检索结果-内蒙古大学图书馆

Congress on Image and Signal processing, CISP

作者： Zunliang Wang Xueming Li Min Zhao Key Laboratory of Information Processing and Intelligent Technology Beijing University of Posts and Telecommunications Beijing China

Distributed coding is a new paradigm for compressing correlated distributed sources, based on Slepian-Wolf and Wyner-Ziv theorem. This scheme is appropriate for wireless sensor network and distributed video coding. In this paper, we address the problem of coding two Gaussian correlated non-binary sources with one of which is only available at the decoder using the non-binary low-density parity-check (LDPC) codes. The proposed approach is based on the extension of the channel coding concept of syndrome. The correlation between the sources is modeled as a virtual additive Gaussian backward channel. The use of non-binary LDPC codes in the proposed system makes coding without converting non-binary sources to binary bits feasible, and thus it overcomes the reduction in correlation caused by conversion. Experiments show that the proposed system achieves a good performance over GF(4) and GF(8), which enables us to reasonably conclude that the considered scheme is extremely suitable for distributed coding of correlated non-binary sources.

关键词： Parity check codes Source coding Image coding Channel coding Binary sequences AWGN Wireless sensor networks Video coding Iterative decoding Signal processing

来源：评论

学校读者我要写书评

暂无评论

Model of Network Traffic Based on Network Applications and Network Users

Model of Network Traffic Based on Network Applications and N...

引用

International Symposium on Computer Science and Computational technology, ISCSCT

作者： Peng Liu Fang Liu Zhenming Lei Key Laboratory of Information Processing and Intelligent Technology Beijing University of Posts and Telecommunications Beijing China

There was a close relationship among network traffic, network user and network application in the complex network environment. We use Gini coefficient in economics to describe elephant and mice phenomenon the network traffic. A new model of network traffic which was comprised of network traffic, network user and network application was built on the basis of Gini coefficient. The result of experiment indicated that the model and Gini coefficient was efficacious and useful for future work.

关键词： Telecommunication traffic Traffic control Mice IP networks Fractals Computer science Computer networks Telecommunication computing Computational modeling Application software

来源：评论

学校读者我要写书评

暂无评论

DHT-Based Channel Estimation for MIMO-OFDM Systems

DHT-Based Channel Estimation for MIMO-OFDM Systems

引用

IEEE Conference on Vehicular technology (VTC)

作者： Yibing Gai Hongyan Li Zhiqiang He Kai Niu Weiling Wu Key Laboratory of Information Processing and Intelligent Technology Beijing University of Posts and Telecommunications Beijing China

Discrete Fourier transform (DFT)-based least square (LS) channel estimation with phase shifted pilots (PSP) is a practical method in multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) systems. In this paper, a real number pilot sequence is presented to replace PSP in time-domain LS channel estimation algorithm, which can reduce computation and save memory while keeping the precision. Furthermore, using discrete Hartley transform (DHT) in LS channel estimation algorithm, a simpler estimator is derived. The simulation results demonstrate the effectiveness of the proposed pilot sequence and the DHT-based channel estimation algorithm.

关键词： Channel estimation OFDM Time domain analysis MIMO Transmitting antennas Partial transmit sequences Discrete Fourier transforms Least squares approximation Fading Receiving antennas

来源：评论

学校读者我要写书评

暂无评论

Transfer learning from multiple source domains via consensus regularization

Transfer learning from multiple source domains via consensus...

引用

17th ACM Conference on information and Knowledge Management, CIKM'08

作者： Luo, Ping Zhuang, Fuzhen Xiong, Hui Xiong, Yuhong He, Qing HP Labs China China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Graduate University of Chinese Academy of Sciences China MSIS Department Rutgers University United States

ISBN: (纸本)9781595939913

Recent years have witnessed an increased interest in transfer learning. Despite the vast amount of research performed in this field, there are remaining challenges in applying the knowledge learnt from multiple source domains to a target domain. First, data from multiple source domains can be semantically related, but have different distributions. It is not clear how to exploit the distribution differences among multiple source domains to boost the learning performance in a target domain. Second, many real-world applications demand this transfer learning to be performed in a distributed manner. To meet these challenges, we propose a consensus regularization framework for transfer learning from multiple source domains to a target domain. In this framework, a local classifier is trained by considering both local data available in a source domain and the prediction consensus with the classifiers from other source domains. In addition, the training algorithm can be implemented in a distributed manner, in which all the source-domains are treated as slave nodes and the target domain is used as the master node. To combine the training results from multiple source domains, it only needs share some statistical data rather than the full contents of their labeled data. This can modestly relieve the privacy concerns and avoid the need to upload all data to a central location. Finally, our experimental results show the effectiveness of our consensus regularization learning. Copyright 2008 ACM.

关键词： Classification Consensus regularization Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Lifting-Based Directionlet Transform for Image Coding

Lifting-Based Directionlet Transform for Image Coding

引用

9th International Conference on Signal processing(第九届国际信号处理学术会议)(ICSP'08)

作者： Jing Bai Jiaji Wu Shan Lu Licheng Jiao Key laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information ProcessingXidian UniversityXi' an 710071P.R.China

In this paper,a new lifting scheme of directionlet transform(LDT) is presented,the corresponding multidirectional and anisotropic transform has latticebased separable filtering and subsampling along any two directions with rational *** design an adaptive compression algorithm based on LDT,using the quad-tree segmentation resulting optimized *** results show that our proposed compression algorithm for image coding outperforms the standard wavelet-based SPIHT and JPEG2000 both in terms of PSNR and visual quality,especially at the low-rate.

关键词： Image coding Wavelet transforms Anisotropic magnetoresistance Compression algorithms Filtering Energy resolution Algorithm design and analysis Image segmentation Transform coding Quantization

来源：评论

学校读者我要写书评

暂无评论

Multivariate classification of deep web sources based on maximum entropy model

引用

Journal of Computational information Systems 2008年第3期4卷 1093-1100页

作者： Huang, Li Zhao, Pengpeng Cui, Zhiming Wei, Fang Institute of Intelligent Information Processing and Application Soochow University Suzhou 215006 China Jiangsu Key Laboratory of Computer Information Processing Technology Soochow University Suzhou 215006 China

With the fast development of World Wide Web, the quantity of web information is increasing in an unprecedented pace, a great many of which are generated dynamically from background databases, and can't be indexed by traditional search engine, so we call them Deep Web. For the heterogeneous and dynamic features of Deep Web sources, classifying the Deep Web source by domain effectively is a significant precondition of Deep Web sources integration. In this paper, we consider the visible features of Deep Web and Maximum Entropy approach, and then on the basis of binary classification, we propose a new multivariate classification approach based on Maximum Entropy towards Deep Web sources. In addition, we propose a Feedback algorithm to improve the accuracy of classification. An experimental evaluation over real Web data shows that, our approach could provide an effective and general solution to the multivariate classification of Deep Web sources.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

A modified decoding algorithm of V-BLAST Architecture

A modified decoding algorithm of V-BLAST Architecture

引用

International Conference on Communications and Networking in China (CHINACOM)

作者： Dongfeng Zhao Daoben Li Key Laboratory of Information Processing and Intelligent Technology Information Engineering School Beijing University of Posts and Telecommunications Beijing China

In this paper, a new algorithm to simplify the Sphere-decoding of V-BLAST architecture is deduced. The system bit error ratio (BER) and complexity are simulated to compare the performance when sphere-decoding algorithm is used with the performance when classical sphere-decoding algorithm is used. According to simulation, the complexity of the modified sphere-decoding algorithm is much lower than the complexity of classical sphere-decoding.

关键词： Maximum likelihood decoding Receiving antennas Random variables Rayleigh channels Laboratories information processing Computer errors Bit error rate MIMO Polynomials

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Travel Itinerary Selection Assistant under Fuzzy User Preferences

An Adaptive Travel Itinerary Selection Assistant under Fuzzy...

引用

2008 Conference on Human System Interactions (HSI 2008), vol.1

作者： Ruihong Shi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

This paper presents a candidate-evaluation model (CEM) which interactively elicits user preferences and assists decision makers in decision making in applications such as travel itinerary planning. The CEM contrasts with traditional decision analytic and planning frameworks in which a complete user model is elicited beforehand or is constructed by a human expert. We used the CEM model to implement an Itinerary Selection Assistant (ISA) system, which helps tourists identify satisfactory travel itineraries. The ISA starts with fuzzy user preferences and gradually approximate the optimal solution through carefully choosing candidate solutions to present to the user and inferring user's actual preferences by analyzing user evaluations over the candidates.

关键词： Augmented weighted Tchebycheff programming Fuzzy user preferences Multi-attribute decision making Travel itinerary User modeling

来源：评论

学校读者我要写书评

暂无评论

COUNT PASSENGERS BASED ON HAAR-LIKE FEATURE IN ELEVATOR APPLICATION

COUNT PASSENGERS BASED ON HAAR-LIKE FEATURE IN ELEVATOR APPL...

引用

2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

作者： HONG LIU YUE-LIANG QIAN QUN LIU JIN-TAO LI Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080

Present elevator control use button sensors to determine when and where to dispatch an elevator car, which don't use the number of passengers. In this paper, we analyze images from camera to detect how many persons waiting for the elevator or in an elevator. A novel framework is proposed for optimized elevator schedule. Extended Haar-like features and Adaboost are used to train a head-shoulder classifier. Some images are selected from video according to elevator button callings to detect head-shoulder. To reduce false alarms a post process is added after detecting. Experimental results show the proposed method with post process has higher performance than existed methods. The information of passenger number can be send to elevator control system for effective schedule, which can reduce passengers waiting time and elevator's unnecessary stop, finally save energy and reduce maintain fee.

关键词： Elevator control system Haar-like features Adaboost Post process

来源：评论

学校读者我要写书评

暂无评论

The Maximum Entropy based Rule Selection Model for Statistical Machine Translation (Invited Paper)

The Maximum Entropy based Rule Selection Model for Statistic...

引用

International Symposium on Universal Communication, ISUC

作者： Qun Liu Zhongjun He Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

This paper presents a novel rule selection model for statistical machine translation (SMT) that uses the maximum entropy approach to predict target-side for an ambiguous source-side. The maximum entropy based rule selection (MERS) model combines rich contextual information as features, thus can help SMT systems perform context-dependent rule selection. We incorporate the MERS model into two kinds of the state-of-the-art syntax-based SMT models: the hierarchical phrase-based model and the tree-to-string alignment template model. Experiments show that our approach achieves significant improvements over both the baseline systems.

关键词： Entropy Surface-mount technology Helium Decoding Predictive models Context modeling Power generation economics Laboratories Machine intelligence information processing

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：