检索结果-内蒙古大学图书馆

International Conference on Communication systems

作者： Mingchen Zhang Fanggang Wang Xiaojun Yuan Lei Chen Center for Intelligent Networking and Commun National Key Lab. of Sci. and Tech. on Commun University of Electronic Sci. and Tech. of China Chengdu China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China School of Information Science and Technology ShanghaiTech University Shanghai China

ISBN: (纸本)9781538678657;9781538678640

High-speed mobility is a challenging scenario in wireless communications since it involves fast-varying channels, in which orthogonal frequency-division multiplexing (OFDM) could degrade significantly without accurate Doppler compensation. Recently, a modulation called orthogonal time frequency space (OTFS) was proposed for the specific scenario. The advantages are two-fold, i.e., the orthogonality in the time-frequency domain and the clustered sparsity of channel information in the delay-Doppler domain. In this paper, we propose a two-dimensional structured Turbo compressed sensing (CS) algorithm based on our previous work on Turbo CS for fast time-varying channel estimation. Markov random field is applied to model the clustered sparse prior of the channel in the two-dimensional delay-Doppler domain. In contrast to the conventional Turbo CS, a two-dimensional structured minimum mean-square error (MMSE) estimator is designed by message passing over a Markov random field. The convergence and the MSE performance of the proposed algorithm is evaluated, and the simulation results validate that the proposed algorithm outperforms the existing algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SAR: Semantic analysis for recommendation

arXiv

引用

arXiv 2017年

作者： Xiao, Han Meng, Lian State Key Lab. of Intelligent Technology and Systems National Lab. for Information Science and Technology Dept. of Computer Science and Technology Tsinghua University Beijing100084 China

Recommendation system is a common demand in daily life and matrix completion is a widely adopted technique for this task. However, most matrix completion methods lack semantic interpretation and usually result in weak-semantic recommendations. To this end, this paper proposes a Semantic Analysis approach for Recommendation systems (SAR), which applies a two-level hierarchical generative process that assigns semantic features and categories for user/item. SAR learns the semantic representations of users/items merely from user ratings on items, which offers a novel path to recommendation by semantic matching with the learned semantic representations. Extensive experiments demonstrate SAR outperforms other state-of-the-art baselines substantially. Copyright © 2017, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Motor Imagery EEG Classification using Wavelet Common Spatial Boosting Pattern

Motor Imagery EEG Classification using Wavelet Common Spatia...

引用

2017 5th International Conference on Advanced Computer Science Applications and Technologies(ACSAT 2017)

作者： Shaobo Liu Fuchun Sun Wenchang Zhang Chuanqi Tan Department of Computer Science and Technology Tsinghua UniversityState Key Lab. of Intelligent Technology and SystemsTsinghua National Laboratory for Information Science and Technology (TNList)

Feature Extraction is one of the most important steps in brain-computer interface(BCI) systems. In particular, the common spatial patterns(CSP) is one of the most successful solutions which has been widely used in MI-BCIs. However, studies have reported that the performance of CSP heavily depends on its channels configuration. To the best of our current knowledge, it is not availab.e to obtain the active channels related to brain activities of stroke patients in advance. Hence, we usually set a relatively broad channels or try to select a subject-specific channels when applying CSP to stroke patients. In this paper, we present a novel approach which employs wavelet transform and boosting algorithm to improve accuracy and robustness of the conventional CSP. In our proposed approach, the channel configurations are initially divided into multiple preconditions. Then, the informative features of the predefined channels are obtained using the Wavelet Common Spatial Pattern(W-CSP) algorithm that provided high-temporal-spectral resolution. Eventually, we train weak classifiers on the obtained features and combine these weak classifiers to a weighted combinational model using boosting strategy. Extensive experiments have been performed on datasets from the famous BCI competition III and IV. The results demonstrate its superior performance.

关键词： Common Spatial Pattern Wavelet Transform Brain-Computer Interface(BCI)

来源：评论

学校读者我要写书评

暂无评论

Nanodevices: Record‐Low‐Threshold Lasers Based on Atomically Smooth Triangular Nanoplatelet Perovskite (Adv. Funct. Mater. 2/2019)

引用

Advanced Functional Materials 2019年第2期29卷

作者： Guohui Li Tao Che Xingqi Ji Shaoding Liu Yuying Hao Yanxia Cui Shengzhong Liu Key Lab of Advanced Transducers and Intelligent Control System of Ministry of Education College of Physics and Optoelectronics Key Laboratory of Interface Science and Engineering in Advanced Materials Taiyuan University of Technology Taiyuan 030024 P. R. China State Key Laboratory of Quantum Optics and Quantum Optics Devices Shanxi University Taiyuan 030006 P. R. China Key Laboratory of Applied Surface and Colloid Chemistry National Ministry of Education Shaanxi Engineering Lab for Advanced Energy Technology School of Materials Science and Engineering Shaanxi Normal University Xi'an 710119 P. R. China

来源：评论

学校读者我要写书评

暂无评论

From one point to a manifold: Knowledge graph embedding for precise link prediction 25

From one point to a manifold: Knowledge graph embedding for ...

引用

25th International Joint Conference on Artificial Intelligence, IJCAI 2016

作者： Xiao, Han Huang, Minlie Zhu, Xiaoyan State Key Lab. of Intelligent Technology and Systems National Lab. for Information Science and Technology Dept. of Computer Science and Technology Tsinghua University Beijing100084 China

Knowledge graph embedding aims at offering a numerical knowledge representation paradigm by transforming the entities and relations into continuous vector space. However, existing methods could not characterize the knowledge graph in a fine degree to make a precise link prediction. There are two reasons for this issue: being an ill-posed algebraic system and adopting an overstrict geometric form. As precise link prediction is critical for knowledge graph embedding, we propose a manifold-based embedding principle (ManifoldE) which could be treated as a well-posed algebraic system that expands point-wise modeling in current models to manifold-wise modeling. Extensive experiments show that the proposed models achieve substantial improvements against the state-of-theart baselines, particularly for the precise prediction task, and yet maintain high efficiency.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Model-driven deep learning for physical layer communications

arXiv

引用

arXiv 2018年

作者： He, Hengtao Jin, Shi Wen, Chao-Kai Gao, Feifei Li, Geoffrey Ye Xu, Zongben National Mobile Communications Research Laboratory Southeast University Nanjing210096 China Institute of Communications Engineering National Sun Yat-sen University Kaohsiung804 Taiwan State Key Lab of Intelligent Technologies and Systems Tsinghua University Department of Automation Tsinghua University Beijing China School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30332 United States Institute for Information and System Sciences Xian Jiaotong University Xi'an710049 China

intelligent communication is gradually becoming a mainstream direction. As a major branch of machine learning, deep learning (DL) has been applied in physical layer communications and demonstrated an impressive performance improvement in recent years. However, most of the existing works related to DL focus on data-driven approaches, which consider the communication system as a black box and train it by using a huge volume of data. Training a network requires sufficient computing resources and extensive time, both of which are rarely found in communication devices. By contrast, modeldriven DL approaches combine communication domain knowledge with DL to reduce the demand for computing resources and training time. This article discusses the recent advancements in model-driven DL approaches in physical layer communications, including transmission schemes, receiver design, and channel information recovery. Several open issues for future research are also highlighted. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

GAKE: Graph aware knowledge embedding 26

GAKE: Graph aware knowledge embedding

引用

26th International Conference on Computational Linguistics, COLING 2016

作者： Feng, Jun Huang, Minlie Yang, Yang Zhu, Xiaoyan State Key Lab. on Intelligent Technology and Systems Tsinghua National Lab. for Information Science and Technology Dept. of Computer Science and Technology Tsinghua University China College of Computer Science and Technology Zhejiang University China

ISBN: (纸本)9784879747020

Knowledge embedding, which projects triples in a given knowledge base to d-dimensional vectors, has attracted considerable research efforts recently. Most existing approaches treat the given knowledge base as a set of triplets, each of whose representation is then learned separately. However, as a fact, triples are connected and depend on each other. In this paper, we propose a graph aware knowledge embedding method (GAKE), which formulates knowledge base as a directed graph, and learns representations for any vertices or edges by leveraging the graph's structural information. We introduce three types of graph context for embedding: neighbor context, path context, and edge context, each reflects properties of knowledge from different perspectives. We also design an attention mechanism to learn representative power of different vertices or edges. To validate our method, we conduct several experiments on two tasks. Experimental results suggest that our method outperforms several state-of-art knowledge embedding models. © 1963-2018 ACL.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Experimental Study on Full-Polarization Micro-Doppler of Space Precession Target in Microwave Anechoic Chamber 6

Experimental Study on Full-Polarization Micro-Doppler of Spa...

引用

6th Conference of the Sensor Signal Processing for Defence, SSPD 2016

作者： Jin, Liu Qi-Hua, Wu Xiao-Feng, Ai Shun-Ping, Xiao State Key Lab. of Complex Electromagnetic Environment Effects on Electronics and Information System National University of Defense Technology Changsha Hunan China

ISBN: (纸本)9781509003266

Based on the background of radar target detection and recognition of space precession targets, an experimental study on full-polarization micro-Doppler of those targets is introduced. The wide-band scattering properties of space precession targets are analyzed, and then the theoretical full-polarization micro-Doppler models are proposed. The scenario of the experiment is introduced, and the measured data are analyzed, and then the differences of full-polarization micro-Doppler of different scattering structures can be observed during precession. © 2016 IEEE.

关键词： Polarization

来源：评论

学校读者我要写书评

暂无评论

Thumt: An open source toolkit for neural machine translation

arXiv

引用

arXiv 2017年

作者： Zhang, Jiacheng Ding, Yanzhuo Shen, Shiqi Cheng, Yong Sun, Maosong Luan, Huanbo Liu, Yang State Key Lab. of Intelligent Technol. and Syst. Tsinghua Natl. Lab. for Info. Sci. and Technology Department of Computer Science and Technology Tsinghua University Beijing China Jiangsu Collaborative Innovation Center for Language Competence Jiangsu China Institute for Interdisciplinary Information Sciences Tsinghua University Beijing China

This paper introduces THUMT, an opensource toolkit for neural machine translation (NMT) developed by the Natural Language Processing Group at Tsinghua University. THUMT implements the standard attention-based encoder-decoder framework on top of Theano and supports three training criteria: Maximum likelihood estimation, minimum risk training, and semi-supervised training. It features a visualization tool for displaying the relevance between hidden states in neural networks and contextual words, which helps to analyze the internal workings of NMT. Experiments on Chinese-English datasets show that THUMT using minimum risk training significantly outperforms GroundHog, a state-of-the-art toolkit for NMT. Copyright © 2017, The Authors. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Effects of Electrospun Carbon Nanofibers Interlayers on High Performance Lithium Sulfur Batteries

Effects of Electrospun Carbon Nanofibers Interlayers on High...

引用

2017年锂硫电池前沿学术研讨会

作者： Tianji Gao TrungHieu Le Ying Yang Zhihao Yu Zhenghong Huang Feiyu Kang State Key Lab. of Power System Tsinghua University Department of Chemical and Environmental Engineering China University of Mining and Technology Department of Electrical Engineering Tsinghua University Laboratory of Advanced Materials Department of Materials Science and EngineeringTsinghua University

Two different interlayers were introduced in the lithium-sulfur batteries to improve the cycling stability with sulfur loading as high as 80%of total mass of *** was recommended as a nitrogen-rich(N-rich)amine component to synthesize a modified polyacrylic acid(MPAA).The electrospun MPAA was carbonized into N-rich carbon nanofibers which was used as cathode interlayer,whilst,

关键词： Effects of Electrospun Carbon Nanofibers Interlayers on High Performance Lithium Sulfur Batteries

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：