检索结果-内蒙古大学图书馆

Build a Tourism-Specific Sentiment Lexicon Via Word2vec

Annals of data Science 2018年第1期5卷 1-7页

作者： Li, Wei Zhu, Luyao Guo, Kun Shi, Yong Zheng, Yuanchun School of Economics and Management University of Chinese Academy of Sciences Beijing China Fictitious Economy and Data Science Research Center Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China College of Information Science and Technology University of Nebraska at Omaha OmahaNE68182 United States

Online travel and online travel culture developed fast in China recently years while useful knowledge still hidden under a large number of tourism reviews. Therefore, we need effective sentiment analysis methods to mine useful knowledge which can help tourism websites make decisions and improve their travel products. Some data-driven sentiment lexicons have poor performance on sentiment polarity classification due to lack of semantic information. Thus, we propose an effective and more proper data-driven sentiment lexicon construction method incorporating manually labeled sentiment scores, semantic similarity information that is introduced by machine learning method word2vec. Experimental results demonstrate that our method improves the performance of tourism sentiment analysis significantly. © 2018, Springer-Verlag GmbH Germany.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

ALOR: Adaptive layout optimization of raft groups for heterogeneous distributed key-value stores 1

引用

15th IFIP International Conference on Network and Parallel Computing, NPC 2018

作者： Wang, Yangyang Chai, Yunpeng Wang, Xin Key Laboratory of Data Engineering and Knowledge Engineering MOE Beijing China School of Information Renmin University of China Beijing China College of Intelligence and Computing Tianjin University Tianjin China

ISBN: (数字)9783030056773

ISBN: (纸本)9783030056766

Many distributed key-value storage systems employ the simple and effective Raft protocol to ensure data consistency. They usually assume a homogeneous node hardware configuration for the underlying cluster and thus adopt even data distribution schemes. However, today’s distributed systems tend to be heterogeneous in nodes’ I/O devices due to the regular worn I/O device replacement and the emergence of expensive new storage media (e.g., non-volatile memory). In this paper, we propose a new data layout scheme called Adaptive Layout Optimization of Raft groups (ALOR), considering the hardware heterogeneity of the cluster. ALOR aims to optimize the data layout of Raft groups to achieve a better practical load balance, which leads to higher performance. ALOR consists of two components: leader migration in Raft groups and skewed data layout based on cold data migration. We conducted experiments on a practical heterogeneous cluster, and the results indicate that, on average, ALOR improves throughput by 36.89%, reduces latency and 99th percentile tail latency by 24.54% and 21.32%, respectively. © IFIP International Federation for Information Processing 2018.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Motion Coordination of Multiple Robots Based on Deep Reinforcement Learning

Motion Coordination of Multiple Robots Based on Deep Reinfor...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Xiuzhao Hao Zhihao Wu Haiguang Zhou Xiangpeng Bai Youfang Lin Sheng Han Beijing Key Laboratory of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University Beijing China Systems Engineering Research Institude Beijing China

Multi-robot motion coordination is a sequential decision problem that controls each robot's action through a coordination mechanism to avoid collisions and reach their respective destinations. This problem can be viewed as a Markov Decision Process. Therefore, under determinate conditions of the motion path, we make the attempt of applying deep reinforcement learning (DRL) to solve the motion coordination problems. In this paper, in order to make this problem solvable through RL methods, we design a Path Checkerboard Diagram (PCD) to represent the collision relationship among different paths and determine whether collisions occur when the agent takes action. Technically, we design the states, actions and reward function. However, the traditional Deep Q-Networks (DQN) algorithm has the problem of overestimation of state-action values and high approximation error variance of the target values. To fit the motion coordination problem scenario, we further propose a new algorithm Multi-Loss Double DQN (MLDDQN) based on the Double DQN (DDQN), which minimizes the weighted sum of loss of different target networks we have learned before. We evaluate the performance of our algorithm through the different motion coordination tasks. Results suggest that our MLDDQN method yields remarkable improvements in terms of the success rate, success steps and the stability of training process compared with the original DDQN algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning compact binary codes for fingerprint indexing

引用

Frontiers of Information Technology & Electronic engineering 2018年第9期19卷 1112-1123页

作者： Chao-chao BAI Wei-qiang WANG Tong ZHAO Ru-xin WANG Ming-qiang LI School of Computer and Control University of Chinese Academy of Science School of Mathematical Sciences University of Chinese Academy of Science Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Science

With the rapid growth in fingerprint databases, it has become necessary to develop excellent fingerprint indexing to achieve efficiency and accuracy. Fingerprint indexing has been widely studied with real-valued features,but few studies focus on binary feature representation, which is more suitable to identify fingerprints efficiently in large-scale fingerprint databases. In this study, we propose a deep compact binary minutia cylinder code（DCBMCC）as an effective and discriminative feature representation for fingerprint indexing. Specifically, the minutia cylinder code（MCC）, as the state-of-the-art fingerprint representation, is analyzed and its shortcomings are ***, we propose a novel fingerprint indexing method based on deep neural networks to learn *** novel network restricts the penultimate layer to directly output binary codes. Moreover, we incorporate independence, balance, quantization-loss-minimum, and similarity-preservation properties in this learning ***, a multi-index hashing（MIH） based fingerprint indexing scheme further speeds up the exact search in the Hamming space by building multiple hash tables on binary code substrings. Furthermore, numerous experiments on public databases show that the proposed approach is an outstanding fingerprint indexing method since it has an extremely small error rate with a very low penetration rate.

关键词： Fingerprint indexing Minutia cylinder code Deep neural network Multi-index hashing

来源：评论

学校读者我要写书评

暂无评论

Culture versus Policy: More Global Collaboration to Effectively Combat COVID-19

引用

The Innovation 2020年第2期1卷 15-16页

作者： Jianping Li Kun Guo Enrique Herrera Viedma Heesoek Lee Jiming Liu Ning Zhong Luiz Flavio Autran Monteiro Gomes Florin Gheorghe Filip Shu-Cherng Fang Mujgan SagirÖzdemir Xiaohui Liu Guoqing Lu Yong Shi School of Economics and Management University of Chinese Academy of SciencesBeijing 100190China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of SciencesBeijing 100190China Research Center on Fictitious Economy&Data Science Chinese Academy of SciencesBeijing 100190China Department of Computer Science and Artificial Intelligence E.T.S.de Ingenieria Informatica y de TelecomunicacionesUniversity of Granada18071 GranadaSpain Department of Information Management Korea Advanced Institute of Science and TechnologySeoul 207-43 Korea Department of Computer Science and HKBU-CSD&NIPD Joint Research Laboratory for Intelligent Disease Surveillance and Control Hong Kong Baptist UniversityHong KongChina Department of Life Science and Informatics Maebashi Institute of TechnologyMaebashi 371-0816Japan Ibmec University Center Av.Presidente Wilson118Office#111020030-020 Rio de JaneiroBrazil The Romanian Academy Bucharest010071Romania Industrial and Systems Engineering Department North Carolina State UniversityRaleighNC 27695USA Department of Industrial Engineering Eskisehir Osmangazi University26480 EskisehirTurkey Department of Computer Science Brunel University LondonLondonUB83PHUK Department of Biology and School of Interdisciplinary Informatics University of Nebraska at OmahaOmahaNE 68182USA College of Information Science and Technology University of Nebraska at OmahaOmahaNE 68182USA

The outbreak of COVID-19 seriously challenges every government with regard to capacity and management of public health systems facing the catastrophic *** and anti-epidemic policy do not necessarily conflict with each *** countries and governments should be more tolerant to each other in seeking cultural and political consensus to overcome this historically tragic pandemic together.

关键词： seeking overcome policy

来源：评论

学校读者我要写书评

暂无评论

Urban tourism competitiveness evaluation system and its application: Comparison and analysis of regression and classification methods

引用

Procedia Computer Science 2019年 162卷 429-437页

作者： Shuze Guo Yao Jiang Wen Long China University of Political Science and Law Fuxue Road #27Beijing 102220 China School of Economics & Management University Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining & Knowledge Management Chinese Academy of Sciences Beijing 100190 P.R. China

Under the background of economic transformation, tourism is one of the most dynamic and promising tertiary industries. How to improve the competitiveness of tourism has become a new idea for industrial upgrading in various regions. This paper builds an evaluation system consisting of five major aspects, based on the data of 75 tourist destinations; then, uses cluster analysis to classify cities, and uses logistic regression, SVM and random forest methods to predict the tourism competitiveness of sample cities and compare the advantages and disadvantages of the two methods - classification and regression. From the results of the empirical test, the results of the classification method are generally better than the results of the regression, and in the classification method, the results of the SVM are better than the results of the random forest. In this case, the SVM model gives full play to its ability to solve the problem of nonlinear classification.

关键词： tourism competitiveness cluster analysis logistics regression SVM random forest

来源：评论

学校读者我要写书评

暂无评论

Dense residual network: Enhancing global dense feature flow for character recognition

arXiv

引用

arXiv 2020年

作者： Zhang, Zhao Tang, Zemin Wang, Yang Zhang, Zheng Zhan, Choujun Zha, Zhengjun Wang, Meng School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei230009 China School of Computer Science and Technology Soochow University Suzhou215006 China Shenzhen China School of Computer South China Normal University Guangzhou510631 China Deparmtment of Computer Science and Technology University of Science and Technology of China Hefei China

Deep Convolutional Neural Networks (CNNs), such as Dense Convolutional Network (DenseNet), have achieved great success for image representation learning by capturing deep hierarchical features. However, most existing network architectures of simply stacking the convolutional layers fail to enable them to fully discover local and global feature information between layers. In this paper, we mainly investigate how to enhance the local and global feature learning abilities of DenseNet by fully exploiting the hierarchical features from all convolutional layers. Technically, we propose an effective convolutional deep model termed Dense Residual Network (DRN) for the task of optical character recognition. To define DRN, we propose a refined residual dense block (r-RDB) to retain the ability of local feature fusion and local residual learning of original RDB, which can reduce the computing efforts of inner layers at the same time. After fully capturing local residual dense features, we utilize the sum operation and several r-RDBs to construct a new block termed global dense block (GDB) by imitating the construction of dense blocks to adaptively learn global dense residual features in a holistic way. Finally, we use two convolutional layers to design a down-sampling block to reduce the global feature size and extract more informative deeper features. Extensive results show that our DRN can deliver enhanced results, compared with other related deep models. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Endurable SSD-Based Read Cache for Improving the Performance of Selective Restore from Deduplication Systems

引用

Journal of Computer Science & Technology 2018年第1期33卷 58-78页

作者： Jian Liu Yun-Peng Chai Xiao Qin Yao-Hong Liu Division of Computer Science and Engineering Louisiana State University Baton Rouge LA 70803 U.S.A. Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education of China Beijing 100872 China School of Information Renmin University of China Beijing 100872 China Shelby Center for Engineering Technology Department of Computer Science and Software Engineering Samuel Ginn College of Engineering Auburn University Auburn AL 368~9-53~7 U.S.A.

Deduplication has been commonly used in both enterprise storage systems and cloud storage. To overcome the performance challenge for the selective restore operations of deduplication systems, solid-state-drive-based （i.e., SSD-based） re^d cache cm, be deployed for speeding up by caching popular restore contents dynamically. Unfortunately, frequent data updates induced by classical cache schemes （e.g., LRU and LFU） significantly shorten SSDs＇ lifetime while slowing down I/O processes in SSDs. To address this problem, we propose a new solution -- LOP-Cache to greatly improve tile write durability of SSDs as well as I/O performance by enlarging the proportion of long-term popular （LOP） data among data written into SSD-based cache. LOP-Cache keeps LOP data in the SSD cache for a long time period to decrease the number of cache replacements. Furthermore, it prevents unpopular or unnecessary data in deduplication containers from being written into the SSD cache. We implemented LOP-Cache in a prototype deduplication system to evaluate its pertbrmance. Our experimental results indicate that LOP-Cache shortens the latency of selective restore by an average of 37.3% at the cost of a small SSD-based cache with only 5.56% capacity of the deduplicated data. Importantly, LOP-Cache improves SSDs＇ lifetime by a factor of 9.77. The evidence shows that LOP-Cache offers a cost-efficient SSD-based read cache solution to boost performance of selective restore for deduplication systems.

关键词： data deduplication solid state drive （SSD） flash cache endurance

来源：评论

学校读者我要写书评

暂无评论

Can stock markets lead the macroeconomic variables? Dynamic analysis based on TOP method

引用

Procedia Computer Science 2019年 162卷 39-45页

作者： Zhenni Jin Yijing Wang Xiao Cui Kun Guo Sino-Danish College University of Chinese Academy of Science Beijing China Research Center on Fictitious Economy & Data Science Chinese Academy of Science Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Science Beijing China School of Economics and Management University of Chinese Academy of Science Beijing China CHINALCO Finance Company Limited Beijing China

Fictitious economy connects with real economy in many aspects. The interaction between stock markets and macro-economy is becoming more and more crucial for different parties in the whole economic society. On the basis of the Thermal Optimal Path (TOP) method, this paper used the quarterly and monthly data of seven pairs of time series to analyse the dynamic lead-lag connections between the macro-economic fluctuation and the stock market change. The results suggest that the data of stock market can be used to predict the macro-economic variables for most time periods. Investors as an important agent in the stock markets, their expectations can be reflected by stock prices. The irrationality of investors can affect the” barometer” function of stock markets.

关键词： Stock market Macro-economy Thermal optimal path Lead-lag analysis

来源：评论

学校读者我要写书评

暂无评论

Investigation on Automatic data Acquisition of Well Logging Curve based on Color Recognition 4

Investigation on Automatic Data Acquisition of Well Logging ...

引用

2019 4th International Conference on Intelligent Computing and Signal Processing, ICSP 2019

作者： Wang, Han Ye, Zhihui Chen, Dong Zhu, Dandan Li, Shouding College of Safety and Ocean Engineering China University of PetroleumBeijing Beijing102249 China State Key Laboratory of Petroleum Resources and Prospecting College of Petroleum Engineering China University of PetroleumBeijing Beijing102249 China Beijing Key Lab of Petroleum Data Mining Department of Computer Science and Technology Beijing102249 China Institute of Geology and Geophysics Chinese Academy of Sciences Key Laboratory of Shale Gas and Geoengineering Institute of Geology and Geophysics Chinese Academy of Sciences Beijing100029 China University of Chinese Academy of Sciences Beijing100083 China Institutions of Earth Science Chinese Academy of Sciences Beijing100029 China

Well logging data are important to evaluate rock and fluid properties underground. Many well logging data, as functions of well depth, are conserved as figures in the literature. Digitizing technics should be applied when utilizing the well logging data. In order to address this problem, a method was proposed to automatically identify and acquire the well logging data from well logging curves. Based on the color recognition, this algorithm is able to extract curve features based on pixels. Comparing to other data digitizing methods, the background grid lines could be easily filtered and removed. The algorithm is verified by digitizing some typical well logging curves. This main contribution of this work is to provide a new and efficient way for data digitizing from well logging curves. © 2019 IOP Publishing Ltd. All rights reserved.

关键词： data acquisition

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：