检索结果-内蒙古大学图书馆

IEEE International Conference on Image Processing (ICIP 2006)

作者： Wei, Xiaohui Chu, Mei Yi Ahmad, Ishfaq Liang, Yongfang Univ Texas Dept Comp Sci & Engn Arlington TX 76019 USA

ISBN: (纸本)9781424404810

Exploitation of redundancies for superior coding efficiency is one of the major research issues in multi-view video coding (MVC). However, this incurs extra computation, counteracting the benefit gained from coding efficiency. This paper exploits inter-view correlations among video objects and background to lower the prediction complexity while achieving high coding efficiency in MVC. We propose an effective object-based scheme that utilizes video object information obtained from the coded base view. This information assists to predict disparity vectors and motion vectors in enhancement views (EVs) by employing object registration and warping. This leads to high compression and low-complexity coding scheme for EVs. The proposed scheme provides higher coding efficiency when compared to the segmentation-free scheme, while achieving lower computational complexity.

关键词： base view segmentation low computational complexity multi-view video coding object warping

来源：评论

学校读者我要写书评

暂无评论

Dynamic Resource Allocation for Heterogeneous Services in Cognitive Radio Networks with Imperfect Channel Sensing

Dynamic Resource Allocation for Heterogeneous Services in Co...

引用

54th Annual IEEE Global Telecommunications Conference (GLOBECOM)

作者： Xie, Renchao Yu, F. Richard Ji, Hong Beijing Univ Posts & Telecommun Sch Informat & Commun Engn Ottawa ON Canada Carleton Univ Sch Informat Technol Dept Syst & Comp Engn Ottawa ON Canada Beijing Univ Posts & Telecommun Minist Educ Key Lab Univ Wireless Commun Beijing 100876 Peoples R China

ISBN: (纸本)9781424492688

In cognitive radio networks (CRNs), perfect knowledge of a dynamic radio environment is hard to know due to hardware limitation, short sensing time and network connectivity issues in CRNs. In this paper, we study the dynamic resource allocation problem for heterogeneous services in CRNs with imperfect channel sensing. We formulate the optimization problem as a mixed integer programming problem under constraints. Then we solve the optimal joint power and channel allocation problem using discrete stochastic optimization method. The proposed algorithm has low computation complexity and fast convergence to approximate to the optimal solution under imperfect channel sensing. Another advantage of this method is that it can track the changing radio environment to allocate the resources dynamically. Simulation results are presented to demonstrate the effectiveness of the proposed scheme.

关键词： Approximation algorithms Base stations Channel allocation Cognitive radio Heuristic algorithms Resource management Sensors channel allocation channel allocation problem cognitive radio cognitive radio networks computational complexity discrete stochastic optimization method dynamic radio environment dynamic resource allocation heterogeneous services imperfect channel sensing integer programming low computational complexity mixed integer programming problem network connectivity optimal joint power allocation problem optimization problem radio networks resource allocation stochastic programming

来源：评论

学校读者我要写书评

暂无评论

Fast SVM classifier for large-scale classification problems

引用

INFORMATION SCIENCES 2023年第1期642卷

作者： Wang, Huajun Li, Genghui Wang, Zhenkun Changsha Univ Sci & Technol Dept Math & Stat Changsha Peoples R China Southern Univ Sci & Technol Sch Syst Design & Intelligent Mfg Shenzhen Peoples R China Southern Univ Sci & Technol Dept Comp Sci & Engn Shenzhen Peoples R China

Support vector machines (SVM), as one of effective and popular classification tools, have been widely applied in various fields. However, they may incur prohibitive computational costs when solving large-scale classification problems. To address this problem, we construct a new fast SVM with a truncated squared hinge loss (dubbed as L ��-SVM). We begin by developing an optimality theory of the nonconvex and nonsmooth L ��-SVM, which makes it convenient for us to investigate the support vectors and working set of L ��-SVM. Based on this, we propose a new and effective global convergence algorithm to address the L ��-SVM. This method is found to enjoy a tremendously low computational complexity, which makes sufficiently decreasing the demand for extremely large-scale computation possible. Numerical comparisons with eight other solvers show that our proposed algorithm achieves excellent performance on large-scale classification problems with regard to shorter computational times, more desirable accuracy levels, fewer support vectors and more robust to outliers.

关键词： Support vector machine Truncated squared hinge loss Support vectors Optimality theory Global convergence low computational complexity

来源：评论

学校读者我要写书评

暂无评论

Probability-weighted tensor robust PCA with CP decomposition for hyperspectral image restoration

引用

SIGNAL PROCESSING 2023年第1期209卷

作者： Zhang, Aiyi Liu, Fulai Du, Ruiyan Northeastern Univ Sch Comp Sci & Engn Shenyang 110819 Liaoning Peoples R China Northeastern Univ Qinhuangdao Inst Engn Optimizat Smart Antenna Qinhuangdao 066004 Hebei Peoples R China

This paper presents a novel probability-weighted tensor robust principal component analysis (TRPCA) method based on CANDECOMP/PARAFAC decomposition (CPD) for hyperspectral image (HSI) restoration with low computational complexity from the coexistence of dense noise and sparse outliers. In the pro-posed method, via the CPD property, the tensor nuclear norm (TNN) optimization object is replaced as the CPD factor matrix of HSI with lower dimensions without losing low-rank property, so as to the com-putational complexity could be reduced during optimizing TNN in TRPCA model. To demonstrate the dif-ferent effects of noise and outliers on HSI restoration, two weighted sets are defined with probability by the prior knowledge of the occurrence of outliers, which are used to analyze the probability whether the HSI is corrupted by dense noise or outliers. Via the probability theory, information entropy is employed to measure the uncertainty of noise and outlier occurrence in received data, so that to demonstrate their difference impacts on HSI restoration to improve the recovery accuracy. Theoretical analysis and simula-tion results show that the proposed method has lower computational complexity and better restoration performance compared with other related methods. (c) 2023 Elsevier B.V. All rights reserved.

关键词： HSI restoration Robust principal component analysis CP decomposition low computational complexity Probability weighted

来源：评论

学校读者我要写书评

暂无评论

Fast and Epsilon-Optimal Discretized Pursuit Learning Automata

引用

IEEE TRANSACTIONS ON CYBERNETICS 2015年第10期45卷 2089-2099页

作者： Zhang, JunQi Wang, Cheng Zhou, MengChu Tongji Univ Dept Comp Sci & Technol Key Lab Embedded Syst & Serv Comp Minist Educ Shanghai 200092 Peoples R China New Jersey Inst Technol Dept Elect & Comp Engn Newark NJ 07102 USA

Learning automata (LA) are powerful tools for reinforcement learning. A discretized pursuit LA is the most popular one among them. During an iteration its operation consists of three basic phases: 1) selecting the next action;2) finding the optimal estimated action;and 3) updating the state probability. However, when the number of actions is large, the learning becomes extremely slow because there are too many updates to be made at each iteration. The increased updates are mostly from phases 1 and 3. A new fast discretized pursuit LA with assured e-optimality is proposed to perform both phases 1 and 3 with the computational complexity independent of the number of actions. Apart from its low computational complexity, it achieves faster convergence speed than the classical one when operating in stationary environments. This paper can promote the applications of LA toward the large-scale-action oriented area that requires efficient reinforcement learning tools with assured e-optimality, fast convergence speed, and low computational complexity for each iteration.

关键词： Discretized pursuit learning automata (LA) low computational complexity stationary environments

来源：评论

学校读者我要写书评

暂无评论

Fast Sparse Bayesian Learning Method for Scanning Radar Super-Resolution Imaging

引用

IEEE ACCESS 2024年 12卷 166393-166401页

作者： Yu, Ze AVIC Chengdu Aircraft Design & Res Inst Chengdu 610073 Peoples R China

The high azimuth resolution and low computational complexity are significant for scanning radar super-resolution imaging. In this paper, we propose a fast sparse Bayesian learning method with truncated singular value (FSBL-T) to quickly improve the azimuth resolution. Firstly, we truncate the small singular value of the convolution matrix to rewrite the echo signal. Secondly, we introduce the Gaussian-Gamma distribution to model the echo noise and sparse target. Then, the expectation maximization method is utilized to estimate the imaging parameters. To reduce the computational load, we introduce Kailath Variant conversion to reduce the size of the inverse matrix. Finally, the simulations illustrate that the FSBL-T method can effectively enhance the azimuth resolution without reducing the imaging accuracy.

关键词： Radar imaging Azimuth Radar Imaging Bayes methods Sparse matrices Noise Superresolution Convolution computational complexity Scanning radar super-resolution imaging sparse Bayesian learning low computational complexity truncated singular value

来源：评论

学校读者我要写书评

暂无评论

low complexity Channel Estimation in Fast Time-Varying Channels for OFDM Systems

引用

JOURNAL OF INTERNET TECHNOLOGY 2016年第4期17卷 661-669页

作者： Jan, Yih-Haw Nan Kai Univ Technol Dept Digital Living Innovat Caotun 542 Nantou Taiwan

Orthogonal frequency division multiplexing (OFDM) is widely adopted in broadband wireless communication systems. However, its performance suffers from the inter-carrier interference (ICI) induced by fast time-varying channel resulting from high mobile speed. Reliable coherent OFDM systems require an accurate channel estimation. Our aim, in this paper, is to propose the channel estimation that is low computational complexity and robust to the fast time-varying channels. The proposed channel estimation is based on the pilot-assisted polynomial interpolation in a multi-symbol configuration. In this method, the time variations of each channel path corresponding to the successive OFDM symbols, regarding as an observation window, are interpolated by arbitrary polynomial order functions. Simulation results show that the interpolation performing over a window profits low pilot overheads. It also shows the offline mode reduces the computational complexity by as high as 99.9% whereas achieving good performance. This method, with low complexity and low pilot overhead, can provide high performance in the fast time-varying channels.

关键词： Channel estimation OFDM Fast time-varying channel low computational complexity low pilot overhead

来源：评论

学校读者我要写书评

暂无评论

Reduced-Overhead Channel Estimation for OFDM Systems in Multipath Fast Time-Varying Channels

引用

JOURNAL OF INTERNET TECHNOLOGY 2015年第6期16卷 1099-1108页

作者： Jan, Yih-Haw Nan Kai Univ Technol Dept Digital Living Innovat Caotun Township Taiwan

Orthogonal frequency division multiplexing (OFDM) is the core technology in new generation cellular networks, which can compete the last mile broadband wireless access solution. Accurate OFDM channel estimation with low pilot overheads in high mobility communication environments is one of the key issues to be resolved in broadband wireless access. Unfortunately, the Doppler frequency resulted from high mobility will cause inter-carrier interference (ICI) and degrade the performance of the OFDM systems. Due to the severe ICI, channel estimation becomes a difficult task in higher mobility scenarios. This paper proposes a computationally efficient channel estimation method for OFDM systems that is robust to high Doppler frequency with low pilot overheads. In this method, the time durations of each channel path corresponding to the transmitted consecutive OFDM systems, which are considered a 'window', are interpolated using polynomial functions. To improve interpolation accuracy, the training symbol and pilot symbol are allocated at the two ends of the windows, and the data symbols are allocated between the training symbol and the pilot symbol. The proposed two-step method is initialized to the least squares (LS) estimates of the channels corresponding to the time interval of the training symbol and pilot symbol within the window. Then, the channel interpolation is performed in the entire window. Compared with the state-of-the-art method, the computational complexity and pilot overhead of this method can be markedly reduced for each estimate. Simulation results show that the proposed method is robust to high Doppler frequencies and enhances transmission efficiency.

关键词： Broadband wireless access OFDM channel estimation low computational complexity low pilot overhead Polynomial interpolation

来源：评论

学校读者我要写书评

暂无评论

complexity-Reduced Super Resolution for Foveation-Based Driving Head Mounted Displays

引用

IEEE ACCESS 2021年 9卷 140042-140049页

作者： Nam, Hyoungsik Kang, Hangyeol Kyung Hee Univ Dept Informat Display Seoul 02447 South Korea

In this paper, we propose a foveation-based super resolution (SR) algorithm to create high resolution images from low resolution inputs for virtual reality head mounted displays. Because the proposed SR algorithm is integrated in the previous foveation-based driving technology to cover the small area around the foveation point that requires high rendering quality, the overall computational complexity is substantially reduced, compared to the whole area SR. The target display has 4 times as high resolution as the input image, therefore, the proposed SR algorithm generates 4 x as well as 2 x SR images at the same time. To support two SR output images, small area SR, and small number of weights, we employ cropping as well as progressive and recursive framework used in the previous MS-LapSRN. We reduce the number of neurons by placing the deconvolutional layer after convolutional layers, compared to the MS-LapSRN. PSNR and SSIM performances of the proposed SR for the 4 x scale are estimated as 31.152 dB and 0.935 for Set5, 26.656 dB and 0.858 for Set14, 27.138 dB and 0.830 for BSD100, and 25.078 dB and 0.836 for Urban100. For the target 8K display of 7;680 x 4 :320, the proposed FovSR-integrated driving technology achieves the substantial reductions by 76.7 % and 99.02 % on the number of lines from 7,680 to 1,788 and the number of neurons from 24,518,246,400 to 239,541,184, respectively.

关键词： Image resolution Neurons Head Training Rendering (computer graphics) computational complexity Licenses Super resolution low computational complexity virtual reality head mounted display foveation-based driving

来源：评论

学校读者我要写书评

暂无评论

A new fast ADMM for kernelless SVM classifier with truncated fraction loss

引用

KNOWLEDGE-BASED SYSTEMS 2024年 283卷

作者： Wang, Huajun Zhou, Weijun Shao, Yuanhai Changsha Univ Sci & Technol Dept Math & Stat Changsha Peoples R China Hainan Univ Sch Management Haikou Peoples R China

Support vector machine (SVM) is one of well-known supervised machine learning classifier and is used widely in image classification, pattern recognition, disease diagnosis, etc. However, the high computational complexity is a major issue for large-scale classification problems. To address this issue, we propose a new truncated fraction loss function to construct a new sparse and robust SVM model (Ltf-SVM). By newly developed support vectors and a working set based on the proximal operator of truncated fraction loss, we prove the sparsity and robustness to outliers of Ltf-SVM from a theoretical perspective. When it comes to solve Ltf-SVM problems, we develop an alternating direction method of multipliers with a working set for addressing Ltf-SVM. The proposed algorithm is proven to converge globally and enjoys very low computational complexity. Moreover, numerical experiments verify its superior performance with respect to its high accuracy and high computational speed in comparison with other leading solvers.

关键词： Truncated fraction loss Proximal operator Support vectors Working set low computational complexity

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：