检索结果-内蒙古大学图书馆

MDC-based robust stereo video coding using ICP

Journal of information Hiding and Multimedia Signal processing 2015年第4期6卷 648-654页

作者： Meng, Li Li Zhang, Hua Xiang Department of Information Science and Engineering Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Shandong Normal University No.88 Wenhua East Road Jinan250014 China

In this paper, a robust stereo video coding based on multiple description coding (MDC) scheme is presented. In this scheme, the stereo video is divided into two descriptions, the odd frames of stereo video sequences are one description, and the even frames of stereo video sequences belong to another description. If there is an error of transmission or reconstruction for one description, the stereo video still can be reconstructed by the other description. Moreover, the interpolating compensation preprocessing (ICP) is firstly proposed to improve the coding efficiency. Plenty of experiments demonstrate that the proposed ICP is very effective. © 2015 ISSN.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

A unified semi-supervised framework for author disambiguation in academic social network

A unified semi-supervised framework for author disambiguatio...

引用

25th International Conference on Database and Expert Systems Applications, DEXA 2014

作者： Wang, Peng Zhao, Jianyu Huang, Kai Xu, Baowen School of Computer Science and Engineering Southeast University China State Key Laboratory for Novel Software Technology Nanjing University China State Key Laboratory of Software Engineering Wuhan University China Provincial Key Laboratory for Computer Information Processing Technology Soochow University China

ISBN: (纸本)9783319100845

This paper addresses the author disambiguation problem in academic social network, namely, resolves the phenomenon of synonym problem "multiple names refer to one person" and polysemy problem "one name refers to multiple persons". A unified semi-supervised framework is proposed to deal with both the synonym and polysemy problems. First, the framework uses semi-supervised approach to solve the cold-start problem in author disambiguation. Second, robust training data generating method based on multi-aspect similarity indicator is used and a way based on support vector machine is employed to model different kinds of feature combinations. Third, a self-taught procedure is proposed to solve ambiguity in coauthor information to boost the performances from other models. The proposed framework is verified on a large-scale real-world dataset, and obtains promising results. © 2014 Springer International Publishing Switzerland.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Privacy preserving for network coding in smart grid 15th

Privacy preserving for network coding in smart grid

引用

15th International Conference on Algorithms and Architectures for Parallel processing, ICA3PP 2015

作者： He, Shiming Zeng, Weini Xie, Kun Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer and Communication Engineering Hunan Province Engineering Research Center of Electric Transportation and Smart Distributed Network Changsha University of Science and Technology Changsha410114 China The 716th Research Institute China Shipbuilding Industry Corporation Lianyungang222061 China College of Computer Science and Electronics Engineering Hunan University Changsha410082 China Department of Electrical and Computer Engineering State University of New York at Stony Brook New York United States

ISBN: (纸本)9783319271361

In smart grid, privacy implications to individuals and their family is an important issue, due to the fine-grained usage data collection. Wireless communications are considered by many utility companies to obtain information. Network coding is exploited in smart grids, to enhance network performance in terms of throughput, delay, robustness, and energy consumption. However, Network Coding introduces new challenge for privacy preserving due to the encoding of packet in forwarder nodes. We propose a distributed privacy preserving scheme for network coding in smart grid, which considers the converged flows character of smart grid and exploits a homomorphic encryption function to decrease the complex in forwarder node. The message content of packet is encrypted and the tag of packet is encrypted by homomorphic encryption function. Then the forwarder node linear random codes the encrypted message contents and directly processes the tags cryptotext based on the homomorphism feature. It offers message content confidentiality privacy preserving feature, which can efficiently thwart traffic analysis. Extensive security analysis and performance evaluations demonstrate the validity and efficiency of the proposed scheme. © Springer International Publishing Switzerland 2015.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

A Consistent and Low-Overhead Time Synchronization Method for Wireless Sensor Networks

A Consistent and Low-Overhead Time Synchronization Method fo...

引用

International Conference on Instrumentation, Measurement, computer, Communication and Control (IMCCC)

作者： Xiaoming Wu Yinglong Wang Fuqiang Wang College of Information Science and Engineering Shandong University of Science and Technology Qingdao China Shandong Provincial Key Laboratory of Computer Networks Shandong Computer Science Center (National Supercomputer Center in Jinan) Jinan China

ISBN: (纸本)9781467377249

Wireless Sensor Networks (WSNs) is one of the hot topics in the field of information, which can be used in the special environment to realize the signal acquisition, processing and transmission. As a key technology of WSNs, time synchronization has achieved a wide range of attention and many scholars have come up with lots of methods to solve the problems for different applications. Among these problems the consistency of multi hop error in large scale networks is one of the key difficulties that need to be further considered. In this paper, a mobile node and many fixed nodes form a mobile wireless network. Furthermore the mobile node is used as the time source. In our method the synchronization process does not depend on any special network topology because fixed nodes directly synchronized to the mobile node that traverse the whole network periodically. For the nodes synchronize to the mobile node directly, the time synchronization of nodes in the network keeps in good consistency. Experiments and analysis suggest that our method has greatly improved the stability and consistency of the time synchronization in compare with the traditional hop by hop synchronization method.

关键词： Synchronization computers Wireless sensor networks Instruments Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Towards the Independent Spanning Trees in Conditional BC Networks

Towards the Independent Spanning Trees in Conditional BC Net...

引用

2013 International Conference on Advanced computer Science and Electronics information(ICACSEI 2013)

作者： Baolei Cheng Jianxi Fan Shukui Zhang Yan Wang Xi Wang Wenjun Liu School of Computer Science and Technology Soochow University Provincial Key Laboratory for Computer Information Processing Technology Soochow University

Independent spanning trees (ISTs for short) in networks have applications such as reliable communication protocols, the multi-node broadcasting, one-to-all broadcasting, reliable broadcasting, and secure message distribution. However, it is an open problem whether there are n ISTs rooted at any node in any n connected network with n 5. In this paper, we consider the construction of ISTs in a family of hypercube variants, called conditional BC networks. A recursive algorithm based on two common rules is proposed to construct n ISTs rooted at any node in any n -dimensional conditional BC network n X . We also show that our constructive method is adaptive to not only the existing hypercube variants, but also some other ones.

关键词： Conditional BC network, independent spanning trees, node-disjoint paths, recursive algorithm

来源：评论

学校读者我要写书评

暂无评论

Locally Linear Embedding Algorithm Based on OMP for Incremental Learning

Locally Linear Embedding Algorithm Based on OMP for Incremen...

引用

International Joint Conference on Neural Networks

作者： Yiqin Leng Li Zhang Jiwen Yang School of Computer Science and Technology & Provincial Key Laboratory for Computer Information Processing Technology Soochow University

ISBN: (纸本)9781479914821

Locally Linear Embedding (LLE) is a sort of powerful nonlinear dimensionality reduction algorithms. The basic idea behind the LLE method is that each data point and its neighbors lie on or close to a locally linear patch of the manifold if there is sufficient data. Then the local geometry of these patches is described by using linear coefficients which can reconstruct each data point from its neighbors. However, LLE operates in a batch way and its dimension reduction cannot be generalized to unseen samples. If a test sample arrives, LLE must run repeatedly and the former computational results are discarded. Thus, some incremental methods have been proposed for LLE to solve this problem. In these incremental methods, the neighbor number is globally fixed, which may result in selecting points from another linear space as neighbors. This paper presents LLE based on orthogonal matching pursuit (OMP) and applies it to classification tasks. In the classification tasks, dimensionality reduction on test samples is implemented by applying dimension reduction on training samples. The new LLE method could select a more appropriate neighbors from the selected neighbors. OMP is applied to not only LLE for training samples, but also the incremental learning of LLE for test samples. Compared with other linear incremental methods, experimental results show that the proposed method is promising.

关键词： Joints Conferences Neural networks

来源：评论

学校读者我要写书评

暂无评论

Feature Ensemble Learning based on Sparse Autoencoders for Image Classification

Feature Ensemble Learning based on Sparse Autoencoders for I...

引用

International Joint Conference on Neural Networks

作者： Yaping Lu Li Zhang Bangjun Wang Jiwen Yang School of Computer Science and Technology & Provincial Key Laboratory for Computer Information Processing Technology Soochow University

ISBN: (纸本)9781479914821

Deep networks are well known for their powerful function approximations. To train a deep network efficiently, greedy layer-wise pre-training and fine tuning are required. Typically, pre-training, aiming to initialize a deep network, is implemented via unsupervised feature learning, with multiple feature representations generated. However, in general only the last layer representation is to be employed because of its abstraction and compactness being the best with comparisons to the ones of lower layers. To make full use of the representations of all layers, this paper proposes a feature ensemble learning method based on sparse autoencoders for image classification. Specifically, we train three softmax classifiers by using the representations of different layers, instead of one classifier trained by applying the last layer representation. Of the three softmax classifiers, two are obtained by training stacked auto-encoders with fine tuning, and the other one is obtained by directly using a concatenation of two representations. To improve accuracy and stability of a single softmax classifier, the ensemble of multiple classifiers is considered, and some Naive Bayes combination rules are introduced to integrate the three classifiers. Experimental results on the MNIST and COIL datasets are presented, with comparisons to other classification methods.

关键词： Deep network Feature representation Feature ensemble Autoencoder Softmax Naive Bayes

来源：评论

学校读者我要写书评

暂无评论

Image quality assessment based on region of interest

Image quality assessment based on region of interest

引用

2nd International Conference on Mechatronics and Industrial Informatics, ICMII 2014

作者： Wang, Yue Lin, Zeng Gang Liao, Zi Cheng Shaanxi Provincial Key Laboratory of Speech and Image Information Processing School of Computer Science Northwestern Polytechnical University China

ISBN: (纸本)9783038351764

In this paper a new No-Reference (NR) image quality assessment (IQA) method based on the point wise statistics of local normalized luminance signals using region of interest (ROI) processing is proposed. This algorithm firstly extracts the ROI which is relative to human subjectivity by using the image gradient and phase congruency, and then extracts the image quality feature in spatial domain. Particularly, most of the present IQA methods mainly focus on predicting the image quality with respect to human perception, yet, in some other image domains, the final receiver of a digital image may not a human. Thus, we propose a method which can assess the image quality relative to edge detection algorithm. In addition, experimental results on LIVE database are provided to justify the superior compared to the significant image quality metrics. © (2014) Trans Tech Publications, Switzerland.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Solving Unbalanced Problems in Similarity Learning using SVM Ensemble

Solving Unbalanced Problems in Similarity Learning using SVM...

引用

International Joint Conference on Neural Networks

作者： Peipei Xia Li Zhang School of Computer Science and Technology & Provincial Key Laboratory for Computer Information Processing Technology Soochow University

ISBN: (纸本)9781479914821

Similarity learning is one of the most fundamental notions in machine learning and pattern recognition. In real-world problems, the number of the paired-samples in similarity set is far less than the ones in dissimilarity set. In other word, there is an unbalanced problem in the paired-samples of similarity learning. This paper presents a scheme of SVM ensemble to solve it. In our scheme, we randomly select some of samples to construct paired-samples, not producing all the paired-samples, and introduces multiple classifiers to obtain higher stability and reliability. As a result, the SVM ensemble can effectively decrease the number of paired-samples in similarity learning and solve the unbalanced data learning to some degree. In the experiments, the SVM ensemble is compared with some classic unbalanced learning algorithms. The results on classification tasks show that the SVM ensemble gains better performance.

关键词： Training Support vector machines Sampling methods Databases Accuracy Iris Educational institutions

来源：评论

学校读者我要写书评

暂无评论

A model based on crossed cubes for VoD services

A model based on crossed cubes for VoD services

引用

International Conference on Systems and Informatics (ICSAI)

作者： Haifei Shen Jianxi Fan Baolei Cheng Cheng-Kuan Lin School of Computer Science and Technology Soochow University Suzhou China Provincial Key Laboratory for Computer Information Processing Technology Soochow University China

ISBN: (纸本)9781479954599

Content distribution schemes for Video on Demand (VoD) systems, based on the peer-to-peer (P2P) technology, have attracted more and more attention. Recently, people mainly focus on the latency performance, security, interaction, scalability, and so on. We propose a new network topology model - Similarity Crossed Cube(S-CQ for short), which combines with the feature of crossed cube and establishes multiple independent spanning trees for data distribution in the layer. This network model processes the properties such as good self-organization, delay, etc. The simulation results also show that it can effectively reduce the playback delay and maintain a low delay. The S-CQ network model can provide good quality of VoD service and effectively improve the user experience.

关键词： Routing Delays Bandwidth Streaming media Network topology Peer-to-peer computing Servers

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：