检索结果-内蒙古大学图书馆

Bayesian multi-hypothesis Wyner-Ziv video coding

Journal of information Hiding and Multimedia Signal processing 2017年第2期8卷 478-485页

作者： Meng, Li Li Zong, Jing Xiu Sun, Gui Na Cheng, Jie Zhang, Jia Zhao, Meng Chen 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

The performance of distributed video coding (DVC) relies heavily on the quality of the side information (SI), and better performance can be expected if multiple SIs are employed. In this paper, we consider the scenario with two SIs, which are obtained by forward and backward predictions respectively. In this case, a couple of ad hoc approaches have been proposed to approximate the conditional probability density function (pdf) of a Wyner-Ziv-coded frame given the two SIs. However, the optimal conditional pdf and the relative performances of these ad hoc approaches with respect to the optimal solution have not been studied. In this paper, using Bayes’ formula, we derive the closed-form expression of the conditional pdf. Experimental results show that the Bayesian solution has similar performance to previous methods. Moreover, simulation results reveal that when better SIs are available, the Bayesian solution could outperform other methods. This analysis sheds some lights on developing future DVC schemes. © 2017 ISSN.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Using Cost-Sensitive Ranking Loss to Improve Distant Supervised Relation Extraction

Using Cost-Sensitive Ranking Loss to Improve Distant Supervi...

引用

第十六届全国计算语言学学术会议暨第五届基于自然标注大数据的自然语言处理国际学术研讨会

作者： Daojian Zeng Junxin Zeng Yuan Dai Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer and Communication EngineeringChangsha University of Science and TechnologyChangsha 410004P.R.China

ISBN: (纸本)9783319690049

Recently,many researchers have concentrated on using neu-ral networks to learn features for Distant Supervised Relation Extraction(DSRE).However,these approaches generally employ a softmax classi-fier with cross-entropy loss,and bring the noise of artificial class NA into classification ***,the class imbalance problem is serious in the automatically labeled data,and results in poor classification rates on minor classes in traditional *** this work,we exploit cost-sensitive ranking loss to improve *** first uses a Piecewise Convolutional Neural Network(PCNN)to embed the semantics of *** the features are fed into a classifier which takes into account both the ranking loss and ***-periments show that our method is effective and performs better than state-of-the-art methods.

关键词： Classifiers Neural network Semantics Noise Balance impairment Taxonomy embedding

来源：评论

学校读者我要写书评

暂无评论

Achieve Personalized Anonymity Through Query Blocks Exchanging

引用

China Communications 2016年第11期13卷 106-118页

作者： Chunguang Ma Lei Zhang Songtao Yang Xiaodong Zheng Pinhui Ke College of Computer Science and Technology Harbin Engineering University Fujian Provincial Key Laboratory of Network Security and Cryptology Fujian Normal University College of Information and Electronic Technology Jiamusi University College of Applied Technology Qiqihar University

In cyberspace security,the privacy in location-based services(LBSs) becomes more critical. In previous solutions,a trusted third party(TTP) was usually employed to provide disturbance or obfuscation,but it may become the single point of failure or service bottleneck. In order to cope with this drawback,we focus on another important class,establishing anonymous group through short-range communication to achieve k-anonymity with collaborative users. Along with the analysis of existing algorithms,we found users in the group must share the same maximum anonymity degree,and they could not ease the process of preservation in a lower one. To cope with this problem,we proposed a random-QBE algorithm to put up with personalized anonymity in user collaboration algorithms,and this algorithm could preserve both query privacy and location privacy. Then we studied the attacks from passive and active adversaries and used entropy to measure user's privacy level. Finally,experimental evaluations further verify its effectiveness and efficiency.

关键词： cyberspace security location-based services collaborative users personalized anonymity query and location privacy

来源：评论

学校读者我要写书评

暂无评论

Survey of key technologies on millimeter-wave CMOS integrated circuits

引用

IOP Conference Series: Materials Science and Engineering 2018年第1期351卷

作者： Fei Yu Lei Gao Lixiang Li Shuo Cai Wei Wang Chunhua Wang Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation & School of Computer and Communication Engineering Changsha University of Science and Technology Changsha 410114 China College of Information Science and Engineering Hunan University Changsha 410082 China

In order to provide guidance for the development of high performance millimeter-wave complementary metal oxide semiconductor (MMW-CMOS) integrated circuits (IC), this paper provides a survey of key technologies on MMW-CMOS IC. Technical background of MMW wireless communications is described. Then the recent development of the critical technologies of the MMW-CMOS IC are introduced in detail and compared. A summarization is given, and the development prospects on MMW-CMOS IC are also discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

From social to individuals: A parsimonious path of multi-level models for crowdsourced preference aggregation

arXiv

引用

arXiv 2018年

作者： Xu, Qianqian Xiong, Jiechao Cao, Xiaochun Huang, Qingming Yao, Yuan Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing1000190 China Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Tencent AI Lab Shenzhen518057 BICMR-LMAM-LMEQF-LMP School of Mathematical Sciences Peking University Beijing100871 China University of Chinese Academy of Sciences Institute of Computing Technology of Chinese Academy of Sciences Beijing100190 China Department of Mathematics and by courtesy Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Hong Kong

In crowdsourced preference aggregation, it is often assumed that all the annotators are subject to a common preference or social utility function which generates their comparison behaviors in experiments. However, in reality annotators are subject to variations due to multi-criteria, abnormal, or a mixture of such behaviors. In this paper, we propose a parsimonious mixed-effects model, which takes into account both the fixed effect that the majority of annotators follows a common linear utility model, and the random effect that some annotators might deviate from the common significantly and exhibit strongly personalized preferences. The key algorithm in this paper establishes a dynamic path from the social utility to individual variations, with different levels of sparsity on personalization. The algorithm is based on the Linearized Bregman Iterations, which leads to easy parallel implementations to meet the need of large-scale data analysis. In this unified framework, three kinds of random utility models are presented, including the basic linear model with L2 loss, Bradley-Terry model, and Thurstone-Mosteller model. The validity of these multi-level models are supported by experiments with both simulated and real-world datasets, which shows that the parsimonious multi-level models exhibit improvements in both interpretability and predictive precision compared with traditional HodgeRank. Copyright © 2018, The Authors. All rights reserved.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

A novel image segmentation method based on an improved bacterial foraging optimization algorithm

引用

Journal of information Hiding and Multimedia Signal processing 2017年第2期8卷 348-357页

作者： Zeng, Zhi Gao Guan, Liang Hua Zhu, Yan Hui Liu, Qiang He, Jin Rong College of Computer and Communication Hunan University of Technology ZhuzhouHunan412000 China Intelligent Information Perception and Processing Technology Hunan Province Key Laboratory China College of Information Engineering Northwest A and F University YanglingShaanxi Province712100 China

When some bionic optimization algorithms are used for image segmentation, we find that the search speeds of these algorithms are slow and the local searching abilities of these algorithms need be improved. In order to solve these problems, this paper proposed a new image segmentation method based on the improved bacterial foraging optimization algorithm. Firstly, a dynamic step size is used to instead of the fixed step size of the chemotaxis operator, and a dynamic probability is used to instead of the fixed probability of elimination-dispersal operator. Then, the gray histograms of the images are extracted for the image segmentation. Ultimately, the images are segmented using the improved bacterial foraging optimization algorithm. The image segmentation results show that the accuracy and the speed of the image segmentation based on the improved bacterial foraging optimization algorithm are superior to the ones that based on others traditional bionic optimization algorithms. © 2017 ISSN.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Nuclear norm regularized coding with local position-patch and nonlocal similarity for face hallucination

引用

Digital Signal processing 2017年 64卷 107-120页

作者： Guangwei Gao Jian Yang Zhihui Lai Pu Huang Jielin Jiang Hao Gao Dong Yue Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing 210023 PR China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou 350121 PR China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 PR China College of Computer Science and Software Engineering Shenzhen University Shenzhen 518060 PR China Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing 210094 PR China School of Computer and Software Nanjing University of Information Science and Technology Nanjing 210044 PR China

Learning-based face hallucination methods have received much attention and progress in past few decades. Specially, position-patch based approaches have been proposed to replace the probabilistic graph-based or manifold learning-based ones. As opposed to the existing patch based methods, where the input image patch matrix is converted into vectors before combination coefficients calculation, in this paper, we propose to directly use the image matrix based regression model for combination coefficients computation to preserve the essential structural information of the input patch matrix. For each input low-resolution (LR) patch matrix, its combination coefficients over the training image patch matrices at the same position can be computed. Then the corresponding high-resolution (HR) patch matrix can be obtained with the LR training patches replaced by the corresponding HR ones. The nonlocal self-similarities are finally utilized to further improve the hallucination performance. Various experimental results on standard face databases indicate that our proposed method outperforms some state-of-the-art algorithms in terms of both visual quantity and objective metrics.

关键词： Face hallucination Position-patch Matrix based regression Nuclear norm Nonlocal similarity

来源：评论

学校读者我要写书评

暂无评论

Research on Ship Automatic Modeling and Identification System

Research on Ship Automatic Modeling and Identification Syste...

引用

2017 2nd International Conference on Mechatronics and information technology(ICMIT 2017)

作者： Yao-jie Chen Xin Yuan Shu-lin Du Can Song School of Computer Science and Technology Wuhan University of Science and Technology School of Navigation Wuhan University of Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System

When the ship sails in different water situation, it is necessary to forecast the movement state of the ship according to the real-time ship motion state parameters. The traditional method uses the classical MMG(mathematical model group) three-degree-of-freedom motion mathematical model to predict the modeling. For the existence of less detection parameters, the error is relatively large, the accuracy is not enough and so on. In this paper, a six-degree-of-freedom ship motion model based on sway, surge, heave, roll, pitch and yawing is proposed, combined with the least square method to achieve the automatic identification modeling method. Using this method, according to the GPS inertial navigation and positioning module to collect the data to simulate, and contrast with the traditional modeling method. The experimental results show that the improved automatic identification modeling method has better effect than the traditional modeling method, which greatly improves the accuracy of ship motion prediction.

关键词： automatic identification six degrees of freedom least square method

来源：评论

学校读者我要写书评

暂无评论

A novel HEFTS-L algorithm for scheduling large number of DAG tasks

A novel HEFTS-L algorithm for scheduling large number of DAG...

引用

2017 3rd Workshop on Advanced Research and technology in Industry Applications(WARTIA 2017)

作者： Xin Liu Rongbin Xu Yongliang Cheng Pengfei Zhang Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education School of Computer Science and Technology Anhui University Co-Innovation Center for Information Supply & Assurance Technology Anhui University

In recent years, along with the development of technologies for distributed computing such as big data and clouds workflow systems, efficiency of workflow scheduling has become very impotent. Hence sc

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting lung nodule malignancies by combining deep convolutional neural network and handcrafted features

arXiv

引用

arXiv 2018年

作者： Li, Shulong Xu, Panpan Li, Bin Chen, Liyuan Zhou, Zhiguo Hao, Hongxia Duan, Yingying Folkert, Michael Ma, Jianhua Huang, Shiying Jiang, Steve Wang, Jing School of Biomedical Engineering Guangdong Provincial Key Laboratory of Medical Image Processing Southern Medical University Guangzhou510515 China Longgang District People's Hospital Shenzhen518172 China Department of Radiation Oncology University of Texas Southwestern Medical Center DallasTX75235 United States School of Computer Science and Technology Xidian University Xi'an710071 China School of Traditional Chinese Medicine Southern Medical University Guangzhou510515 China

To predict lung nodule malignancy with a high sensitivity and specificity, we propose a fusion algorithm that combines handcrafted features (HF) into the features learned at the output layer of a 3D deep convolutional neural network (CNN). First, we extracted twenty-nine handcrafted features, including nine intensity features, eight geometric features, and twelve texture features based on grey-level co-occurrence matrix (GLCM) averaged from five grey levels, four distances and thirteen directions. We then trained 3D CNNs modified from three 2D CNN architectures (AlexNet, VGG-16 Net and Multi-crop Net) to extract the CNN features learned at the output layer. For each 3D CNN, the CNN features combined with the 29 handcrafted features were used as the input for the support vector machine (SVM) coupled with the sequential forward feature selection (SFS) method to select the optimal feature subset and construct the classifiers. The fusion algorithm takes full advantage of the handcrafted features and the highest level CNN features learned at the output layer. It can overcome the disadvantage of the handcrafted features that may not fully reflect the unique characteristics of a particular lesion by combining the intrinsic CNN features. Meanwhile, it also alleviates the requirement of a large scale annotated dataset for the CNNs based on the complementary of handcrafted features. The patient cohort includes 431 malignant nodules and 795 benign nodules extracted from the LIDC/IDRI database. For each investigated CNN architecture, the proposed fusion algorithm achieved the highest AUC, accuracy, sensitivity, and specificity scores among all competitive classification models. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

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：