检索结果-内蒙古大学图书馆

Cost-sensitive three-way decisions model based on CCA

作者： Zhang, Yanping Zou, Huijin Chen, Xi Wang, Xiangyang Tang, Xuqing Zhao, Shu Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Hefei Anhui Province 230601 China School of Computer Science and Technology Anhui University Hefei Anhui Province 230601 China Anhui Electrical Engineering Professional Technique College Hefei Anhui Province 230051 China Jiangnan University Wuxi China

ISBN: (纸本)9783319086439

The concept of three-way decisions was proposed by Yao and most of three-way decisions models use two thresholds α and β to partition the universe into three parts: the positive region POS(X), the negative region NEG(X) and the boundary region BND(X). But acquirement of a pair of thresholds is a challenge. In this paper, we propose a new method to get the thresholds of three-way decisions model. We introduce loss function into three-way decisions model based on constructive covering algorithm (CCA). A loss function is interpreted as the costs of making classification decisions. More specifically, for reducing losses of classification, we change the radius of the cover according to the loss function, then we compute the thresholds based on the modification. This paper propose an effective method to compute thresholds α and β, which is according to cost-sensitive three-way decisions model based on CCA. © 2014 Springer International Publishing.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Research for delay tolerant network node similarity-based on social network

引用

Journal of Computational Information Systems 2013年第13期9卷 5189-5195页

作者： Wang, Guizhu Yang, Yingying Song, Xin Wang, Jie Li, Weiming Ding, Dawei Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China

Social network is a special kind of network, and the relationship between nodes in social networks are used to evaluate a network of social-related strength. Network area is divided into multiple regions, as the network node has its own properties in the multiple regions, the use of node location, direction of movement, movement speed, active between the nodes to reflect the Multi-region Similarity. The Simulation shows the node of forwarding packet is based on the Multi-region Similarity of nodes, which would greatly improve the forwarding efficiency, and reduce the consumption of network resources at the same time. © 2013 by Binary Information Press.

关键词： Delay tolerant networks

来源：评论

学校读者我要写书评

暂无评论

Core nodes-assisted energy-saving and routing research in delay tolerant networks

引用

Journal of Computational Information Systems 2013年第5期9卷 2057-2065页

作者： Wang, Guizhu Wang, Jie Song, Xin Yang, Yingying Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China

In realistic Delay Tolerant Networks (DTNs), the nodes need to keep probing the environment to discover the neighbors in their transmission range. In this paper we assume that the network has a small amount of energy-sufficient nodes, or core nodes, continuously transmitting beacon messages, thereby enhancing the probability of successful probing and alleviating the regular nodes' energy consumption. We first derive the regular node's probability distribution of link duration when the network has some core nodes, then on this basis, the theoretical energy consumption of the regular nodes. The simulation results show that besides energy saving, the message delivery rate and average delay are all improved when compared with the network that only has regular nodes. Copyright © 2013 Binary Information Press.

关键词： Energy conservation

来源：评论

学校读者我要写书评

暂无评论

A distributed differential transmission scheme based on cyclic delay diversity for two-way wireless cooperative relay networks

引用

Journal of Computational Information Systems 2013年第15期9卷 5995-6001页

作者： Zhang, Hongwei Li, Fengzhen Liu, Jianxun Li, Xiaohui Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China

While neither both source terminals nor relay nodes know any channel state information (CSI) in twoway wireless relay networks, it is difficult for some conventional distributed differential relay models to achieve high spectrum efficiency and good diversity performances. To solve this problem, a threestage distributed differential transmission scheme using space-time-frequency coding method based on cyclic delay diversity (CDD) is proposed in this paper. The differentially encoded data at two source terminals are sent to all relay nodes respectively during the first two stages, and the message matrices are designed by normalized or constant-modulus (CM) modulation symbols. Then cyclic delay manner is used to amplify-and-forward (AF) the received signals at all relays in different time slots during the third stage. Due to the employment of CDD ways, the design of differential transmission is simplified and the detection complexity is reduced. Simulation results verify that the proposed differential scheme can exploit high spatial diversity gains and then implement high reliable transmission. © 2013 Binary Information Press.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Text classification based on feature selection and LDA model

引用

Journal of Computational Information Systems 2013年第6期9卷 2321-2328页

作者： Zheng, Cheng Xiang, Long Liu, Jiaoli Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei 230039 China

The tradition methods about feature selection are based on mathematical statistics and lack of semantic information. LDA(Latent Dirichlet Allocation) model is a three-level hierarchical Bayesian and a kind of unsupervised learning model. With the ability to express the text topic which has been put forward in recent years, it can explore the semantic information which has been hidden in the documents without the help of outer knowledge bases. This paper presents a kind of text classification method based on the feature selection and LDA model, blends the digital representation of tests which have been obtained from the mathematical statistics and LDA model and then classify the texts. This method can combine the external and internal information presented by the texts well. Experiments on Sogou Corgus show the method can improve text classification effectiveness: On micro F1 measures, it approaches an improvement of 9.4% and 2.84% respectively on contrast experiments. Copyright © 2013 Binary Information Press.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Improved hybrid algorithm of indoor wireless localization based on RSSI for wireless sensor networks

引用

Journal of Computational Information Systems 2013年第9期9卷 3707-3714页

作者： Zhu, Jun Gao, Hui Ma, Shuai Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China

Due to the complexity of indoor wireless environment, indoor position is more difficult than other location technologies in wireless sensor network, and how to improve accuracy of location is one of the key research problems. So a new hybrid algorithm based on RSSI (Received signal Strength Indicator) is proposed. In this algorithm, a dynamic real-time method of solving path fading factor is introduced, which improves accuracy of RSSI ranging obviously;then a modified algorithm based on weighted centric algorithm is used, which improves accuracy of location estimation. Simulation results show that the hybrid algorithm has better performance compared with weighted centric algorithm and least square method algorithm. The proposed hybrid algorithm can achieve obviously higher localization accuracy and better error performances. © 2013 by Binary Information Press.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Economic development prediction based on wavelet LSSVM algorithm

引用

Journal of Computational Information Systems 2013年第13期9卷 5197-5204页

作者： Li, Ping Zhang, Yu Wang, Jie Li, Weiming Ding, Dawei Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China

This paper is to predict economic development based on wavelet least squares support vector machine algorithm. The same as support vector machine, least squares support vector machine employs the principle of structure risk minimization, which has better generalization ability compared with SVM. In the study, wavelet kernel function can be used to create the kernel function of least squares support vector machine. In order to testify the effective of wavelet least squares support vector machine for economic development prediction, the comparison of the prediction error among the three prediction methods: wavelet least squares support vector machine, least squares support vector machine and support vector machine is performed. Obviously, the prediction error of wavelet least squares support vector machine for economic development is smaller than other prediction models. Therefore, we can conclude that the prediction ability of wavelet least squares support vector machine for economic development is better than least squares support vector machine and support vector machine. © 2013 by Binary Information Press.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Robust point pattern matching based on spectral context

Robust point pattern matching based on spectral context

引用

作者： Tang, Jun Shao, Ling Zhen, Xiantong Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Huangshan Road Hefei 230039 China College of Electronic and Information Engineering Nanjing University of Information Science and Technology Nanjing 210044 China Department of Electronic and Electrical Engineering University of Sheffield Mappin Street Sheffield S1 3JD United Kingdom

Finding correspondences between two related feature point sets is a basic task in computer vision and pattern recognition. In this paper, we present a novel method for point pattern matching via spectral graph analysis. In particular, we aim to render the spectral matching algorithm more robust for positional jitter and outlier. A local structural descriptor, namely the spectral context, is proposed to describe the attribute domain of point sets, which is fundamentally different from the previous methods. Furthermore, the approximate distance order is defined and employed as the metric for geometric consistency of neighboring points in this work. By combining these two novel ingredients, we formulate feature point set matching as an optimization problem with one-to-one constraints. The correspondences are then obtained by maximizing the given objective function via the technique of probabilistic relaxation. Comparative experiments conducted on both synthetic and real data demonstrate the effectiveness of the proposed method, especially in the presence of positional jitter and outliers. © 2013 Elsevier Ltd. All rights reserved.

关键词： Jitter

来源：评论

学校读者我要写书评

暂无评论

Numerical Simulation of Mixing Behavior in a Planar Asymmetric Split-and-Recombine Micromixer

Numerical Simulation of Mixing Behavior in a Planar Asymmetr...

引用

第九届全国微全分析系统学术会议、第四届全国微纳尺度生物分离分析学术会议、2014国际微流控芯片与微纳尺度生物分离分析学术会议

作者： Bo Rong Chengjun Huang Minquan Li Jun Luo Key laboratory of Microelectronics Devices & Integrated Technology Institute of Microelectronics Chinese Academy of SciencesBeijing100029P. R. China Key Laboratory of Intelligent Computing and Signal Processing Anhui UniversityHefei 230039China Key laboratory of Microelectronics Devices & Integrated Technology Institute of MicroelectronicsChinese Academy of SciencesBeijing100029P.R.China Key Laboratory of Intelligent Computing and Signal ProcessingAnhui UniversityHefei 230039China

来源：评论

学校读者我要写书评

暂无评论

Improving whisper intelligibility in noise environment based on joint time frequency analysis

引用

Information Technology Journal 2013年第6期12卷 1089-1097页

作者： Zhou, Jian Wang, Huabin Fang, Xianyong Tao, Liang Zhao, Li Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Heifei 230601 China Key Laboratory of Underwater Acoustic Signal Processing Ministry of Education Southeast University Nanjing 210096 China

A whisper intelligibility enhancement method was proposed based on the Real-valued Discrete Gabor Transform (RDGT) in the joint time frequency domain where the RDGT can change the density of the spectrum through the over sample rate parameter. An optimal logarithmic spectrum estimator was derived based on RDGT coefficients. Experimental results showed that the proposed method improved the intelligibility of enhanced whisper in an adverse noise environment when using a proper over sample rate value. The largest gains in intelligibility were got when the over sample rate value is set to 16 or 32. The proposed method outperforms other four speech enhancement algorithms in terms of intelligibility improvement. The experimental results also implied that the intelligibility performance of the conventional speech enhancement algorithms might be improved when increasing the density of the time-frequency spectrum properly. © 2013 Asian Network for Scientific Information.

关键词： Frequency domain analysis

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：