检索结果-内蒙古大学图书馆

2018 ISWC Posters and Demonstrations, Industry and Blue Sky Ideas Tracks, ISWC-P and D-Industry-BlueSky 2018

作者： Meng, Chenhong Zhang, Xiaowang Xiao, Guohui Feng, Zhiyong Qi, Guilin School of Computer Science and Technology Tianjin University Tianjin300350 China School of Computer Software Tianjin University Tianjin300350 China Faculty of Computer Science Free University of Bozen-Bolzano BolzanoI-39100 Italy School of Computer Science and Engineering Southeast University Nanjing211189 China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin300350 China

This poster shows an ontology-mediated query answering system (gOWL) based on pure materialization to avoid query rewriting online. gOWL shows that answering queries over a partial materialization of the chase is complete for a large fragment of practical queries with bounded depth. From a system engineering perspective, the materialization approach allows us to design a modular architecture to integrate off-the-shelf efficient SPARQL query engines. The poster will be based on DBpedia and UOBM datasets. We will compare the performance of gOWL with PAGOdA, Ontop, and Pellet (with speedup up to three orders of magnitude). © 2018 CEUR-WS. All rights reserved.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

RESIDUAL SHUFFLING CONVOLUTIONAL NEURAL NETWORKS for DEEP SEMANTIC IMAGE SEGMENTATION USING MULTI-MODAL DATA

RESIDUAL SHUFFLING CONVOLUTIONAL NEURAL NETWORKS for DEEP SE...

引用

2018 ISPRS TC II Mid-term Symposium "Towards Photogrammetry 2020"

作者： Chen, K. Weinmann, M. Gao, X. Yan, M. Hinz, S. Jutzi, B. Weinmann, M. Key Laboratory of Spatial Information Processing and Application System Technology Institute of Electronics Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Institute of Computer Science II University of Bonn Bonn Germany Institute of Photogrammetry and Remote Sensing Karlsruhe Institute of Technology Karlsruhe Germany

In this paper, we address the deep semantic segmentation of aerial imagery based on multi-modal data. Given multi-modal data composed of true orthophotos and the corresponding Digital Surface Models (DSMs), we extract a variety of hand-crafted radiometric and geometric features which are provided separately and in different combinations as input to a modern deep learning framework. The latter is represented by a Residual Shuffling Convolutional Neural Network (RSCNN) combining the characteristics of a Residual Network with the advantages of atrous convolution and a shuffling operator to achieve a dense semantic labeling. Via performance evaluation on a benchmark dataset, we analyze the value of different feature sets for the semantic segmentation task. The derived results reveal that the use of radiometric features yields better classification results than the use of geometric features for the considered dataset. Furthermore, the consideration of data on both modalities leads to an improvement of the classification results. However, the derived results also indicate that the use of all defined features is less favorable than the use of selected features. Consequently, data representations derived via feature extraction and feature selection techniques still provide a gain if used as the basis for deep semantic segmentation. © 2018 Copernicus GmbH. All rights reserved.

关键词： Aerial Imagery CNN Deep Learning Multi-Modal Data Residual Network Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

User Identity Authentication and Identification Based on Multi-Factor Behavior Features

User Identity Authentication and Identification Based on Mul...

引用

IEEE Globecom Workshops

作者： Xing Ding Changgen Peng Hongfa Ding Maoni Wang Hui Yang Qinyong Yu College of Computer Science & Technology State Key Laboratory of Public Big Data Guizhou University Guiyang China College of Information Guizhou University of Financial and Economics Guiyang China National Engineering Laboratory Big Data Application on Improving Government Governance Capabilities Guiyang China CETC Big Data Research Institute Co. Ltd Guiyang China

ISBN: (数字)9781728109602

ISBN: (纸本)9781728109619

Behavior-based identity authentication has been of research interests due to its low cost and the fact that such authentication factors cannot easily copied nor stolen. However, single behavior feature authentication usuall cannot gaurantee sufficient accuracy. In this paper, a multi-factor behavior features identity authentication method is proposed by combining factors of mouse, keystroke and address. We apply support vector machine by using the information divergence of features as the weight of the linear kernel function to solve quantification's problem of features influence degree on authentication. The tailored support vector machine is applied to multi-factor behavior features to identity authentication. Our experimental results show that the improved support vector machine is better than both the linear and Gaussian kernel support vector machines for identity authentication in accuracy. The proppsed method can be applied to large volume users' identity authentication cases where their behavior features are likely to be similar.

关键词： Authentication Mice IP networks Feature extraction Support vector machines Hidden Markov models Presses

来源：评论

学校读者我要写书评

暂无评论

Paddy rice methane emissions across Monsoon Asia

引用

Remote Sensing of Environment 2023年 284卷

作者： Ouyang, Zutao Jackson, Robert B. McNicol, Gavin Fluet-Chouinard, Etienne Runkle, Benjamin R.K. Papale, Dario Knox, Sara H. Cooley, Sarah Delwiche, Kyle B. Feron, Sarah Irvin, Jeremy Andrew Malhotra, Avni Muddasir, Muhammad Sabbatini, Simone Alberto, Ma. Carmelita R. Cescatti, Alessandro Chen, Chi-Ling Dong, Jinwei Fong, Bryant N. Guo, Haiqiang Hao, Lu Iwata, Hiroki Jia, Qingyu Ju, Weimin Kang, Minseok Li, Hong Kim, Joon Reba, Michele L. Nayak, Amaresh Kumar Roberti, Debora Regina Ryu, Youngryel Swain, Chinmaya Kumar Tsuang, Benjei Xiao, Xiangming Yuan, Wenping Zhang, Geli Zhang, Yongguang Department of Earth System Science Stanford University StanfordCA United States Woods Institute for the Environment Stanford University StanfordCA United States Precourt Institute for Energy Stanford University StanfordCA United States Department of Earth and Environmental Sciences University of Illinois Chicago ChicagoIL United States Department of Biological and Agricultural Engineering University of Arkansas FayettevilleAR United States University of Tuscia Viterbo Italy IAFES division Viterbo Italy Department of Geography The University of British Columbia VancouverBC Canada Department of Geography University of Oregon EugeneOR United States Department of Environmental Science Policy And Management UC Berkeley BerkeleyCA United States Campus Fryslan University of Groningen Groningen Netherlands Department of Computer Science Stanford University StanfordCA United States Department of Geography University of Zurich Zurich Switzerland International Rice Research Institute Laguna Philippines Ispra Italy Taiwan Agricultural Research Institute Taichung Wufeng Taiwan Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing China USDA ARS Delta Water Management Research Unit JonesboroAR United States Fudan University Ministry of Education Key Laboratory for Biodiversity Science and Ecological Engineering and Coastal Ecosystems Research Station of the Yangtze River Estuary Shanghai China / Jiangsu Key Laboratory of Agricultural Meteorology Nanjing University of Information Science and Technology Nanjing China Department of Environmental Science Shinshu University Matsumoto Japan China Meteorological Administration Institute of Atmospheric Environment Shenyang China International Institute for Earth System Sciences Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing University Jiangsu Nanjing210023 China National Center for AgroM

Although rice cultivation is one of the most important agricultural sources of methane (CH4) and contributes ∼8% of total global anthropogenic emissions, large discrepancies remain among estimates of global CH4 emissions from rice cultivation (ranging from 18 to 115 Tg CH4 yr−1) due to a lack of observational constraints. The spatial distribution of paddy-rice emissions has been assessed at regional-to-global scales by bottom-up inventories and land surface models over coarse spatial resolution (e.g., > 0.5°) or spatial units (e.g., agro-ecological zones). However, high-resolution CH4 flux estimates capable of capturing the effects of local climate and management practices on emissions, as well as replicating in situ data, remain challenging to produce because of the scarcity of high-resolution maps of paddy-rice and insufficient understanding of CH4 predictors. Here, we combine paddy-rice methane-flux data from 23 global eddy covariance sites and MODIS remote sensing data with machine learning to 1) evaluate data-driven model performance and variable importance for predicting rice CH4 fluxes;and 2) produce gridded up-scaling estimates of rice CH4 emissions at 5000-m resolution across Monsoon Asia, where ∼87% of global rice area is cultivated and ∼ 90% of global rice production occurs. Our random-forest model achieved Nash-Sutcliffe Efficiency values of 0.59 and 0.69 for 8-day CH4 fluxes and site mean CH4 fluxes respectively, with land surface temperature, biomass and water-availability-related indices as the most important predictors. We estimate the average annual (winter fallow season excluded) paddy rice CH4 emissions throughout Monsoon Asia to be 20.6 ± 1.1 Tg yr−1 for 2001–2015, which is at the lower range of previous inventory-based estimates (20–32 CH4 Tg yr−1). Our estimates also suggest that CH4 emissions from paddy rice in this region have been declining from 2007 through 2015 following declines in both paddy-rice growing area and emission rates per unit

关键词： Climate change

来源：评论

学校读者我要写书评

暂无评论

SVM-based deep stacking networks

arXiv

引用

arXiv 2019年

作者： Wang, Jingyuan Feng, Kai Wu, Junjie MOE Engineering Research Center of Advanced Computer Application Technology School of Computer Science Engineering Beihang University Beijing100191 China Beijing Key Laboratory of Emergency Support Simulation Technologies for City Operations School of Economics and Management Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

The deep network model, with the majority built on neural networks, has been proved to be a powerful framework to represent complex data for high performance machine learning. In recent years, more and more studies turn to nonneural network approaches to build diverse deep structures, and the Deep Stacking Network (DSN) model is one of such approaches that uses stacked easy-to-learn blocks to build a parameter-training-parallelizable deep network. In this paper, we propose a novel SVM-based Deep Stacking Network (SVM-DSN), which uses the DSN architecture to organize linear SVM classifiers for deep learning. A BP-like layer tuning scheme is also proposed to ensure holistic and local optimizations of stacked SVMs simultaneously. Some good math properties of SVM, such as the convex optimization, is introduced into the DSN framework by our model. From a global view, SVM-DSN can iteratively extract data representations layer by layer as a deep neural network but with parallelizability, and from a local view, each stacked SVM can converge to its optimal solution and obtain the support vectors, which compared with neural networks could lead to interesting improvements in anti-saturation and interpretability. Experimental results on both image and text data sets demonstrate the excellent performances of SVM-DSN compared with some competitive benchmark models. Copyright © 2019, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Bursty Events Detection Approach on Chinese Microblog Based on Splay Tree Optimization

Bursty Events Detection Approach on Chinese Microblog Based ...

引用

International Conference on Instrumentation, Measurement, computer, Communication and Control (IMCCC)

作者： Ruiguo Yu Yuwang Lin Mankun Zhao Mei Yu School of Computer Science and Technology Tianjin University Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Tianjin Key Laboratory of Advanced Networking Tianjin China

ISBN: (数字)9781538682463

ISBN: (纸本)9781538682470

As a new media, Microblog plays an important role in people's daily life. People can gain, publish and share information in time, and interact with other users. With the characteristics of small text, spreading fast and great impact, an increasing number of scholars choose Microblog as their research object. Since Microblog generates a huge amount of data, bursty events detection seems to be very important. An algorithm based on the splay tree optimization is proposed so as to reduce the burst words clustering by recording the existing results. This paper adopts the method of trade space for time to optimize the algorithm, which changes the original complexity of the burst words clustering algorithm O(SN 3 ) into O(SN 2 log(N). The worst space complexity becomes O(N 2 ), however, it turns to be O(LN) by merely recording the effective results combined with the actual situation. Value L is related to the scale of cluster in the clustering result.

关键词： Event detection Clustering algorithms Hidden Markov models Complexity theory Twitter Current measurement

来源：评论

学校读者我要写书评

暂无评论

A new algorithm for attitude detemination based on chicken swarm optimization 7

A new algorithm for attitude detemination based on chicken s...

引用

7th International Conference on Digital Home, ICDH 2018

作者： Ji, Yuanfa Wu, Yue Sun, Xiyan Yan, Suqing Chen, Qidong Du, Baoqiang Guangxi Key Laboratory of Precision Navigation Technology and Application Guilin University of Electronic Technology Guilin541004 China National and Local Joint Engineering Research Center of Satellite Navigation and Location Service Guilin541004 China Guangxi Experiment Center of Information Science Guilin University of Electronic Technology Guilin541004 China Key Laboratory of Radio Wave Environment and Modeling Technology Qingdao266000 China School of Computer and Communication Engineering Zhengzhou University of Light Industry Zhengzhou450000 China

ISBN: (纸本)9781538694961

In this paper a new algorithm for global navigation satellite system attitude determination based on CSO (Chicken Swarm Optimization) was developed. A distinct feature of this algorithm is the new optimization. The traditional LAMBDA algorithm for integer ambiguity resolution is time-consuming due to the large search space and complex calculation, so the attitude determination time is longer correspondingly. The optimization algorithm without search space based on least squares proposed in this paper improves the efficiency of fixing the integer ambiguity and applied to solve attitude problems. In conclusion, it is proven to work, offering a very efficient method of attitude determination. © 2018 IEEE.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

EKT: Exercise-aware knowledge tracing for student performance prediction

arXiv

引用

arXiv 2019年

作者： Liu, Qi Huang, Zhenya Yin, Yu Chen, Enhong Xiong, Hui Su, Yu Hu, Guoping Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Techonology University of Science and Technology of China Management Science and Information Systems Department Rutgers Business School State University of New Jersey Rutgers United States Iflytek Research Iflytek Co. Ltd Hefei Anhui000000 China

For offering proactive services (e.g., personalized exercise recommendation) to the students in computer supported intelligent education, one of the fundamental tasks is predicting student performance (e.g., scores) on future exercises, where it is necessary to track the change of each student's knowledge acquisition during her exercising activities. Unfortunately, to the best of our knowledge, existing approaches can only exploit the exercising records of students, and the problem of extracting rich information existed in the materials (e.g., knowledge concepts, exercise content) of exercises to achieve both more precise prediction of student performance and more interpretable analysis of knowledge acquisition remains underexplored. To this end, in this paper, we present a holistic study of student performance prediction. To directly achieve the primary goal of performance prediction, we first propose a general Exercise-Enhanced Recurrent Neural Network (EERNN) framework by exploring both student's exercising records and the text content of corresponding exercises. In EERNN, we simply summarize each student's state into an integrated vector and trace it with a recurrent neural network, where we design a bidirectional LSTM to learn the encoding of each exercise from its content. For making final predictions, we design two implementations on the basis of EERNN with different prediction strategies, i.e., EERNNM with Markov property and EERNNA with Attention mechanism. Then, to explicitly track student's knowledge acquisition on multiple knowledge concepts, we extend EERNN to an explainable Exercise-aware Knowledge Tracing (EKT) framework by incorporating the knowledge concept information, where the student's integrated state vector is now extended to a knowledge state matrix. In EKT, we further develop a memory network for quantifying how much each exercise can affect the mastery of students on multiple knowledge concepts during the exercising process. Finally, we con

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Multisource multisink optimal evacuation routing with dynamic network changes: A geometric algebra approach

Multisource multisink optimal evacuation routing with dynami...

引用

作者： Yu, Zhaoyuan Li, Dongshuang Zhu, Shuai Luo, Wen Hu, Yong Yuan, Lingwang Key Laboratory of Virtual Geographic Environment MOE Nanjing Normal University Nanjing210023 China Nanjing210023 China Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing China Department of Computer Science and Technology Nanjing Normal University Nanjing210023 China

In this paper, we introduced geometric algebra to develop a new multisource multisink optimal evacuation route planning method. A dynamically updatable data structure and a matrix-based greedy searching algorithm were developed to support the dynamic evacuation route searching for multiple evacuees. Unlike most existing methods, which iteratively search the optimal path for each evacuee, our method can search all the possible evacuation routes synchronously. The dynamic updating of the network topography, weights, and constraints during the route searching is direct and flexible, thus can support the evacuation in dynamic cases. The method is demonstrated and tested by an evacuation case in the city of Changzhou, China. The simulation experiments suggest that the method can well support the dynamic route searching in large scales with dynamic weight changes. Copyright © 2017 John Wiley & Sons, Ltd.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Establishment and Analysis of Face Recognition Model Based on Least Square Method

Establishment and Analysis of Face Recognition Model Based o...

引用

2018 International Conference on Mathematics, Modelling, Simulation and Algorithms（MMSA2018）

作者： Fan Yang Xuewen Tan School of Mathematics and Computer Science Yunnan Minzu University Key Laboratory of IOT Application Technology of Universities in Yunnan Province Yunnan Minzu University

ISBN: (纸本)9781510863064

Face recognition technology is studied to realize the reconstructed image after many years. The principal component analysis of local facial feature extraction using MATLAB images, two value curve, corrosion and boundary contour extraction, vertical and horizontal projection contour extraction after the picture is compared, obtained by the least square method fitting the corresponding function. The validity and accuracy of the model are verified by simulation.

关键词： gray level processing feature extraction projection least square method

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：