检索结果-内蒙古大学图书馆

34th Information Systems Education Conference, ISECON 2018

作者： Sharif, Nauman Afzal, Muhammad Tanvir Graz University of Technology Infeldgasse 21a Graz8010 Austria Centre for Distributed and Semantic Computing Capital University of Science and Technology Islamabad Pakistan

Social media has been already extensively used in e-learning context. Users produce a vast amount of learning resources on the web using technologies such as tweets, blogs and wikis. It is a daunting task for learners to select the appropriate resources according to their learning styles." One core area in Technology enhanced Learning deals with this information overload. Learning resources metadata features such as Title, Author, Category and keyword are used in literature to provide recommendation. However these metadata features have not been exploited for twitter based recommender systems. A comprehensive evaluations and experimentations are conducted to determine the effectiveness of resource metadata for twitter based e-learning recommendation. The detailed evaluation reveals the effectiveness of the resource metadata for twitter based e-learning recommendation. © 2018 34th Information Systems Education Conference. All Rights Reserved

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Twitter recommendation: Unary metadata features evaluation with TF/IDF using n-grams 34

Twitter recommendation: Unary metadata features evaluation w...

引用

34th Information Systems Education Conference, ISECON 2018

作者： Sharif, Nauman Afzal, Muhammad Tanvir Ahmed, Usman Graz University of Technology Infeldgasse 21a Graz8010 Austria Centre for Distributed and Semantic Computing Capital University of Science and Technology Islamabad Pakistan Capital University of Science and Technology Islamabad Pakistan

Twitter has been identified by many researchers as a useful tool to assist e-Learners. However, contemporary e-learning systems have not fully utilized the strength of twitter to recommend learning resources. In literature metadata of learning resources such as title, author, category and keyword are used to provide recommendation. The aim of this paper is to evaluate the effectiveness of resource metadata for twitter based recommendation. A comprehensive evaluations and experimentations are carried out to validate the effectiveness of resource metadata for twitter based recommendation. A gold standard was formed with 220 research papers and 2957 related tweets collected from domain experts. © 2018 34th Information Systems Education Conference. All Rights Reserved

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Can Twitter be useful for e-learning recommendation? 33

Can Twitter be useful for e-learning recommendation?

引用

33rd Information Systems Education Conference, ISECON 2016

Twitter provides an opportunity to share various learning material along with short and precise text. Micro-blogging community is ever expanding. Discovery of the most relevant learning material becomes essential to solve the information overload problem. There is a potential need to provide twitter based learning recommendation for the learner without directly inferring the tool. E-learning recommender systems have been successfully supporting the individual leaning process. However there is a gap between the e-learning recommender system and twitter based recommendation such that no existing e-learning recommender systems are utilizing the twitter. This paper presents the work-in-progress with the aim to develop recommender system. Personalize learning activities and related tasks can be recommended to the learner according to the individual need of learner and as a result overall learning experience can be enhanced. In literature personalized recommender systems employs the characteristics of items, profiles of users and history of users and items interaction in order to recommend the related items. In this paper we shall investigate if the twitter can be useful for e-learning recommendation and what are the parameters that should be consider when recommending e-learning resources. © 2016 33rd Information Systems Education Conference. All Rights Reserved

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Recommendation approaches for E-learners - A survey 15

Recommendation approaches for E-learners - A survey

引用

7th ACM International Conference on Management of Computational and Collective IntElligence in Digital EcoSystems, MEDES 2015

作者： Sharif, Nauman Afzal, Muhammad Tanvir Institute for Knowledge Management Graz University of Technology Infeldgasse 21a Graz8010 Austria Centre for Distributed and Semantic Computing Mohammad Ali Jinnah University Islamabad Pakistan

ISBN: (纸本)9781450334808

Recommending relevant content to the learner is a challenging task for any e-Learning management system. This paper has critically reviewed the literature and identified the strategies being used to recommend relevant content to learners. This paper highlights the strength and limitations of prominent approaches and has presented challenging tasks which will be useful for the e-Learning research community to focus for the future research. © 2015 ACM.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

The web is big business

引用

Journal of computing and Information Technology 2015年第1期23卷 19-27页

作者： Mehmood, Rizwan Korica-Pehserl, Petra Centre for Distributed and Semantic Computing Mohammad Ali Jinnah University Islamabad Pakistan Department of Computer Engineering University of Belgrade Serbia

As has been explained in the paper "A Survey of Communications and Collaborative Web Technologies" in this special issue the web started as a more or less one-way information system, allowing engineers at CERN to share new results in physics world-wide easily. As it developed, it becamemore and more a two-way (or more precisely a multi-way) communication tool, allowing to collaboratively work in many ways. This has, as it has been described in the aforementioned paper, not just changed how information is created and provided easy ways of communication, but has also allowed the growth of social networks as first tools to tie together the power of brains, changing how we work, think, do research, form new circles of people we are interested in. This on its own would have been a major change in how society works, yet it turned out soon that the technologies available would allow to set up completely new business models, and threaten some existing ones. Among the hundreds of million applications found on the web today, many set up to make money, or at least pay for themselves by providing excellent ways of advertisements. There is no person who could know all the applications available on the web, and there is no way to even list a tiny percentage of them. However, what we are trying in this paper is to classify applications and discuss their commercial or societal impact.

关键词： High energy physics

来源：评论

学校读者我要写书评

暂无评论

Exploiting Title-Keywords Relation to Develop Concept Classifier for Scientific Community

引用

4th International Conference on Networked Digital Technologies, NDT 2012

作者： Khan, Sher Afgun Afzal, Muhammad Tanvir Qadir, Muhammad Abdul Centre for Distributed and Semantic Computing Mohammad Ali Jinnah University Pakistan

ISBN: (纸本)9783642305665

The exponential growth of scientific resources on the web has raised scalability issues like quick retrieval of relevant resource. The major obstacle is attributed to unstructured nature of information. It is estimated that the scientific knowledge is doubling in every five years. This information is being indexed by search engines, citation indexes, and digital libraries etc. Most of the time, the indexed information is unstructured or semi-structured. Therefore, the users are unable to find the relevant research papers. Users are given thousands and sometimes millions of irrelevant hits. This is mainly due to the unstructured nature of information being stored. For a query, the information retrieval may be restricted to the relevant resources if the resources are structured in a classification. Some classifications are being used in different domains such as in computer science, the ACM classification scheme is being used to structure the research papers. However, the ACM classification was majorly updated in 1998 and does not include evolving concepts and domains since then. Furthermore, only ACM papers are classified using ACM classification scheme while other publishers normally do not use this classification. Therefore, the automatic classification becomes a major challenge for scientific community. Several approaches are being used for creating automatic classification on the basis of co-occurrence analysis, keywords analysis, and using domain models, etc. However, the current approaches have their limitations. In this paper, we proposed and implemented a new approach of finding the evolving classification, termed as concept classifier for the scientific community by aggregating the correlation between title terms and keywords of the paper. Initially the experiment has been conducted over the dataset of journal i.e. Journal of Universal Computer Science (***). The resultant taxonomy has been verified and compared with the Growbag dataset (DBLP dataset of co

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A framework for resource recommendations for learners using social bookmarking

A framework for resource recommendations for learners using ...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Nauman Sharif Muhammad Tanvir Afzal Denis Helic Institute for Knowledge Management Graz University of Technology Graz Austria Centre for Distributed and Semantic Computing Mohammad Ali Jinnah University Islamabad Pakistan

E-Learning aims at providing an alternative to classroom learning where learners learn through internet or CD/DVD without physical presence in the classrooms. In this paper, the state-of-the-art e-Learning tools have been reviewed. It has been observed that the contemporary tools can be seen as course management system rather an alternative to classroom learning. When learners need further clarifications on the topic, learners need to visit external sources such as Search Engines, Citation Indexes, and Digital Libraries etc. However, with the advent of Web 2.0, the social community is engaged to share large number of important and recent resources with the scientific community. One of such system is known as: CiteULike which has more than 6 millions research resources and thousands of resources are shared on daily basis. Users of CiteULike annotate resources with useful keywords termed as Tags to give a structure to these resources. This paper further provides a framework for discovering most relevant resources from CiteULike for learners. The keywords of learning resource are matched with tags of CiteULike using Direct Match, Partial Match, and Synonym Match. The resources are further ranked based on number of weights. The ranked list of resources are made available in the local context of the learners in the eLearning system. The proposed framework has been demonstrated with the example of a case study. It has been found that the ranked list of resources are very important for learners. The learners not only get a ranked list of relevant resources, instead the learners discover evolving concepts and resources related to the topic of study. The reoccurs give breadth and depth knowledge to learners for further explorations.

关键词： Communities Electronic learning Abstracts Databases Information services Electronic publishing Internet

来源：评论

学校读者我要写书评

暂无评论

Extraction and visualization of citation network

Extraction and visualization of citation network

引用

1st International Conference on Computer Networks and Information Technology, ICCNIT'11

作者： Naqvi, Mohsin Mailk, Ahmad Usman Razzaq, Sohail Afzal, Muhammad Tanvir Centre for Distributed and Semantic Computing Mohammad Ali Jinnah University Islamabad Pakistan

ISBN: (纸本)9781612849416

The digital information is expanding with exponential curve. It becomes difficult to find the relevant information. For example, in scientific domain, to identify the most relevant paper for the focused paper, one needs to explore the focused paper's citations using some citation index such as Google Scholar etc. However, the focused paper may receive 100's and sometimes 1000's of citations. With this huge number of citations, it becomes difficult for users to find the highly relevant papers with respect to the focused paper. While exploring the relevant papers from citations of the focused paper, the user may end up with finding only few. This is because of the fact that authors often cite a paper for providing a background study of the domain and hence cited and cited-by paper have no strong relationship. Currently users need to skim all citations to filter such papers. There is a dire need to develop a system that could automate the process of finding the most relevant papers from the citations. In the current work, we have proposed such a system which ranks the most relevant cited phapers for a cited-by paper. The system conceptualizes citations as a graph model. Furthermore, the system employs number of weights to find the most relevant papers. Such weights include topic weight, keyword weight, and author weight. The edge between two nodes in the graph gets a maximum Weight if both are the most relevant papers. Subsequently, a visualization technique has been designed to visualize the graph. We have used the dataset of Journal of Universal Computer Science having 1400 papers and 6090 citations. The manual inspection has revealed that the top ranked papers were actually the most relevant papers. © 2011 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Throughput enhancement of simultaneous multipath communication using modified fast retransmit scheme

Throughput enhancement of simultaneous multipath communicati...

引用

1st International Conference on Computer Networks and Information Technology, ICCNIT'11

作者： Khan, Samiullah Ahmed, Syed Zubair Qadir, Mohammad Abdul Centre for Distributed and Semantic Computing Department of Computer Science Mohammad Ali Jinnah University Islamabad Pakistan

ISBN: (纸本)9781612849416

The increased availability of communication resource through simultaneous use of multiple network interfaces of mobile and fixed devices has enabled higher bandwidth for streaming applications. The out-of-sequence arrival on such multipath transport configurations remains the major challenge to be overcome before the available potential is maximized. In this paper, we propose Modified Fast Retransmit (MFR) Scheme for the multi-homed stream control transmission protocol (SCTP) that minimizes the impact of possible out-of-sequence (OOS) arrival at the destination. The proposed scheme isolates local and global OOS arrivals and adapts fast retransmission strategy for global OOS arrival, in accordance to the end-to-end communication path characteristics. The essence of higher availability of bandwidth is also signified through the modified congestion control mechanism. The proposed scheme produces large boost in throughput of the streams transported through multiple paths, as compared to other schemes;such as Concurrent Multipath Transmission. © 2011 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

MinG: An efficient algorithm to mine graphs for semantic associations

MinG: An efficient algorithm to mine graphs for semantic ass...

引用

1st International Conference on Computer Networks and Information Technology, ICCNIT'11

作者： Hassan, Zohaib Qadir, Mohammad Abdul Centre for Distributed and Semantic Computing Department of Computer Science Mohammad Ali Jinnah University Islamabad Pakistan

ISBN: (纸本)9781612849416

Data in semantic web is modelled in terms of directed labelled graph. Vertices of that graph represent entities and edges represent relationships between those entities. semantic web allows the discovery of relations between entities using the p-operators. In this paper an algorithm to answer p-operators, that is, to find all paths between any two nodes from a graph is proposed. The algorithm is based on p-index, an indexing scheme presented in the PhD thesis of Barton. Our algorithm reduces the computational and space complexity of indexing by not creating a special type of adjacency matrix called Path Type Matrix at each level of indexing which Barton's algorithm did. We only need Path Type Matrices at first and last level of indexing. Thus if an indexing has 100 levels, Barton requires Path Type Matrices at each level and we only require Path Type Matrices at level 1 and level 100. © 2011 IEEE.

关键词： Directed graphs

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：