检索结果-内蒙古大学图书馆

2020 international Symposium on Artificial Intelligence in Medical Sciences, ISAIMS 2020

作者： Chen, Juan Lu, Yan Zhang, Ting Ouyang, Zhaolian Institute of Medical Information/Medical Library Chinese Academy of Medical Sciences Peking Union Medical College Beijing China

ISBN: (纸本)9781450388603

Objective: To compare the development status of artificial intelligence (AI) in medicine among the United States (US), China and India with bibliometric analysis. Methods: Articles involving AI in medicine published from 2015 to 2019 were retrieved on March 30, 2020 from web of Science Core Collection. the country-level and the institution-level performance of the US, China and India in the field of AI in medicine were compared with indicators including the amount of papers, 5-year Compound Annual Growth Rate (CAGR) of the amount of papers, the amount of highly-cited papers, the proportion of highly-cited papers and the average citations per paper. In addition, the research hotspots and international cooperation of the three countries in recent 5 years were compared by conducting keywords co-occurrence analysis and co-authorship analysis in VOSviewer. Results: From 2015 to 2019, the US has published 7838 papers and 154 highly-cited papers in the field of AI in medicine, with an average citations per paper to be 9.3, and the proportion of highly-cited papers to be 2.0 %. China has output 6635 papers and 73 highly-cited papers in this field, with an average citations per paper to be 5.3, and the proportion of highly-cited papers to be 1.1%. India has output 3895 papers and 22 highly-cited papers in this field, with an average citations per paper to be 3.6, and the proportion of highly-cited papers to be 0.6%. the 5-year CAGR of the US, China and India in the period of 2015∼2019 were 16.0%, 25.4% and 2.4%, respectively. At the institutional level, most of these indicators were significantly better for the US institutions than for Chinese and Indian ones. there were four research hotspots in this field, namely medical imaging technology, health big data mining, disease prediction with biomarkers and genetic information, and early diagnosis of neurological disease. the three countries focused on different hotspots, with China focusing relatively less on health big data m

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Design and Establishment of Film and Television Recommendation Platform for Optimizing Cold Start Mode

Design and Establishment of Film and Television Recommendati...

引用

Information Technology: IoT and Smart City (ITIoTSC), international conference on

作者： Pinyin Si Yali Qi Qingtao Zeng Jing Wang College of Information Engineering Beijing Institute of Graphic Communication Beijing China

ISBN: (数字)9798350328349

ISBN: (纸本)9798350328356

Today's fast pace and accuracy is what every product merchant considers and what every user wants; and video production often cannot be focused or accurately recommended to users because of copyright issues. this situation makes it less easy for users to get the movies they really like through one platform. So the recommendation platform designed and developed in this paper is to solve the problem of information overload of today's movies and unclear user needs, making the whole recommendation service more personalized than the recommendation information brought by search engines. the recommendation algorithm of the platform mainly uses the most abundant and stable collaborative filtering algorithm based on data mining. A solution to the common cold-start problem in recommendation platforms is proposed. the specific steps are based on collaborative filtering algorithms to make recommendations combined with tag-based recommendations to avoid the vacancy of users' initial data. the platform will generate users' preferred tag values for the tags, and then update the corresponding preferred tag values after each review, and will select recommendations from the preferred tags when the rating data is insufficient or the recommended movies are insufficient; and the recommended list of preferred tags is recommended using the "hottest now" ranking. Eventually the platform can successfully complete two algorithmic recommendations of user CF and item CF based on the initial rating data, and recommend the hottest movies with similar interests at the initial use stage of new users; the mixed recommendation user preference values combined with tags will also be long involved in the subsequent movie and TV recommendations of users and gradually generate user interest-oriented.

关键词： TV Smart cities Reviews Collaborative filtering Redundancy Production search engines

来源：评论

学校读者我要写书评

暂无评论

Efficient temporal keyword search over versioned text 10

Efficient temporal keyword search over versioned text

引用

Proceedings of the 19th acm international conference on Information and knowledge management

作者： Avishek Anand Srikanta Bedathur Klaus Berberich Ralf Schenkel Max-Planck Institute for Informatics Saarbrücken Germany Saarland University Saarbrücken Germany

ISBN: (纸本)9781450300995

Modern text analytics applications operate on large volumes of temporal text data such as web archives, newspaper archives, blogs, wikis, and micro-blogs. In these settings, searching and mining needs to use constraints on the time dimension in addition to keyword constraints. A natural approach to address such queries is using an inverted index whose entries are enriched with valid-time intervals. It has been shown that these indexes have to be partitioned along time in order to achieve efficiency. However, when the temporal predicate corresponds to a long time range, requiring the processing of multiple partitions, naive query processing incurs high cost of reading of redundant entries across *** present a framework for efficient approximate processing of keyword queries over a temporally partitioned inverted index which minimizes this overhead, thus speeding up query processing. By using a small synopsis for each partition we identify partitions that maximize the number of final non-redundant results, and schedule them for processing early on. Our approach aims to balance the estimated gains in the final result recall against the cost of index reading required. We present practical algorithms for the resulting optimization problem of index partition selection. Our experiments with three diverse, large-scale text archives reveal that our proposed approach can provide close to 80% result recall even when only about half the index is allowed to be read.

关键词： partitioned inverted index synopses partition selection time-travel search

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap: Enhancing Entrepreneurship Education in Jordanian Universities

Bridging the Gap: Enhancing Entrepreneurship Education in Jo...

引用

international conference on Social Networks Analysis, Management and Security (SNAMS)

作者： Fuad M. Kreishan Motteh S. Al-Shibly Mohamed Sayed Abou Elseoud Belal Mahmoud AlWadi Mahmoud Alghizzawi Dina Naser Tahat Khalaf Tahat Mohammed Habes Department of Business Economics School of Business University of Jordan Department of Business Administration Amman ArabUniversity Jordan Collage of Business Administration University of Bahrain Bahrain & Sadat Academy for Management Sciences Egypt Department of Basic Sciences (Humanities and Scientific) Al-Zaytoonah University of Jordan Jordan Faculty of Business Amman Arab University Amman Jordan Al Ain University Al Ain UAE Digital media & journalism Dept The University of Jordan Radio & TV department -Yarmouk University Irbid Jordan

ISBN: (数字)9798331518349

ISBN: (纸本)9798331518356

this research aims to understand the nature of entrepreneurship education, identify weaknesses, and propose policies for improvement. It highlights the importance of focusing on entrepreneurship education in Jordan and the broader Middle East region. Employing descriptive analytics, the study combines survey data with a comprehensive web search of Jordanian higher education institutions. the key findings reveal that, although various entrepreneurship courses are offered by Jordanian universities, effective integration of entrepreneurship education into the curricula of all institutions is yet to be achieved. Moreover, the study indicates that entrepreneurship education primarily relies on theoretical knowledge and predominantly adopts a business administration perspective. Based on these results, the study proposes recommendations for enhancing entrepreneurship education by emphasizing the proper incorporation of entrepreneurship courses into all academic disciplines. Additionally, it urges higher education policymakers to establish a realistic model for teaching entrepreneurship, necessitating improvements in the capacity and resources dedicated to entrepreneurship education in Jordan. these improvements should encompass both human resources and infrastructure elements. thus, this study contributes to the existing literature by highlighting the need for enhanced integration and improvement of entrepreneurship education across Jordanian universities.

关键词： Surveys Training Technological innovation Social networking (online) Education Entrepreneurship Stakeholders Security Unemployment web search

来源：评论

学校读者我要写书评

暂无评论

A Model to Enhance Governance Issues through Opinion Extraction

A Model to Enhance Governance Issues through Opinion Extract...

引用

international conference and Workshop on Computing and Communication (IEMCON)

作者： Kamran Shaukat Talha Mahboob Alam Muhammad Ahmed Suhuai Luo Ibrahim A. Hameed Muhammad Shahid Iqbal Jiaming Li Muhammad Atif Iqbal School of Electrical Engineering and Computing The University of Newcastle Newcastle Australia University of Engineering and Technology Lahore Pakistan Norwegian University of Science and Technology Norway Air University Islamabad Pakistan Data61 Commonwealth Scientific and Industrial Research Organization Australia

ISBN: (数字)9781728184166

ISBN: (纸本)9781728184173

We live in a world where data is expanding exponentially. Most of the data is unstructured when obtained through the web. Many organizations, institutes, and governments worldwide gather public views regarding their products, services, or policies. With thousands of reviews about some product, service, or policy, it is impossible to conclude some kind of final thought from it. To handle this, there is a desperate need for a model that can extract meaningful information from data to make correct and timely decisions for the efficient growth of business and smooth running of an organization or government. Otherwise, the practice of collecting and storing data will be ineffective. In this study, we focused on conducting an extensive public survey on issues of Southern Punjab, carry out appropriate processing on collected data and predict trends in public opinion for decision-making. Natural Language Processing (NLP) and Machine Learning (ML) have dealt with this problem. Different data preprocessing techniques have been utilized to remove the noise from data. Our experiments stated that unemployment, poverty, education, and corruption are the major issues of the targeted region. this study will help government officials and non-governmental organizations to be focused on the extracted issues in the specific region.

关键词： Terrorism Government Sociology Education data mining Unemployment Statistics

来源：评论

学校读者我要写书评

暂无评论

A Text mining Analysis of Social Media Criticisms on Tuition Fee Policies at State Universities in Indonesia

A Text Mining Analysis of Social Media Criticisms on Tuition...

引用

international conference on Electrical Engineering, Computer Science and Informatics (EECSI)

作者： Wiyli Yustanti Rindu Puspita Wibawa Yuni Yamasari Andi Iwan Nurhidayat Department of Information System Universitas Negeri Surabaya Surabaya Indonesia Department of Information Technology Education Universitas Negeri Surabaya Surabaya Indonesia Department of Informatics Universitas Negeri Surabaya Surabaya Indonesia Department of Information Management Universitas Negeri Surabaya Surabaya Indonesia

ISBN: (数字)9798350355314

ISBN: (纸本)9798350355321

this study aims to identify public criticism on social media related to the residential tuition policy imposed in state universities in Indonesia. Knowing the public's criticism of the single tuition policy on social media can identify critical issues, understand the public sentiment, and provide insights for policy improvement. the benefits of the process can be used to improve the quality of policies, strengthen relations with the public, increase student satisfaction and welfare, and contribute to academic knowledge about policy analysis using social media. the data came from public comments about tuition fees on Twitter, You'Tube, Instagram, and TikTok platforms. the dataset was labeled as neutral, negative, and positive sentiment in the first step using IndoBERT's pre-trained model. the result of a negative sentiment of 62.26% from the dataset was then used for topic analysis using the Latent Dirichlet Allocation algorithm, and a different number of topics was obtained on each platform with topic compositions for Twitter, YouTube, Instagram, and TikTok of 10, 5, 2, 10 topics respectively. the results of the synthesis from all platforms concluded that seven themes are the main issues discussed in public criticism related to tuition fees, where the top three themes are criticism of government policies that increase tuition fees (48,60/0), corruption cases occur in state universities (20,3 %) and students' concerns about continuing their studies when there is an increase in tuition fees (12,5 % ).

关键词： Government policies Text mining Surveys Video on demand Social networking (online) Reviews Blogs web sites Multimedia communication Resource management

来源：评论

学校读者我要写书评

暂无评论

Meta-analytical biomarker search of EST expression data reveals three differentially expressed candidates

引用

BMC GENOMICS 2012年第Sup7期13卷 S12-S12页

作者： Wu, Timothy H. Chu, Lichieh J. Wang, Jian-Chiao Chen, Ting-Wen Tien, Yin-Jing Lin, Wen-Chang Ng, Wailap V. Natl Yang Ming Univ Inst Biomed Informat Taipei 112 Taiwan Chang Gung Univ Mol Med Res Ctr Tao Yuan Taiwan Natl Yang Ming Univ Dept Biotechnol Taipei 112 Taiwan Natl Yang Ming Univ Lab Sci Med Taipei 112 Taiwan Natl Yang Ming Univ Inst Biotechnol Med Taipei 112 Taiwan Chang Gung Univ Bioinformat Ctr Tao Yuan Taiwan Acad Sinica Inst Stat Sci Taipei 11529 Taiwan Acad Sinica Inst Biomed Sci Taipei Taiwan Natl Yang Ming Univ Ctr Syst & Synthet Biol Taipei 112 Taiwan

Background: Researches have been conducted for the identification of differentially expressed genes (DEGs) by generating and mining of cDNA expressed sequence tags (ESTs) for more than a decade. Although the availability of public databases make possible the comprehensive mining of DEGs among the ESTs from multiple tissue types, existing studies usually employed statistics suitable only for two categories. Multi-class test has been developed to enable the finding of tissue specific genes, but subsequent search for cancer genes involves separate two-category test only on the ESTs of the tissue of interest. this constricts the amount of data used. On the other hand, simple pooling of cancer and normal genes from multiple tissue types runs the risk of Simpson's paradox. Here we presented a different approach which searched for multi-cancer DEG candidates by analyzing all pertinent ESTs in all categories and narrowing down the cancer biomarker candidates via integrative analysis with microarray data and selection of secretory and membrane protein genes as well as incorporation of network analysis. Finally, the differential expression patterns of three selected cancer biomarker candidates were confirmed by real-time qPCR analysis. Results: Seven hundred and twenty three primary DEG candidates (p-value < 0.05 and lower bound of confidence interval of odds ratio >= 1.65) were selected from a curated EST database with the application of Cochran-Mantel-Haenszel statistic (CMH). GeneGO analysis results indicated this set as neoplasm enriched. Cross-examination with microarray data further narrowed the list down to 235 genes, among which 96 had membrane or secretory annotations. After examined the candidates in protein interaction network, public tissue expression databases, and literatures, we selected three genes for further evaluation by real-time qPCR with eight major normal and cancer tissues. the higher than normal tissue expression of COL3A1, DLG3, and RNF43 in some of

关键词： Tissue Type Cancer Genome Anatomy Project Multiple Tissue Type Common Odds Ratio Express Gene Candidate

来源：评论

学校读者我要写书评

暂无评论

Context-based Image Semantic Similarity

Context-based Image Semantic Similarity

引用

international conference on Fuzzy Systems and Knowledge Discovery

作者： Valentina Franzoni Alfredo Milani Simonetta Pallottelli Clement H.C. Leung Yuanxi Li Dept. of Comput. Univ. of Rome La Sapienza Rome Italy

ISBN: (纸本)9781467376839

In this work we propose Context-based Image Similarity, a scheme for discovering and evaluating image similarity in terms of the associated groups of concepts. Several semantic proximity/similarity among image concepts and different concept ontology - WordNet Distance, Wikipedia Distance, Flickr Distance, Confidence, Normalized Google Distance (NGD), Pointwise Mutual Information (PMI) and PMING, have been considered as elementary metrics for the context. Comparing to Content Based Image Retrieval (CBIR), which measures the image content similarities by low level features, the proposed Context-based Image Similarity outperformed CBIR in measuring the deep concept similarity and relationship of images. Experimental results, obtained in the domain of images semantic similarity using search engine based tag similarity, show the adequacy of the proposed approach in order to reflect the collective notion of semantic similarity.

关键词： semantic Context-based image retrieval data mining collective knowledge knowleadge discovery

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：