检索结果-内蒙古大学图书馆

32nd International Conference on Very Large data Bases, VLDB 2006

作者： Wang, Shan Peng, Zhaohui Zhang, Jun Qin, Lu Wang, Sheng Yu, Jeffrey Xu Ding, Bolin School of Information Renmin Univ. of China Key Laboratory of Data Engineering and Knowledge Engineering MOE of China Beijing China Department of Systems Engineering and Engineering Management The Chinese Univ. of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)1595933859

The integration of database and information retrieval techniques provides users with a wide range of high quality services. We present a prototype system, called NUITS, for efficiently processing keyword queries on top of a relational database. Our NUITS allows users to issue simple keyword queries as well as advanced keyword queries with conditions. The efficiency of keyword query processing and the user-friendly result display will also be addressed in this paper. Copyright 2006 VLDB Endowment, ACM

关键词： Query processing

来源：评论

学校读者我要写书评

暂无评论

Review of graph construction and graph learning in stock price prediction 9th

Review of graph construction and graph learning in stock pri...

引用

9th International Conference on Information Technology and Quantitative Management, ITQM 2022

作者： Wang, Yunong Qu, Yi Chen, Zhensong Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China School of Management and Engineering Capital University of Economics and Business Beijing100070 China

Precise prediction of stock prices leads to more profits and more effective risk prevention, which is of great significance to both investors and regulators. Recent years, various kinds of information not directly-relevant with stock prices have received more attention, such as texts, images or connections. These external information has the potential of reflecting or influencing fluctuations, and thus, given the utilization of advanced analyzing techniques, the forecasting performance of stock prices could be promoted substantially. For instance, graph neural network models have expanded into many other disciplines including stock price prediction, and exhibited impressive representation learning ability. However, in stock markets, well-defined graphs are rarely seen and how to formulate the graph structures needed remains a challenging problem. Towards this end, this article presents a comprehensive overview of graph construction and graph learning in stock price prediction, by reviewing the existing studies, summarizing its general paradigm, special cases and proposing possible prospects. Our research not only systematically reveals the feasible ways of constructing graphs in financial markets, but also provides insights for further implementations of graph learning models into stock prediction tasks. © 2022 The Authors. Published by Elsevier B.V.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

Annotation-free artificial intelligence for abdominal computed tomography anomaly detection

引用

EBiomedicine 2025年 111卷 105497页

作者： Jia Fu Mengjie Fang Zhuozhao Zheng Di Dong Department of Radiology Beijing Tsinghua Changgung Hospital School of Clinical Medicine Tsinghua University Beijing 102218 China. Beijing Advanced Innovation Center for Big Data-Based Precision Medicine School of Engineering Medicine Beihang University Beijing 100191 China CAS Key Laboratory of Molecular Imaging Institute of Automation Chinese Academy of Sciences Beijing 100190 China. CAS Key Laboratory of Molecular Imaging Institute of Automation Chinese Academy of Sciences Beijing 100190 China. Electronic address: di.dong@***.

来源：评论

学校读者我要写书评

暂无评论

Magnetic activity and orbital parameters of CC Com based on photometric data,LAMOST low-and medium-resolution spectra

引用

Research in Astronomy and Astrophysics 2021年第4期21卷 129-138页

作者： Zhong-Zhong Zhu Li-Yun Zhang Gang Meng Yao Cheng Liu Long Xianming L.Han Qing-Feng Pi Lin-Yan Jiang College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China College of Physics Guizhou UniversityGuiyang 550025China Guizhou Provincial Key Laboratory of Public Big Data Guizhou UniversityGuiyang 550025China Dept of Physics and AstronomyButler UniversityIndianapolisIN 46208USA College of Medicine Guizhou University of Traditional Chinese MedicineGuiyang 550025China

In this paper,we present four sets of photometric VRI light curves,and several LAMOST low and medium resolution spectra of contact binary CC *** revised the orbital parameters by simultaneously combining with previously published radial velocity measurements using the WilsonDevinney *** used light curves at different observational times to obtain the starspot *** values of the starspot radius are variable in short-and long-term scales,and their longitudes are *** updated the orbital period change of CC Com,and analyzed the periodic *** period of CC Com decreases at a rate of 4.66(±0.20)×10^(-11)d yr^(-1),which may be due to mass transfer from the secondary component to the primary *** oscillation of its orbital period with a period of17.18(0.08)years and amplitude of 0.0018(1)d may be caused by the light time effect(LITE)via a third body of 0.06 M☉dwarf or magnetic activity ***,we obtained one optical spectrum from the LAMOST survey,which gives the spectral type of CC Com as K7±2 *** emissions exist in the Ha,and Ca 11 H&K lines in the observed spectrum,indicating strong chromospheric activity on CC *** the 12 LAMOST medium-resolution spectra,the EWs of Ha line are variable along the phase and time,which may be a plage or flare event.

关键词： binaries:magnetic activity stars:eclipsing stars:individual(CC Com)

来源：评论

学校读者我要写书评

暂无评论

Ngram2vec: Learning improved word representations from ngram co-occurrence statistics

Ngram2vec: Learning improved word representations from ngram...

引用

2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017

作者： Zhao, Zhe Liu, Tao Li, Shen Li, Bofang Du, Xiaoyong School of Information Renmin University of China China Key Laboratory of Data Engineering and Knowledge Engineering MOE China Institute of Chinese Information Processing Beijing Normal University China UltraPower-BNU Joint Laboratory for Artificial Intelligence Beijing Normal University China

ISBN: (纸本)9781945626838

The existing word representation methods mostly limit their information source to word co-occurrence statistics. In this paper, we introduce ngrams into four representation methods: SGNS, GloVe, PPMI matrix, and its SVD factorization. Comprehensive experiments are conducted on word analogy and similarity tasks. The results show that improved word representations are learned from ngram co-occurrence statistics. We also demonstrate that the trained ngram representations are useful in many aspects such as finding antonyms and collocations. Besides, a novel approach of building co-occurrence matrix is proposed to alleviate the hardware burdens brought by ngrams. © 2017 Association for Computational Linguistics.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

A Character-Word Graph Attention Networks for chinese Text Classification

A Character-Word Graph Attention Networks for Chinese Text C...

引用

IEEE International Conference on Big knowledge (ICBK)

作者： Shigang Yang Yongguo Liu Knowledge and Data Engineering Laboratory of Chinese Medicine School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781665438599

Text classification is an important task in natural language processing. Different from English, chinese text owns two representations, character-level and word-level. The former has abundant connotations and the latter owns specific meanings. Current researches often simply concatenated two-level features with little processing and failed to explore the affiliation relation-ship between chinese characters and words. In this paper, we proposed a character-word graph attention network (CW-GAT) to explore the interactive information between characters and words for chinese text classification. A graph attention network is adopted to capture the context of sentences and the interaction between characters and words. Extensive experiments on six real chinese text datasets show that the proposed model outperforms the latest baseline methods.

关键词： Conferences Text categorization Prediction algorithms Natural language processing Classification algorithms Task analysis Faces

来源：评论

学校读者我要写书评

暂无评论

Initializing convolutional filters with semantic features for text classification

Initializing convolutional filters with semantic features fo...

引用

2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017

作者： Li, Shen Zhao, Zhe Liu, Tao Hu, Renfen Du, Xiaoyong Institute of Chinese Information Processing Beijing Normal University China UltraPower-BNU Joint Laboratory for Artificial Intelligence Beijing Normal University China College of Chinese Language and Culture Beijing Normal University China School of Information Renmin University of China China Key Laboratory of Data Engineering and Knowledge Engineering MOE China

ISBN: (纸本)9781945626838

Convolutional Neural Networks (CNNs) are widely used in NLP tasks. This paper presents a novel weight initialization method to improve the CNNs for text classification. Instead of randomly initializing the convolutional filters, we encode semantic features into them, which helps the model focus on learning useful features at the beginning of the training. Experiments demonstrate the effectiveness of the initialization technique on seven text classification tasks, including sentiment analysis and topic classification. © 2017 Association for Computational Linguistics.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Capability description and discovery of Internetware entity

引用

Science China(Information Sciences) 2010年第4期53卷 685-703页

作者： WANG PuWei1*, JIN Zhi2,3* & LIU HongYan4 1Key laboratory of data engineering and knowledge engineering of the Ministry of Education, Renmin University of China, Beijing 100872, China 2Key laboratory of High Confidence Software Technologies of the Ministry of Education, Peking University, Beijing 100871, China 3Academy of Mathematics and System Sciences, chinese Academy of Sciences, Beijing 100190, China 4Department of Management Science and engineering, Tsinghua University, Beijing 100084, China 1. Key Laboratory of Data Engineering and Knowledge Engineering of the Ministry of Education Renmin University of China Beijing 100872 China2. Key Laboratory of High Confidence Software Technologies of the Ministry of Education Peking University Beijing 100871 China3. Academy of Mathematics and System Sciences Chinese Academy of Sciences Beijing 100190 China4. Department of Management Science and Engineering Tsinghua University Beijing 100084 China

Internetware can be formed through aggregation of Internetware entities bottom-up to satisfy the user's requirements. In the process, capability description of Internetware entity plays an important role. This paper proposes a capability description of Internetware entity based on environment ontology. The environment ontology includes environment entities and possible interactions with the environment entities in a particular domain. Tree-like hierarchical state machines are also included in the ontology to describe domain life-cycle of the environment entities. On the basis of the ideas, the capability of Internetware entity is embodied by interacting with environment entities and the changes of the environment entities during the interactions. Finally, this paper describes the matchmaking between capability descriptions of Internetware entities to support the discovery of Internetware entity. An example of online education course is given to illustrate the ideas.

关键词： Internetware capability description domain environment ontology tree-like hierarchical state machine

来源：评论

学校读者我要写书评

暂无评论

data Cleaning of Binary Sensor Events in Activity Recognition by Cluster-Based Methods 7th

Data Cleaning of Binary Sensor Events in Activity Recognitio...

引用

7th International Conference on Human Aspects of IT for the Aged Population, ITAP 2021, held as part of the 23rd International Conference, HCI International 2021

作者： Zhao, Chunyang Que, Xia Yin, Yue Xing, Xiaoman Yang, Jiaoyun An, Ning Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China Medical Imaging Department Chinese Academy of Sciences Suzhou China

ISBN: (纸本)9783030781101

The Ambient Assisted Living (AAL) systems use sensors to detect the daily behavior of older adults and provide necessary assistance based on changes in their cognitive status and physical functions, thus enabling older adults to maintain their independence at home. However, the effectiveness of the AAL systems depends on the accuracy of the data provided by sensors. Namely, when a human error or a hardware failure occurs, the activity recognition model can become inaccurate. This inaccuracy hinders the identification of critical and potentially life-threatening activities. Although there are many methods for cleaning sensor data, there is no method for binary sensors deployed in smart homes. By considering noisy sensor events and unintentional forgetting of turning off the device, this paper proposes two clustering-based methods for denoising and splitting binary sensor events to address possible inaccuracy due to the two mentioned problems. The effectiveness of the proposed methods is verified by the experiments using four machine learning models and three real-world smart home datasets and adopting different sensor configurations. The experimental results demonstrate that compared to the original unprocessed datasets, by combining the two proposed methods, the average accuracy and F-measure are improved by 15.00% and 17.25%, respectively. © 2021, Springer Nature Switzerland AG.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Ferritin nanocages for early theranostics of tumors via inflammation-enhanced active targeting

引用

Science China(Life Sciences) 2022年第2期65卷 328-340页

作者： Bing Jiang Xiaohua Jia Tianjiao Ji Meng Zhou Jiuyang He Kun Wang Jie Tian Xiyun Yan Kelong Fan Nanozyme Medical Center School of Basic Medical SciencesZhengzhou UniversityZhengzhou 450001China CAS Engineering Laboratory for Nanozyme Key Laboratory of Protein and Peptide PharmaceuticalsInstitute of BiophysicsChinese Academy of SciencesBeijing 100101China Key Laboratory of Molecular Imaging of Chinese Academy of Sciences Institute of AutomationChinese Academy of SciencesBeijing 100190China CAS Key Laboratory for Biomedical Effects of Nanomaterials&Nanosafety CAS Center for Excellence in NanoscienceNational Center for Nanoscience and TechnologyBeijing 100190China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of SciencesBeijing 100049China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine School of MedicineBeihang UniversityBeijing 100191China

Engineered nanocarriers have been widely developed for tumor ***,the delivery of imaging probes or therapeutic drugs to the tumor pre-formation site for early and accurate detection and therapy remains a major ***,by using tailor-functionalized human H-ferritin(HFn),we developed a triple-modality nanoprobe IRdye800-M-HFn and achieved the early imaging of tumor cells before the formation of solid tumor ***,we developed an HFn-doxorubicin(Dox)drug delivery system by loading Dox into the HFn protein cage and achieved early-stage tumor *** intravenous injection of HFn nanoprobes enabled the imaging of tumor cells as early as two days after tumor implantation,and the triple-modality imaging techniques,namely,near-infrared fluorescence molecular imaging(NIR-FMI),magnetic resonance imaging(MRI),and photoacoustic imaging(PAI),ensured the accuracy of *** exploration indicated that HFn could specifically penetrate into pre-solid tumor sites by tumor-associated inflammation-mediated blood vessel leakage,followed by effective accumulation in tumor cells by the specific targeting property of HFn to transferrin receptor ***,the HFn-Dox drug delivery system delivered Dox into the tumor pre-formation site and effectively killed tumor cells at early ***800-M-HFn nanoprobes and HFn-Dox provide promising strategies for early-stage tumor diagnosis and constructive implications for early-stage tumor treatment.

关键词： ferritin nanocage early theranostics tumor-associated inflammation multimodality tumor imaging drug delivery

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：