我要写书评

暂无评论

ICT-FLAG: a web-based e-assessment platform featuring learning analytics and gamification

引用

INTERNATIONAL JOURNAL OF web INFORMATION SYSTEMS 2017年第1期13卷 25-54页

作者： Ganan, David Caballe, Santi Clariso, Robert Conesa, Jordi Baneres, David Univ Oberta Catalunya Fac Comp Sci Multimedia & Telecommun Barcelona Spain

Purpose - The purpose of this paper is to present an innovative web-based eLearning platform called ICT-FLAG that provides e-assessment tools with general-purpose formative assessment services featuring learning analytics and gamification. Design/methodology/approach - The paper reports on the technical development of the platform driven by the Reference Model for Open Distributed Processing software methodology, which guides the platform construction, including the analysis and design steps. Findings - The ICT-FLAG platform is technically tested by integrating it into a real e-assessment tool. Results are positive in terms of functional and non-functional aspects as well as user's satisfaction on usability, emotional state, thus validating the platform as a valuable educational tool. Research limitations/implications - Because of the chosen technical paper as article type, validation of the impact of the ICT-FLAG platform in the learning process is not provided. Ongoing research with this platform is to measure the learning outcomes of its use in a real context of eLearning. Practical implications - The paper shows implications of the main technical issues and challenges encountered during the integration of the ICT-FLAG platform with external eLearning tools, involving relevant aspects of interoperability, security, modularity, scalability, portability and so on. Originality/value - This platform can fill the gap of many e-assessment systems, which currently do not have built-in analytical and gamification tools for learning, thus providing them with the experience to improve the quality of education and learning.

关键词： Advanced web applications web data integration web-based education

来源：评论

学校读者我要写书评

暂无评论

Tukuchiy: a dynamic user interface generator to improve usability

引用

INTERNATIONAL JOURNAL OF web INFORMATION SYSTEMS 2016年第2期12卷 150-176页

作者： Barrera-Leon, Luisa Mejia-Molina, Nadia Carrillo-Ramos, Angela Florez-Valencia, Leonardo Pavlich-Mariscal, Jaime A. Pontificia Univ Javeriana Dept Ingn Sistemas Bogota Colombia Univ Catolica Norte Dept Ingn Sistemas & Comp Antofagasta Chile

Purpose - This paper aims to present a detailed description of Tukuchiy, a framework to dynamically generate adapted user interfaces. Tukuchiy is based on Runa-Kamachiy, a conceptual integration model that combines human-computer interaction ( HCI) standards to create user interfaces with user-centered concepts usually addressed by adaptation. Design/methodology/approach - The first step was the definition of three profiles: user, context and interface. These profiles contain information, such as user disabilities, location characteristics (e.g. illumination) and preferences ( e.g. interface color or type of system help). The next step is to define the rules that ensure usability for different users. All of this information is used to create the Tukuchiy framework, which generates dynamic user interfaces, based on the specified rules. The last step is the validation through a prototype called Idukay. This prototype uses Tukuchiy to provide e-learning services. The functionality and usability of the system was evaluated by five experts. Findings - To validate the approach, a prototype of Tukuchiy, called Idukay, was created. Idukay was evaluated by experts in education, computing and HCI, who based their evaluation in the system usability scale ( SUS), a standard usability test. According to them, the prototype complies with the usability criteria addressed by Tukuchiy. Research limitations/implications - This work was tested in an academic environment and was validated by different experts. Further tests in a production environment are required to fully validate the approach. Originality/value - Tukuchiy generates adapted user interfaces based on user and context profiles. Tukuchiy uses HCI standards to ensure usability of interfaces that dynamically change during execution time. The interfaces generated by Tukuchiy adapt to context, functionality, disabilities ( e.g. color blindness) and preferences ( usage and presentation) of the user. Tukuchiy enforces specific

关键词： web design metrics web data integration web-based education

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：