检索结果-内蒙古大学图书馆

ACM SIGKDD Workshop on Mining Data Semantics 2012, MDS'12 - SIGKDD 2012

作者： Zhao, Shu Xu, Xiansheng Hua, Bo Zhang, Yanping School of Computer Science and Technology Anhui University Hefei Anhui Province 230039 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei Anhui Province 230039 China

ISBN: (纸本)9781450315463

In this paper, we present a novel idea to solve maximum flow problem in the directed networks. Given a directed flow network which we call original network here, we propose a method of Contracting Neighbor-node-set Approach (CNA) based on Quotient Space Theory. It selects some nodes from fine-grained original network as equivalence class to form a new node in the new network. The coarse-grained new network is called quotient network. Then we apply classic algorithms on quotient network to solve the maximum flow of original network. The performance in practice of our algorithm is better than that of classic algorithms and the method of simplifying network. Experimental results show that CNA can approximate accurately solve the maximum flow of original network . The correctness of maximum flow is over 95%. At the same time, the node scale reduces to 55.45% of node scale of original network and edge scale reduces to 32.10% of edge scale of original network, averagely. Copyright © 2012 ACM.

关键词： Equivalence classes

来源：评论

学校读者我要写书评

暂无评论

Estimate unlabeled-data-distribution for semi-supervised PU learning

引用

14th Asia Pacific Web Technology Conference, APWeb 2012

作者： Hu, Haoji Sha, Chaofeng Wang, Xiaoling Zhou, Aoying Shanghai Key Laboratory of Trustworthy Computing Software Engineering Institute East China Normal University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

ISBN: (纸本)9783642292521

Traditional supervised classifiers use only labeled data (features/label pairs) as the training set, while the unlabeled data is used as the testing set. In practice, it is often the case that the labeled data is hard to obtain and the unlabeled data contains the instances that belong to the predefined class beyond the labeled data categories. This problem has been widely studied in recent years and the semi-supervised learning is an efficient solution to learn from positive and unlabeled examples(or PU learning). Among all the semi-supervised PU learning methods, it's hard to choose just one approach to fit all unlabeled data distribution. This paper proposes an automatic KL-divergence based semi-supervised learning method by using unlabeled data distribution knowledge. Meanwhile, a new framework is designed to integrate different semi-supervised PU learning algorithms in order to take advantage of the former methods. The experimental results show that (1)data distribution information is very helpful for the semi-supervised PU learning method;(2)the proposed framework can achieve higher precision when compared with the-state-of-the-art method. © 2012 Springer-Verlag Berlin Heidelberg.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

UPML-FDTD parallel computing on GPU

UPML-FDTD parallel computing on GPU

引用

2012 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2012

作者： Ma, Weiwei Sun, Dong Wu, Xianliang Key of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China School of Electrical Engineering and Automation Anhui University Heifei 230039 China

ISBN: (纸本)9781467321839

Finite-Difference Time-Domain method (FDTD) which is known with its simple and flexible is widely used for the calculating of electromagnetic fields. However, it costs a lot of time in simulating the electrical-large object. To sovle the promble, parallel method for UPML-FDTD algorithm was put forward using GPU based-on Compute Unified Device Architecture (CUDA) in this paper. The algorithm is further optimized by using texture memory. Comparing with the calculation with traditional CPU, The result of simulation shows that this algorithm has enough precision and the remarkable increased efficiency was acquired in different sizes of Yee cells. © 2012 IEEE.

关键词： Finite difference time domain method

来源：评论

学校读者我要写书评

暂无评论

Novel Retinex algorithm by interpolation and adaptive noise suppression

引用

Journal of Central South University 2012年第9期19卷 2541-2547页

作者：李武劲古博黄江涛王明辉 College of Computer Science Sichuan University College of Computer and Information Engineering Guangxi Teachers Education University Key Laboratory of Scientific Computing and Intelligent Information Processing of Guangxi Province (Guangxi University)

In order to improve image quality, a novel Retinex algorithm for image enhancement was presented. Different from conventional algorithms, it was based on certain defined points containing the illumination information in the intensity image to estimate the illumination. After locating the points, the whole illumination image was computed by an interpolation technique. When attempting to recover the reflectance image, an adaptive method which can be considered as an optimization problem was employed to suppress noise in dark environments and keep details in other areas. For color images, it was taken in the band of each channel separately. Experimental results demonstrate that the proposed algorithm is superior to the traditional Retinex algorithms in image entropy.

关键词： Retinex algorithm illumination estimation interpolation adaptive noise suppression

来源：评论

学校读者我要写书评

暂无评论

Secure two-party computation of the quadratic function's extreme minimal value

Secure two-party computation of the quadratic function's ext...

引用

2012 9th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2012

作者： Fen, Wu Hong, Zhong Runhua, Shi Hongsheng, Huang School of Computer Science and Technology Anhui University Anhui China Key Laboratory of Intelligent Computing and Signal Processing Anhui University Ministry of Education Anhui China Department of Operation and Maintence in China Mobile Xuancheng China

ISBN: (纸本)9781467300223

Privacy-Preserving Computational Geometry (PPCG) is a special Secure Multi-party Computation, which is a hot research in information security. This paper presented a special PPCG problem of secure two-party computing the quadratic function's extreme minimal value on a secret interval. Based on Paillier's additive homomorphic and secure comparison protocol, a novel protocol for this problem is proposed. Furthermore, its correctness, security and efficiency are analyzed. The analysis results show that the proposed protocol is much more efficient than current protocol, which can be applied in some military and commercial fields. © 2012 IEEE.

关键词： Computational geometry

来源：评论

学校读者我要写书评

暂无评论

Numerical dispersion analysis of symplectic and ADI schemes

Numerical dispersion analysis of symplectic and ADI schemes

引用

2012 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2012

作者： Ren, Xin-Gang Huang, Zhi-Xiang Wu, Xian-Liang Lu, Si-Long Mei, Yi-Cai Du, Hong-Mei Wang, Hui Shen, Jing Key Lab. of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China Department of Physics and Electronic Engineering Hefei Normal University Hefei China

ISBN: (纸本)9781467321839

In this paper, Maxwell's equations are taken as a Hamiltonian system and then written as Hamiltonian canonical equations by using the functional variation method. The symplectic and ADI schemes, which can be extracted by applying two types of approximation to the time evolution operator, are explicit and implicit scheme in computational electromagnetic simulation, respectively. Since Finite-difference time-domain (FDTD) encounter low accuracy and high dispersion, the more accurate simulation methods can be derived by evaluating the curl operator in the spatial direction with kinds of high order approaches including high order staggered difference, compact finite difference and scaling function approximations. The numerical dispersion of the symplectic and ADI schemes combining with the three high order spatial difference approximations have been analyzed. It has been shown that symplectic scheme combining with compact finite difference and ADI scheme combining with scaling function performance better than other methods. Both schemes can be usefully employed for simulating and solving the large scale electromagnetic problems. © 2012 IEEE.

关键词： Maxwell equations

来源：评论

学校读者我要写书评

暂无评论

Speech endpoint detection based on emd and spectral entropy in noisy environments

Speech endpoint detection based on emd and spectral entropy ...

引用

4th International Conference on Mechanical and Electrical Technology, ICMET 2012

作者： Liu, Yanli Zhang, Dexiang Ji, Mingwei The Institute of Mechanical and Electrical Engineering of Anhui University of Architecture Hefei 230601 China Key Lab. of Intelligent Computing and Signal Processing Anhui University Hefei 230039 China

ISBN: (纸本)9783037855102

Accurate endpoint detection is crucial for speech recognition accuracy. A novel approach that finds robust features for endpoint detection based on the empirical mode decomposition (EMD) algorithm and spectral entropy in a noisy environment is proposed. With the EMD, the noise signals can be decomposed into different numbers of sub-signals called intrinsic mode functions (IMFs), which is a zero-mean AM-FM component. Then spectral entropy can be used to extract the desired feature for IMF components. In order to show the effectiveness of the proposed method, we present examples showing that the new measure is more effective than traditional measures. The experiments show that the proposed algorithm can suppress different noise types with different SNR, and the algorithm is robust in the real signal tests. © (2012) Trans Tech Publications, Switzerland.

关键词： Intrinsic mode functions

来源：评论

学校读者我要写书评

暂无评论

Parallel decision tree with application to water quality data analysis 1

引用

9th International Symposium on Neural Networks, ISNN 2012

作者： He, Qing Dong, Zhi Zhuang, Fuzhen Shang, Tianfeng Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Graduate University of Chinese Academy of Sciences China

ISBN: (数字)9783642313622

ISBN: (纸本)9783642313615

Decision tree is a popular classification technique in many applications, such as retail target marketing, fraud detection and design of telecommunication service plans. With the information exploration, the existing classification algorithms are not good enough to tackle large data set. In order to deal with the problem, many researchers try to design efficient parallel classification algorithms. Based on the current and powerful parallel programming framework - MapReduce, we propose a parallel ID3 classification algorithm(PID3 for short). We use water quality data monitoring the Changjiang River which contains 17 branches as experimental data. As the data are time series, we process the data to attribute data before using the decision tree. The experimental results demonstrate that the proposed algorithm can scale well and efficiently process large datasets on commodity hardware. © 2012 Springer-Verlag.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

TINAC: A fast and effective web video topic detection framework

TINAC: A fast and effective web video topic detection framew...

引用

2012 9th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2012

作者： Ao, Xiang Zhuang, Fuzhen He, Qing Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Graduate University of Chinese Academy of Sciences China

ISBN: (纸本)9781467300223

Most of the previous works for web video topic detection(e.g., graph-based co-clustering method) always encounter the problem of real-time topic detection, since they all suffer from the high computation complexity. Therefore, a fast topic detection is needed to meet users' or administrators' requirement in real-world scenarios. Along this line, we propose a fast and effective topic detection framework, in which video streams are first partitioned into buckets using a time-window function, and then an incremental hierarchical clustering algorithm is developed, finally a video-based fusion strategy is used to integrate information from multiple modalities. Furthermore, a series of novel similarity metrics are defined in the framework. The experimental results on three months' YouTube videos demonstrate the effectiveness and efficiency of the proposed method. © 2012 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Theory for semantic relation computing and its application in semantic link network

Theory for semantic relation computing and its application i...

引用

2012 8th International Conference on Semantics, Knowledge and Grids, SKG 2012

作者： Sun, Yunchuan Lu, Cheng Yan, Hongli Bie, Rongfang Beijing Normal University Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9780769547947

Semantic relation among different objects is one of the most important kinds of semantics which plays the primary role for people and intelligent systems in grasping the situation accurately in the context of connected systems. The semantic relations are viewed as the most important elements in most existing information models (such as ER model, RDF and SLN) during the mapping from the physical world into the cyber world, where efficient ways of representation for semantic relations are developed. However, all these models deal with the semantic relations in a simple and intuitive way. Few works go deep into the study of semantic relations from a mathematic view. This paper aims at exploring a mathematic theory of the semantic relations between objects including representing methods, normal forms of operations, semantic orthogonal basis of the semantic relations. We also discuss the reasoning mechanism based on the proposed theory. The applications of the developed theory in semantic link network are discussed finally. © 2012 IEEE.

关键词： intelligent systems

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：