检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks

作者： Ke Wang Ping Guo Qian Yin A-Li Luo Xin Xin School of Computer Science and Technology Beijing Institute of Technology Image Processing and Pattern Recognition Laboratory Beijing Normal University Key Laboratory of Optical Astronomy National Astronomical Observatories Chinese Academy of Sciences

ISBN: (纸本)9781509006212

Deep learning scheme has received significant attention during these years, particularly as a way of building hierarchical representations from unlabeled data for a variety of signal and information processing tasks. However, deep neural networks suffer from slow learning speed since most used training algorithms are based on variations of the gradient descent algorithms which require iterative optimization and thus are time-consuming. In addition, a series of control parameters need to be specified empirically which lacks of the theoretical guidance, and current learning algorithms for deep networks are not very suitable to incremental learning scenario. To address these issues, we propose a fast learning scheme in this paper. The basic idea of our approach is to pre-train basic units such as auto-encoders of the deep architecture in an analytical way without any iterative optimization procedure. This scheme is also extended to an incremental learning version. The experimental result shows the superiority of our approach over the state-of-the-art gradient descent based algorithms. To demonstrate the impact of our algorithm on complicated real world applications, we give an example of its performance in astronomical spectra pattern recognition.

关键词： astronomical spectra Spectra pattern recognition learning (artificial intelligence) recognition (Psychology) Neural network algorithms control parameter Optimization Procedure descent Fasting Functional training Road

来源：评论

学校读者我要写书评

暂无评论

A comparative study of different feature mapping methods for image annotation

A comparative study of different feature mapping methods for...

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Yiren Wang Hassan Dawood Qian Yin Ping Guo the Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China the Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China Computer Science Department Beijing Normal University Beijing China

Automatic image annotation and tagging is necessary for indexing and searching of images using querying a text. It is widely used in search engines like Google, Yahoo, Baidu, etc. Fast image Tagging (FastTag) algorithm is proposed to accelerate image annotation process, while keeping the precision of automatic image annotation results. Feature mapping is used to map image features vectors onto higher dimensional feature space. Feature mapping methods plays an important role in automatic image annotation. In this paper, we have compared 6 kernels, among which four kernels are used in homogeneous feature mapping and two kernels are used in discriminative tree based feature mapping, to investigate which feature mapping performs better for automatic image annotation. The performance of these methods has been analyzed by conducting intensive experiments on three different datasets as used by FastTag algorithm in their experiments. We have found that the homogeneous feature mapping with χ 2 kernel is more suitable when used in FastTag algorithm in terms of precision, recall, FI score and N+ measures, and with a relatively acceptable performance.

关键词： Phase change materials Search engines Kernel Indexing Histograms

来源：评论

学校读者我要写书评

暂无评论

A new network traffic prediction algorithm based on discrete queue

引用

Journal of Computational Information Systems 2015年第12期11卷 4255-4261页

作者： Zhang, Hong Hu, Jun Shen, Yuncheng Key Laboratory of Pattern Recognition and Intelligent Information Processing Chengdu China College of Information Science and Technology Chengdu University Chengdu China College of Computer Science Sichuan University Chengdu China School of Traffic and Transportation Beijing Jiaotong University Beijing China Faculty of Computer Science Chengdu Normal University Chengdu China College of Information Science and Technology Zhaotong University Zhaotong China

In order to verify the network traffic decline because by node breakdown, this paper proposes a new type of prediction algorithm (Prediction algorithm based on Discrete-Queue for FARIMA model, PDF). At first, the mathematic formula for queuing situation and average queue length in steady state is derived with queuing theory in this algorithm based on discrete time, and the prediction method is established by FARIMA Model. Then, a simulation was conducted to research on the relationships between average queue length and service rate. The result shows that it has good adaptability, and the standard deviation between prediction traffic and original traffic is 10.18. ©, 2015, Binary Information Press. All right reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A multi-dimensional perception of adaptive routing algorithm based OLSR

引用

Journal of Information and Computational science 2015年第8期12卷 3165-3172页

作者： Zhang, Hong Shen, Yuncheng Li, Zhongwen Hu, Jun Key Laboratory of Pattern Recognition and Intelligent Information Processing Chengdu China College of Information Science and Technology Chengdu University Chengdu China College of Computer Science Sichuan University Chengdu China College of Information Science and Technology Zhaotong University Zhaotong China School of Traffic and Transportation Beijing Jiaotong University Beijing China Faculty of Computer Science Chengdu Normal University Chengdu China

Center nodes have a bigger load and burden with lots of routing in an Ad Hoc Network Model. Congestion of the nodes' packets has a great impact on network performance, especially in wireless networks. This paper proposes a multi-dimensional perception of adaptive routing algorithms based on the loading of MAC, in particular its utility. Through calculating the probabilities of packet arrival, distribution and intensity of interference, conicting nodes and adjusting the contracting strength of packets would optimize network performance. Our simulated experiments show that this algorithm improves the success rate of data transmission, reduces the delay of packet transmission and improves network throughputs. Copyright © 2015 Binary Information Press.

关键词： Network performance

来源：评论

学校读者我要写书评

暂无评论

An efficient and scalable learning algorithm for Near-Earth objects detection in astronomy big image data

An efficient and scalable learning algorithm for Near-Earth ...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Ke Wang Ping Guo School of computer Science and Technology Beijing Institute of Technology Beijing P.R. China Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing P.R. China

ISBN: (纸本)9781479938414

In this paper, we investigate the efficiency and scalability of Gaussian mixture model based learning algorithm for the detection of Near-Earth objects in large scale astronomy image data. We propose an effective scheme to reduce the computational complexity of current learning algorithm, this is achieved by adopting the perceptual image hashing method. Our proposed scheme is validated on raw astronomy image data. The experiment results illustrate that both efficiency and scalability are improved significantly in astronomical scenario and other scenario.

关键词： Astronomy Scalability Big data Data mining Gaussian distribution Hamming distance Gaussian mixture model

来源：评论

学校读者我要写书评

暂无评论

Kernel based weighted group sparse representation classifier

Kernel based weighted group sparse representation classifier

引用

15th International Conference on Human-computer Interaction, HCI International 2013

作者： Xu, Bingxin Guo, Ping Chen, C. L. Philip Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China Faculty of Science and Technology University of Macau China

ISBN: (纸本)9783642393419

Sparse representation classification (SRC) is a new framework for classification and has been successfully applied to face recognition. However, SRC can not well classify the data when they are in the overlap feature space. In addition, SRC treats different samples equally and ignores the cooperation among samples belong to the same class. In this paper, a kernel based weighted group sparse classifier (KWGSC) is proposed. Kernel trick is not only used for mapping the original feature space into a high dimensional feature space, but also as a measure to select members of each group. The weight reflects the importance degree of training samples in different group. Substantial experiments on benchmark databases have been conducted to investigate the performance of proposed method in image classification. The experimental results demonstrate that the proposed KWGSC approach has a higher classification accuracy than that of SRC and other modified sparse representation classification. © 2013 Springer-Verlag.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Cattle's fur detection in complex background based on Graph Cuts

Cattle's fur detection in complex background based on Graph ...

引用

International Conference on Advanced computer science and Information System (ICACSIS)

作者： Hisyam Fahmi Ary Noviyanto Aniati Murni Arymurthy Image Processing and Pattern Recognition Laboratory Faculty of Computer Science Universitas Indonesia

Segmentation becomes a difficult task if the objects are not homogeneous and have overlapping characteristics. The Graph Cuts methods combined with Gaussian Mixture Model (GMM) for initialization label has been adopted to detect cattle object in an image with complex background. The RGB colors and Gray Level Co-occurrence Matrix (GLCM) textures are used as the features set. This method can robustly segment the cattle beef image from its background. This segmentation method produces the average of accuracy value up to 90%.

关键词： image segmentation Cows Accuracy image color analysis Equations Mathematical model Gaussian mixture model

来源：评论

学校读者我要写书评

暂无评论

Robust visual tracking based on online learning of joint sparse dictionary

Robust visual tracking based on online learning of joint spa...

引用

6th International Conference on Machine Vision, ICMV 2013

作者： Li, Qiaozhe Qiao, Yu Yang, Jie Bai, Li Key Laboratory of Ministry of Education for System Control and Information Processing Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai China School of Computer Science University of Nottingham Nottingham United Kingdom

ISBN: (纸本)9780819499967

In this paper, we propose a robust visual tracking algorithm based on online learning of a joint sparse dictionary. The joint sparse dictionary consists of positive and negative sub-dictionaries, which model foreground and background objects respectively. An online dictionary learning method is developed to update the joint sparse dictionary by selecting both positive and negative bases from bags of positive and negative image patches/templates during tracking. A linear classifier is trained with sparse coefficients of image patches in the current frame, which are calculated using the joint sparse dictionary. This classifier is then used to locate the target in the next frame. Experimental results show that our tracking method is robust against object variation, occlusion and illumination change. © 2013 SPIE.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Wideband CPW-Fed 5.8GHz RFID Tag Antenna

引用

电子学报(英文版) 2012年第2期21卷 202-208页

作者： LI Huihui MOU Xuanqin JI Zhen YU Hang LI Yan Institute of Image Processing and Pattern Recognition Xi'an Jiaotong University Xi'an 710049 China College of Computer Science and Software Engineering Shenzhen University Shenzhen 518060 China Shenzhen Key Laboratory of Embedded System Design Shenzhen 518060 China

A novel wideband 5.8GHz CPW-fed an- tenna is presented for Radio frequency identification (RFID) tag. Four U-shaped and four L-shaped branches are used as additional resonators to achieve wideband operation. The proposed antenna was analyzed numeri- cally using the Method of moment (MOM) and the Fi- nite element method (FEM). With the antenna size lim- ited to 30 × 30mm2, the ?10dB bandwidth obtained by MOM is 3.235GHz (5.765～9GHz) and the ?9.5dB band- width obtained by FEM is 2.74GHz (5.32～8.06GHz), cor- responding to 55.7% and 47.2% of the center frequency 5.8GHz respectively. Moreover, the simulated results show that the proposed antenna has gain of more than 4.8dBi and the radiation pattern is nearly omnidirectional in the H-plane. The measured ?10dB bandwidth is 2.68GHz (5.63GHz～8.31GHz), 46.2% of the 5.8GHz frequency. Fur- thermore, there are three measured resonant frequencies at 1.34GHz, 3.23GHz and 5.8GHz with lower than ?10dB return loss respectively. The measurement result achieves a wideband RFID tag antenna performance and is in good agreement with the calculated results.

关键词： RFID标签天线尺寸共面波导宽带无线电频率识别有限元分析网络连接数值分析

来源：评论

学校读者我要写书评

暂无评论

Feedback-free and hybrid distributed video coding using neural networks

Feedback-free and hybrid distributed video coding using neur...

引用

2012 11th International Conference on Information science, Signal processing and their Applications, ISSPA 2012

作者： Nickaein, Isaac Rahmati, Mohammad Ghidary, Saeed Shiry Zohrabi, Abtin Image Processing and Pattern Recognition Lab Department of Computer Engineering and IT Amirkabir University of Technology Tehran Iran Abtin Zohrabi Faculty of Computer Science University of New Brunswick Canada

ISBN: (纸本)9781467303828

Distributed Video Coding (DVC) is a new class of video coding techniques with the aim of coding the decentralized video sources. While the Stanford Wyner-Ziv codec is a well-known architecture in DVC literature, one of its main drawbacks is the presence of a feedback channel from the decoder to the encoder. This feedback channel makes the use of the codec impractical in some applications. Since the only application of the feedback channel is in requesting more parity bits from the encoder, it could be omitted if the encoder estimates the required parity bits and sends them at once. In this paper, a new method of bitrate estimation using a neural network trained by a new set of features is proposed. In addition, a Hybrid mode is proposed that reduces computational complexity at the decoder in a conventional Wyner-Ziv codec. © 2012 IEEE.

关键词： image coding

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：