检索结果-内蒙古大学图书馆

Chinese Conference on Pattern Recognition (CCPR)

作者： Linlin Shen Zhen Ji Yuwen Li Li Bai Shenzhen Key Laboratory of Embedded System Design School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Information Technology Shenzhen China School of Computer Science University of Nottingham UK

Although biometrics technology has progressed substantially, its performance is still to be improved for real applications. This paper aims to improve the accuracy of personal identification, when only single sample is registered as template, by integrating multiple hand-based biometrics. To make fusion much easier, the same feature, so called fusion code, and decision level fusion strategy are used. Two fusion cases, face & palmprint and FKP & palmprint were taken as examples to verify the effectiveness. Experimental results show that much better performance than single modal biometrics has been achieved.

关键词： Face Biometrics Feature extraction Databases Testing Biomedical imaging Accuracy

来源：评论

学校读者我要写书评

暂无评论

3D topological reconstruction based on Hough transform and growing neural gas for informationally structured space

3D topological reconstruction based on Hough transform and g...

引用

2010 IEEE/RSJ International Conference on Intelligent Robots and systems

作者： Naoyuki Kubota Tsubasa Narita Beom Hee Lee Department of System Design Tokyo Metropolitan University Hino Tokyo Japan Japan School of Electrical Engineering and Computer Science Seoul National University of Technology Seoul South Korea

This paper proposes a method of 3D topological reconstruction for informationally structured space including sensor networks and robot partners for co-existing with people. The informationally structured space realizes the quick update and access of valuable and useful information for both people and robots on real and virtual environments. In this paper, we use distance information and color information measured by 3D distance image sensor and CMOS camera for 3D topological reconstruction. First, we propose an extraction method of objects from the background image based on Hough transform as preprocessing. Next, we propose a method of 3D topological reconstruction based on growing neural gas to construct informationally structured space. Finally, we show experimental results of the proposed method and discuss the effectiveness of the proposed method.

关键词： Three dimensional displays Robot sensing systems Transforms Cameras Image color analysis Mobile robots

来源：评论

学校读者我要写书评

暂无评论

A Sensor Network Configuration Considering Priori Estimation Error and Communication Energy

引用

IFAC Proceedings Volumes 2010年第8期43卷 341-346页

作者： Takashi Takeda Toru Namerikawa Division of Electrical Engineering and Computer Science Graduate School of Natural Science and Technology Kanazawa University Kakuma-machi Kanazawa 920-1192 JAPAN Department of System Design Engineering Keio University 3-14-1 Hiyoshi Kohoku-ku Yokohama 223-8522 JAPAN

This paper deals with a network configuration considering priori estimation error variance and communication energy in sensor networked feedback system. Each sensor transmits information to a fusion center via multi-hop communication network. We propose a novel network configuration algorithm that each sensor node transmits information with a same dimension. The transmitted information is merged in each sensor node and consists of measurement data with time delay. Then the priori estimate can be minimum variance estimation. The proposed algorithm achieves sub-***optimal network topology with minimum energy and a desired variance. Experimental results show an effectiveness of the proposed method.

关键词： sensor network communication energy data fusion priori estimation error variance multi-hop communication

来源：评论

学校读者我要写书评

暂无评论

Extended information ratio proposal for portfolio optimization based on market dynamics

Extended information ratio proposal for portfolio optimizati...

引用

SICE Annual Conference

作者： Yukiko Onto Hisashi Yamamoto Tomokazu Sasaki Toru Kurazumi Yasuhiro Tsujimura Yasushi Kambayashi Hiroshima Daigaku Higashihiroshima Hiroshima JP Graduate School of System Design Tokyo Metropolitan University Tokyo Japan Department of Computer and Information Engineering Nippon Institute of Technology Saitama Japan

It is well known that the information ratio is one of the most famous indices to evaluate the performances of portfolios. However, it is difficult to design a portfolio through the information ratio to keep the performance in its future period. In order to keep the portfolio's performance that does not depend on the market dynamics in the future period, we propose the extended information ratios for the portfolio design that uses the beta and the beta prime in this paper. We apply a simulated annealing (SA) to optimize the portfolios employing the extended information ratios and then evaluate the efficiency of the portfolios. In the numerical experiments, we show that our portfolios keep the good performances when the trend of the market of the future period becomes different from that of the past period. Even though the portfolios employing the information ratio as an evaluation value display good performances, they have some computational flaws. We found that the evaluation values do not converge for some data periods. We discuss this problem in this paper as well.

关键词： Portfolios Indexes Benchmark testing Optimization Gallium Investments Stock markets

来源：评论

学校读者我要写书评

暂无评论

Bilateral teleoperation of multiple cooperative robots with time-varying delay

Bilateral teleoperation of multiple cooperative robots with ...

引用

IEEE Conference on Control Technology and Applications (CCTA)

作者： Duc Do Nam Yusuke Yamashina Toru Namerikawa Kanazawa Daigaku Kanazawa Ishikawa JP Division of Electrical Engineering and Computer Science Kanazawa University Kakuma-machi Kanazawa-City JAPAN Department of System Design Engineering Keio University Kohoku-ku Yokohama JAPAN

This paper deals with a passive-decomposition based control of bilateral teleoperation between a single master robot and multiple cooperative slave robots under time varying delay in the communication line. At first, we decompose the dynamics of multiple slave robots into two decoupled dynamics: the Shape-system describing dynamics of the cooperative works, and the Locked-system representing overall behavior of the multiple slave robots. Second, we propose a PD control method for bilateral teleoperation to guarantee the asymptotical stability of the system for time varying delay. Finally, experimental results show the effectiveness of our proposed teleoperation.

关键词： Delay Grasping Force Robot kinematics Equations Dynamics

来源：评论

学校读者我要写书评

暂无评论

Face recognition using gabor wavelet and self-adaptive intelligent single particle optimizer

Face recognition using gabor wavelet and self-adaptive intel...

引用

Chinese Conference on Pattern Recognition

作者： Zhou, Jiarui Ji, Zhen Huang, Weigan Tian, Tao College of Biomedical Engineering and Instrument Science Zhejiang University Hangzhou 310027 China College of Computer Science and Software Engineering Shenzhen University Shenzhen 518060 China Shenzhen Key Laboratory of Embedded System Design Shenzhen 518060 China

ISBN: (纸本)9781424472109

A Gabor wavelet based face recognition algorithm of PSOGabor is introduced in this paper. By using particular Gabor filters in feature extraction on important region of face image, PSOGabor can attain more representative feature information with less processing time. To overcome the drawback of overly dependence on the input parameters in intelligent single particle optimizer (ISPO), an improved algorithm of self-adaptive ISPO (AdpISPO) is proposed in this paper. With no critical parameter required, AdpISPO can achieve higher performance than original algorithms. Experimental results demonstrated that, by employing AdpISPO in Gabor filters' selection, PSOGabor can attain higher recognition rate with less computational time. ©2010 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Shooting two birds with two bullets: How to find Minimum Mean OSPA estimates

Shooting two birds with two bullets: How to find Minimum Mea...

引用

International Conference on Information Fusion

作者： Marco Guerriero Lennart Svensson Daniel Svensson Peter Willett Research & Advanced System Design Department Electronica S.p.A. Italy Department of Signals and Systems Chalmers University of Technology Gothenburg Sweden Department of Electrical and Computer Engineering University of Connecticut USA

Most area-defense formulations follow from the assumption that threats must first be identified and then neutralized. This is reasonable, but inherent to it is a process of labeling: threat A must be identified and then threat B, and then action must be taken. This manuscript begins from the assumption that such labeling (A & B) is irrelevant. The problem naturally devolves to one of Random Finite Set (RFS) estimation: we show that by eschewing any concern of target label we relax the estimation procedure, and it is perhaps not surprising that by such a removal of constraint (of labeling) performance (in terms of localization) is enhanced. A suitable measure for the estimation of unla-beled objects is the Mean OSPA (MOSPA). We derive a general algorithm which provided the optimal estimator which minimize the MOSPA. We call such an estimator a Minimum MOSPA (MMOSPA) estimator.

关键词： Birds Target tracking Signal processing algorithms Joints Labeling Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

L1/2 Sparsity Constrained Nonnegative Matrix Factorization for Hyperspectral Unmixing

L1/2 Sparsity Constrained Nonnegative Matrix Factorization f...

引用

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Yuntao Qian Sen Jia Jun Zhou Antonio Robles-Kelly College of Computer Science University of Zhejiang Hangzhou China Shenzhen City Key Laboratory of Embedded System Design College of Computer Science and Software Engineering Shenzhen University Shenzhen China Canberra Research Laboratory NICTA Canberra ACT Australia College of Engineering and Computer Science Australian National University Canberra ACT Australia

Hyperspectral unmixing is a crucial preprocessing step for material classification and recognition. In the last decade, nonnegative matrix factorization (NMF) and its extensions have been intensively studied to unmix hyperspectral imagery and recover the material end-members. As an important constraint, sparsity has been modeled making use of L 1 or L 2 regularizers. However, the full additivity constraint of material abundances is often overlooked, hence, limiting the practical efficacy of these methods. In this paper, we extend the NMF algorithm by incorporating the L 1/2 sparsity constraint. The L 1/2 -NMF provides more sparse and accurate results than the other regularizers by considering the end-member additivity constraint explicitly in the optimisation process. Experiments on the synthetic and real hyperspectral data validate the proposed algorithm.

关键词： Hyperspectral imaging Pixel Signal to noise ratio Equations Cost function Materials

来源：评论

学校读者我要写书评

暂无评论

Extended information ratio proposal for portfolio optimization based on market dynamics

Extended information ratio proposal for portfolio optimizati...

引用

作者： Orito, Yukiko Yamamoto, Hisashi Sasaki, Tomokazu Kurazumi, Toru Tsujimura, Yasuhiro Kambayashi, Yasushi Hiroshima University 1-2-1 Kagamiyama Higashi-Hiroshima Hiroshima 739-8525 Japan Graduate School of System Design Tokyo Metropolitan University 6-6 Asahigaoka Hino Tokyo 191-0065 Japan Department of Computer and Information Engineering Nippon Institute of Technology 4-1 Gakuendai Miyashiro-cho Saitama 345-8501 Japan

ISBN: (纸本)9784907764364

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

A Generalized File Replication Scheme with Diffusion-Based Storage Load Balancing Function in Unstructured P2P File-Sharing Networks

A Generalized File Replication Scheme with Diffusion-Based S...

引用

International Conference on Intelligent Networking and Collaborative systems (INCOS)

作者： Masanori Takaoka Masato Uchida Yuji Oie Graduate School of Computer Science and System Engineering Kyushu Institute of Technology Fukuoka Japan Network Design Research Center Kyushu Institute of Technology Tokyo Japan NCOS Laboratory NEC Communication Systems Kanagawa Japan

In this paper, we provide a generalized file replication scheme with a storage load balancing function in unstructured P2P file-sharing networks. The generalized file replication scheme is expressed as a weighted mixture of the concepts introduced in existing schemes. A mathematical analysis shows that the system behavior realized by the generalized file replication scheme can be described by a thermal diffusion equation composed of heat, reaction and diffusion terms, the weights of which are controlled by a parameter of the mixing rate. Here, the heat term represents a function to enhance file search performance by making replicas on specific peers. The reaction term represents a function to avoid concentrations of storage loads on specific peers. The diffusion term represents a function to uniform the storage loads among peers. The simulation results show that the generalized file replication scheme enables us to control the trade-off between search and storage load balancing performances extensively and intuitively by controlling the parameter of the mixing rate. In addition, the simulation results show that the generalized file replication scheme can adapt to dynamic P2P file-sharing environments.

关键词： Load management Mathematical model Heating Load modeling Equations Probabilistic logic Time measurement

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：