检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Jin, Xin Wu, Le Zhao, Geng Li, Xiaodong Zhang, Xiaokun Ge, Shiming Zou, Dongqing Zhou, Bin Zhou, Xinghui Department of Cyber Security Beijing Electronic Science and Technology Institute Beijing100070 China Cetc Big Data Research Institute Co. Ltd. Guiyang Guizhou550018 China Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China SenseTime Research Beijing100084 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Peng Cheng Laboratory Beijing100191 China

Image aesthetic quality assessment has been a relatively hot topic during the last decade. Most recently, comments type assessment (aesthetic captions) has been proposed to describe the general aesthetic impression of an image using text. In this paper, we propose Aesthetic Attributes Assessment of Images, which means the aesthetic attributes captioning. This is a newformula of image aesthetic assessment, which predicts aesthetic attributes captions together with the aesthetic score of each attribute. We introduce a new dataset named DPC-Captions which contains comments of up to 5 aesthetic attributes of one image through knowledge transfer from a full-annotated small-scale dataset. Then, we propose Aesthetic Multi-Attribute Network (AMAN), which is trained on a mixture of fully-annotated small-scale PCCD dataset and weakly-annotated large-scale DPC-Captions dataset. Our AMAN makes full use of transfer learning and attention model in a single framework. The experimental results on our DPC-Captions and PCCD dataset reveal that our method can predict captions of 5 aesthetic attributes together with numerical score assessment of each attribute. We use the evaluation criteria used in image captions to prove that our specially designed AMAN model outperforms traditional CNN-LSTM model and modern SCA-CNN model of image captions. Copyright © 2019, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A multidimensional space based fault-tolerant control system design method for commercial aircraft

A multidimensional space based fault-tolerant control system...

引用

CSAA/IET International Conference on Aircraft Utility Systems, AUS 2018

作者： Wang, Jun Wang, Shaoping Wang, Xingjian Tomovic, Mileta M. Shi, Cun School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data-based Precision Medicine Beihang University Beijing100191 China State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang University Hangzhou310027 China Engineering Technology Department Old Dominion University NorfolkVA United States

ISBN: (纸本)9781785617911

The fault-tolerant control techniques can maintain the safety of aircraft under fault conditions. Different strategies should be used to response to specific fault conditions according to the fault diagnosis information. To improve the fault-tolerant control design efficiency, this paper propose a multidimensional space based method, the flight/actuation system is divided and modeled by using the multidimensional space first, and then operator norm is used to map and quantize the fault information, finally, the decision making algorithm is designed to match the fault-tolerant control strategies to specific fault conditions. © 2018 IET Conference Publications. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Novel Texture Generation Super Resolution Model

引用

Procedia Computer Science 2019年 162卷 924-931页

作者： Biao Li Yong Shi Sujuan Li Bo Wang Zhiquan Qi Jiabin Liu School of Economics and Management University of Chinese Academy of Sciences Beijing 101408 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China College of Information Science and Technology University of Nebraska at Omaha NE 68182 USA Department of Otology the First Affiliated Hospital of Zhengzhou University No. 1 eastern Jianshe road Zhengzhou Henan 450052 China School of Information Technology and Management University of International Business and Economics Beijing 100029 China Department of Computer Science and Engineering Texas A&M University TX 77843 USA

Recently, super-resolution methods pursue visual pleasant details attract more attention in academic circle. Unlike former accurate driving models, they leverage new losses measured the difference of features extracting from a pre-trained deep learning model. Moreover, the popular GANs structure are introduced to approach better outputs. In general, these new visual feeling promoting losses are constrained by the learning ability of model and effected by the weakness of GANs. In order to address these problems, we propose a novel SR method to generating abundant details. Based on former SR methods and texture generated models, we combine new model constructure and integrated loss function to achieve our goal. The new constructure derives from the very thought that more information from the LR input leads to more accurate results. The new integrated loss try to decrease the weakness of each one by corresponding loss.. Experiments show that our model achieves higher quality generations than former methods.

关键词： Super Resolution Multi Scale Smooth Loss Visual Quality

来源：评论

学校读者我要写书评

暂无评论

Research on Mining Global Maximal Frequent Itemsets for Health big data 3rd

Research on Mining Global Maximal Frequent Itemsets for Heal...

引用

2017 IEEE 第3届信息技术与机电一体化工程国际学术会议(ITOEC 2017)

作者： Bo He Jianhui Pei School of Computer Science and Engineering ChongQing University of Technology Key Laboratory of Statistical information technology and data mining State Statistics BureauChengDu University of Information Technology Guizhou Key Laboratory of Power Big Data Guizhou Institute of Technology

Traditional mining algorithms did not suit mining of global maximal frequent ***,a new mining algorithm of global maximal frequent itemsets for health big data,namely,NMAGMFI algorithm

ISBN: (纸本)9781509053643;9781509053636

Traditional mining algorithms did not suit mining of global maximal frequent ***,a new mining algorithm of global maximal frequent itemsets for health big data,namely,NMAGMFI algorithm

关键词： Itemsets data mining Frequency modulation big data Algorithm design and analysis Information technology

来源：评论

学校读者我要写书评

暂无评论

An incremental mining algorithm for global maximum frequent itemsets based on health big data 2

An incremental mining algorithm for global maximum frequent ...

引用

2017 IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC 2017)

作者： Bo He Jianhui Pei Hongyuan Zhang School of Computer Science and Engineering ChongQing University of Technology Key Laboratory of Statistical information technology and data mining State Statistics Bureau ChengDu University of Information Technology Guizhou Key Laboratory of Power Big Data Guizhou Institute of Technology

ISBN: (纸本)9781509064151;9781509064144

The global maximum frequent itemsets need to be updated because of incremental distributed database. On the base of the fast mining algorithm for global maximum frequent itemsets, an incremental mining algorithm for global maximum frequent itemsets based on health big data was proposed, namely,IMAGMFI algorithm. Firstly, the global frequent items were ***, the FP-tree was reconstructed by incremental distributed database. Third, the global maximum frequent itemsets of incremental distributed database were mined. Last,the global maximum frequent itemsets were gained by the strategy of top-down. The experimental results show that IMAGMFI algorithm is effective.

关键词： FP-tree Global Maximum Frequent Itemset Increasing Mining Algorithm

来源：评论

学校读者我要写书评

暂无评论

s-LWSR: Super lightweight super-resolution network

arXiv

引用

arXiv 2019年

作者： Li, Biao Liu, Jiabin Wang, Bo Qi, Zhiquan Shi, Yong School of Economics and Management University of Chinese Academy of Sciences Beijing101408 China 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 Information Technology and Management University of International Business and Economics Beijing100029 China Department of Computer Science and Engineering Texas A&M University College StationTX77843 United States College of Information Science and Technology University of Nebraska OmahaNE68182 United States

Deep learning (DL) architectures for super-resolution (SR) normally contain tremendous parameters, which has been regarded as the crucial advantage for obtaining satisfying performance. However, with the widespread use of mobile phones for taking and retouching photos, this character greatly hampers the deployment of DL-SR models on the mobile devices. To address this problem, in this paper, we propose a super lightweight SR network: s-LWSR. There are mainly three contributions in our work. Firstly, in order to efficiently abstract features from the low resolution image, we build an information pool to mix multi-level information from the first half part of the pipeline. Accordingly, the information pool feeds the second half part with the combination of hierarchical features from the previous layers. Secondly, we employ a compression module to further decrease the size of parameters. Intensive analysis confirms its capacity of trade-off between model complexity and accuracy. Thirdly, by revealing the specific role of activation in deep models, we remove several activation layers in our SR model to retain more information for performance improvement. Extensive experiments show that our s-LWSR, with limited parameters and operations, can achieve similar performance to other cumbersome DL-SR methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

HMOD： An Omics database for Herbal Medicine Plants

引用

Molecular Plant 2018年第5期11卷 757-759页

作者： Xiao Wang Jiajin Zhang Simei He Yuanni Gao Xiaoqin Ma Yun Gao Guanghui Zhang Ling Kui Wen Wang Ying wang Shengchao Yang Yang Dong State Key Laboratory of Genetic Resources and Evolution Kunming Institute of Zoology Chinese Academy of Sciences Kunming 650223 People's Republic of China Kunming College of Life Science University of Chinese Academy of Sciences Kunming 650204 People's Republic of China School of Information Engineering Yunnan Agricultural University Kunming 650201 People's Republic of China State Key Laboratory of Conservation and Utilization of Bio-resources in Yunnan The Key Laboratory of Medicinal Plant Biology of Yunnan ProvinceNational & Local Joint Engineering Research Center on Germplasms Innovation & Utilization of Chinese Medicinal Materials in Southwest China Yunnan Agricultural University Kunming 650201 People's Republic of China Nowbio Biotech Inc. Kunming 650201 People's Republic of China Province Key Laboratory Biological Big Data College Yunnan Agricultural University Kunming 650201 People's Republic of China Key Laboratory of South China Agricultural Plant Molecular Analysis andGenetic Improvement South China Botanical Garden Chinese Academy of Sciences Guangzhou 510650 People's Republic of China

Dear Editor ,More than 50% of drugs are derived from chemical compounds that have been isolated from various plants （Fabricant and Farnsworth, 2001; Yarnell and Abascal, 2002）. With the development of sequencing technology and synthetic biology, we can obtain molecular information from the transcriptomic and genomic data of plants and then utilize bacteria to synthesize desired chemical compounds （Atanasov et al., 2015; Smanski et al., 2016）. Increasing numbers of researchers have started to publish omics data generated from herbal plants.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Photoluminescence: MoS2and Perylene Derivative Based Type‐II Heterostructure: Bandgap engineering and Giant Photoluminescence Enhancement (Adv. Mater. Interfaces 2/2020)

引用

Advanced Materials Interfaces 2020年第3期7卷

作者： Sk Md Obaidulla Mohammad Rezwan Habib Yahya Khan Yuhan Kong Tao Liang Mingsheng Xu State Key Laboratory of Silicon Materials College of Information Science & Electronic Engineering Zhejiang University Hangzhou 310027 P. R. China Department of Polymer Science and Engineering Zhejiang University Hangzhou 310027 P. R. China College of Big Data and Information Engineering Guizhou University Guiyang 550025 P. R. China

来源：评论

学校读者我要写书评

暂无评论

Band structure of silicon and germanium thin films based on first principles

引用

Chinese Physics B 2017年第3期26卷 478-482页

作者：吴学科黄伟其黄忠梅秦朝建董泰阁王刚唐延林 College of Big Data and Information Engineering Guizhou University Guiyang 550025 China Institute of Nanophotonic Physics Guizhou University Guiyang 550025 China State Key Laboratory of Surface Physics Key Laboratory of Micro and Nano Photonic Strnctures (Ministry of Education) and Department of Physics Fudan University Shanghai 200433 China State Key Laboratory of Ore Deposit Geochemistry Institute of Geochemistry Chinese Academy of Sciences Guiyang 550003 China

In nanomaterials, optical anisotropies reveal a fundamental relationship between structural and optical properties, in which directional optical properties can be exploited to enhance the performance of optoelectronic devices. First principles calculation based on density functional theory （DFT） with the generalized gradient approximation （GGA） are carried out to investigate the energy band gap structure on silicon （Si） and germanium （Ge） nanofilms. Simulation results show that the band gaps in Si （100） and Ge （111） nanofilms become the direct-gap structure in the thickness range less than 7.64 nm and 7.25 nm respectively, but the band gaps of Si （111） and Ge （110） nanofilms still keep in an indirect-gap structure and are independent on film thickness, and the band gaps of Si （110） and Ge （100） nanofilms could be transferred into the direct-gap structure in nanofilms with smaller thickness. It is amazing that the band gaps of Si（1-x）/ZGexSi（1-x）/2 sandwich structure become the direct-gap structure in a certain area whether （111） or （100） surface. The band structure change of Si and Ge thin films in three orientations is not the same and the physical mechanism is very interesting, where the changes of the band gaps on the Si and Ge nanofilms follow the quantum confinement effects.

关键词： direct band gap first principles calculation quantum confinement effect nanofilms

来源：评论

学校读者我要写书评

暂无评论

A holistic approach to aligning geospatial data with multidimensional similarity measuring

引用

International Journal of Digital Earth 2018年第8期11卷 845-862页

作者： Li Yu Peiyuan Qiu Xiliang Liu Feng Lu Bo Wan State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources ResearchChinese Academy of SciencesBeijingPeople’s Republic of China National Science Library Chinese Academy of SciencesBeijingPeople’s Republic of China Fujian Collaborative Innovation Center for Big Data Applications in Governments FuzhouPeople’s Republic of China Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application NanjingPeople’s Republic of China Faculty of Information Engineering China University of GeosciencesWuhanPeople’s Republic of China

Semantically aligning the heterogeneous geospatial datasets(GDs)produced by different organizations demands efficient similarity matching ***,the strategies employed to align the schema(concept and property)and instances are usually not reusable,and the effects of unbalanced information tend to be neglected in GD *** solve this problem,a holistic approach is presented in this paper to integrally align the geospatial entities(concepts,properties and instances)***,lexical,structural and extensional similarity metrics are designed and automatically aggregated by means of approval *** presented approach is validated with real geographical semantic webs,Geonames and *** with the well-known extensional-based aligning system,the presented approach not only considers more information involved in GD alignment,but also avoids the artificial parameter setting in metric *** reduces the dependency on specific information,and makes the alignment more robust under the unbalanced distribution of various information.

关键词： Geospatial data data alignment similarity matching semantic web

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：