检索结果-内蒙古大学图书馆

IEEE Conference on Industrial electronics and Applications (ICIEA)

作者： ChunYang Wang Ying Luo YangQuan Chen Dept. of Electronics and Information Engineering Changchun University of Science and Technology Dept. of Automatic Science and Engineering South China University Dept. of Electrical and Computer Engineering Utah State University

ISBN: (纸本)9781424427994

In this paper, two tuning methods of Fractional Order Proportional Integral (FOPI) controller and Fractional Order [Proportional Integral] (FO[PI]) controller for the typical first-order velocity servo system are discussed. Using the Integer Order Proportional, Integral and Derivative (IOPID) controller, the controller can not be designed to follow the proposed tuning idea to achieve the robustness requirement. However, the FOPI and FO[PI] controllers designed by the proposed tuning methods can improve the performance and robustness of the first order velocity servo system. Furthermore, following the proposed systematic and analytical design schemes, the FO[PI] controller outperforms the FOPI controller. Simulation results are presented to validate the proposed tuning methods.

关键词： Fractional Order Proportional Integral (FOPI) Controller Fractional Order [Proportional Integral](FO[PI]) Controller Integer Order PID (IOPID)Controller First-Order Velocity Servo Plant Robustness Fractional Order Calculus

来源：评论

学校读者我要写书评

暂无评论

Chinese name speech classification using fisher score based on continuous density hidden Markov models

Chinese name speech classification using fisher score based ...

引用

IIH-MSP 2009 - 2009 5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing

作者： Gao, Yi Han, John Lin, Lei Lu, Congde Yang, Qin Electronics Ltd. Chengdu 2nd Branch 611731 China Dept. of Automation Engineering Univ. of Elec. Sci. and Tech. of China Chengdu 610054 China Dept. of Computer Science and Engineering Univ. of Elec. Sci. and Tech. of China Chengdu 610054 China

ISBN: (纸本)9780769537627

Over the last years significant effort has been made to improve the performance of speech recognition. The Fisher Kernel has been suggested as good ways to combine and underlying generative model in the feature space and discriminant classifiers such as SVMs. Chinese name speech patterns are difficult to be classified especially when they are similar in pronunciation. Continuous density hidden Markov model(CHMM) is state-of-the-art method to process this difficulty. A procedure was proposed in this paper to derive the Fisher score from CHMM, and compare it with traditional generative models and Gaussian mixture model(GMM) based Fisher score in Chinese name speech recognition. The result shows that CHMM based Fisher score classified by SVMs receives the best performance. © 2009 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

A novel cooperative communication protocol for qos provisioning in wireless sensor networks

A novel cooperative communication protocol for qos provision...

引用

2009 5th International Conference on Testbeds and Research Infrastructures for the Development of Networks and Communities and Workshops, TridentCom 2009

作者： Liang, Xuedong Chen, Min Yang, Xiao Balasingham, Ilangko Leung, Victor C.M. Dept. of Informatics University of Oslo Oslo N-0316 Norway Interventional Center Rikshospitalet University Hospital Oslo N-0027 Norway Dept. ofElectrical and Computer Engineering University ofBritish Columbia Vancouver V6T lZ4 Canada Dept. of Computer Science University of Alabama Tuscaloosa AL 35487 United States Dept. ofElectronics and Telecommunications Norwegian University ofScience and Technology Trondheim N-7491 Norway

ISBN: (纸本)9781424428472

Cooperative communications have been demonstrated to be effective in combating the multiple fading effects in wireless networks, and improving the network performance in terms of adaptivity, reliability, data throughput and network life time. In this paper, we investigate the use of cooperative communications for quality of service (QoS) provisioning in resource-constrained wireless sensor networks, and propose MRL-CC, a Multi-agent Reinforcement Learning based multi-hop mesh Cooperative Communication mechanism for wireless sensor networks. In order to disseminate data reliably in MRL-CC, a multi-hop mesh cooperative structure is first constructed. Then a cooperative mechanism with cooperative partner assignments, and coding and transmission schemes is implemented using a multi-agent reinforcement learning algorithm. We compare the network performance of MRL-CC with MMCC [1], a Multi-hop Mesh structure based Cooperative Communication scheme, and investigate the impacts of network traffic load, interference and sensor node's mobility on the network performance. Simulation results show that MRL-CC performs well in terms of a number of QoS metrics, and fits well in large-scale networks and highly dynamic environments.

关键词： Cooperative communication

来源：评论

学校读者我要写书评

暂无评论

ROBUST LOW-RESOLUTION FACE IDENTIFICATION AND VERIFICATION USING HIGH-RESOLUTION FEATURES

ROBUST LOW-RESOLUTION FACE IDENTIFICATION AND VERIFICATION U...

引用

International Conference on Image Processing

作者： Pablo H. Hennings-Yeomans B. V. K. Vijaya Kumar Simon Baker Center for Bioimage Informatics and Dept. of Biomedical Engineering Carnegie Mellon University Dept. of Electrical and Computer Engineering Carnegie Mellon University Microsoft Research Microsoft Corporation

ISBN: (纸本)9781424456536;9781424456543

In this work, we elaborate on a rather intuitive hypothesis: face recognition of low-resolution faces can be improved if the processes of reconstruction and recognition are considered simultaneously, instead of sequentially, without feedback or any interaction. Given a high-resolution training set, matching low-resolution probe images with good accuracy is an open problem. We have recently introduced [Hennings-Yeomans, Baker, and Kumar, CVPR, June 2008] a new framework for low-resolution face recognition that uses models from an image formation process, super-resolution priors and face feature extraction methods. By measuring how well an intermediate super-resolution reconstruction of the probe image fits into the models used in the process, the proposed matching algorithm extracts new features for recognition. In this paper, we present results for an improved design of these new features. We show that the proposed algorithm improves performance in both, identification and verification tasks on a large database of 337 subjects that also captures illumination variations.

关键词： Face recognition Super-resolution Feature extraction Biometrics Face models face modeling super-resolution Feature extraction Facial Recognition Biometrics High definition Verification Face Recognition (Psychology) design improvement

来源：评论

学校读者我要写书评

暂无评论

A hierarquical distributed fault diagnosis algorithm based on clusters with detours

A hierarquical distributed fault diagnosis algorithm based o...

引用

6th IEEE/IFIP Latin American Network Operations and Management Symposium, LANOMS 2009

作者： Duarte Jr., Elias P. Albini, Luiz C. P. Brawerman, Alessandro Guedes, André L. P. Federal University of Paraná Dept. Informatics P.O. Box 19018 Curitiba PR 81531-980 Brazil Positivo University Dept. Computer Engineering R. Prof. Pedro V. P. Souza 5300 Curitiba PR 81280-330 Brazil

ISBN: (纸本)9781424445509

A distributed system-level diagnosis algorithm allows the fault-free nodes of a system to diagnose the state of all nodes in the system. Diagnosis has been successfully employed for dependable network fault management. In this paper we present a new hierarchical adaptive distributed system-level diagnosis algorithm, Hi-ADSD with Detours which has latency at most log22N, but requires less tests and less diagnostic information than other hierarchical diagnosis algorithms. Nodes running the new algorithm are grouped in clusters. If a tested node is faulty, instead of executing more tests, the tester tries to obtain information about the rest of the cluster from nodes tested fault-free outside the cluster, such that the diagnosis of the system is not delayed. Each such alternative path to a cluster is called a detour. An extra test is executed on a given cluster only when no detour is available. The worst case of the algorithm's latency is formally proved. Simulation results are presented. © 2009 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Performance improvement of double-layer networks with holographic optical switches

引用

WSEAS Transactions on Communications 2009年第7期8卷 566-577页

作者： Lee, Chi-Ping Chang, Chien-Ping Deng, Jiun-Shiou Lu, Ming-Feng Huang, Yang-Tung Dept. of Electronic Engineering Minghsin University of Science and Technology No. 1 Hsinshing Rd. Hsinfeng Hsinchu 304 Taiwan Dept. of Computer Science and Information Engineering Minghsin University of Science and Technology Department of Electrical Engineering National Defense University Dept. of Electronics Engineering and Institute of Electronics National Chiao-Tung University

In our previous research, combining the unique features of the double-layer network and holographic optical switches not only reduces the volume of the whole system and eliminates all interconnection lines and crossovers significantly, but also reduces the number of drivers from N2/ 4+2Nlog2N-2N to 2Nlog2N. In this paper, modifying the structures of the holographic optical switches to satisfy the characteristics of the double-layer network, the system insertion loss can be minimized significantly from (2log2N-1)(ZPBS+2ZEOHWP) to (2log2N-2)ZPBS+2(log2N)ZEOHWP (dB). After rearranging the channels, the number of electro-optic halfwave plates can be decreased significantly from 2N2-2N to 2Nlog2N.

关键词： Optical switches

来源：评论

学校读者我要写书评

暂无评论

Influence of the wavelet family in the compression-denoising technique on synthetic and natural images

Influence of the wavelet family in the compression-denoising...

引用

2009 16th International Conference on Systems, Signals and Image Processing, IWSSIP 2009

作者： Conci, Aura Kubrusly, Carlos S. Rauber, Thomas W. Computer Science Dept. Univ. Federal Fluminense Niterói RJ Brazil Electrical Engineering Department Catholic University of Rio de Janeiro Rio de Janeiro RJ Brazil Dept. of Informatics Univ. Federal do Espírito Santo Vitória ES Brazil

ISBN: (纸本)9781424445301

A denoising procedure based on a thresholding function has been integrated into the JPEG2000 part II standard which is designed to support a wide variety of applications, including the compression and transmission of medical images. This standard is based on the discrete wavelet transform using the Daubechies(9,7) biorthogonal wavelet, also named the Cohen-Daubechies-Feauveau 9/7 wavelet. However, is this the best choice concerning quality at any time? In this work we compared the results from 36 different variations of wavelets compression schemes to explore their difference related to image content and quality. Two groups of well known images of different levels of complexities and content are used to evaluate the relation among fidelity, image content and noise level. The first group is formed by natural images and the second group is formed by synthetic images. They are considered on two different resolutions (128x128 and 256x256) and with high level of Additive White Gaussian Noise. The performance of each approach is evaluated by means of fidelity, comparing the originals without noise versus the same images after compression/denoising and decompression. The goal is to define which combination present the best and the worst results considering the final visual quality. ©2009 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Autonomously normalized horizontal differentials as features for HMM-based omni font-written OCR systems for cursively scripted languages

Autonomously normalized horizontal differentials as features...

引用

2009 IEEE International Conference on Signal and Image Processing Applications, ICSIPA09

作者： Attia, Mohamed Rashwan, Mohsen A.A. El-Mahallawy, Mohamed S.M. Engineering Company for the Development of Computer Systems RDI Egypt Dept. of Electronics and Electrical Communication Faculty of Eng. Cairo Univ. Egypt Arab Academy for Science and Technology and Maritime Transport AAST-MT Egypt

ISBN: (纸本)9781424455614

Automatic font-written Optical Character Recognition (OCR) is highly desirable for numerous modern information technology (IT) applications. Reliable font-written OCR's for Latin scripts are readily in use since long. For cursively scripted languages, that are the mother tongues of over one fourth of the world population, such OCR's are however not available at a robust and reliable performance. In this regard, the main challenge is the mandatory connectivity of characters/ligatures (i.e. graphemes) that has to be resolved simultaneously upon the recognition of these graphemes. Among the various approaches tried over decades, Hidden Markov Models (HMM)-based OCR's seem to be the most promising as they capitalize on the ability of HMM decoders to achieve segmentation and recognition simultaneously similar to the widely used HMM-based automatic speech recognition (ASR). Unlike ASR's, what is missing in HMM-based OCR's is the definition of a rigorously founded features vector capable to robustly achieving minimal "font type/size-independent" (omnifont) word error rates comparable to those realized with Latin scripts. Here comes the contribution of this paper that introduces such a sound features vector design, and experimentally shows its superiority in this regard.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

A NEW COOPERATIVE TECHNIQUE FOR WIRELESS COMMUNICATIONS WITH IMPROVED DIVERSITY-MULTIPLEXING TRADEOFF

A NEW COOPERATIVE TECHNIQUE FOR WIRELESS COMMUNICATIONS WITH...

引用

European signal processing conference

作者： Christos G. Tsinos Kostas Berberidis Dept. of Computer Engineering & Informatics and RACTI/RU8 University of Patras 26500 Rio-Patras Greece

ISBN: (纸本)9781617388767

In this work we present a new diversity-multiplexing scheme for the uplink transmission of a cooperative system consisting of single-antenna source and relay nodes and a multi-antenna destination node. The proposed technique is based on the singular value decomposition of the channel matrix and, for the same rate, it exhibits higher diversity gain as compared to the existing schemes. Moreover compared with these techniques it is highly reconfigurable and has a lower complexity receiver structure. We evaluate the performance of the new technique via theoretical analysis and simulations.

关键词： CARRIER SYSTEM channel matrix Diversity methods Theoretical analysis new technique multiple antenna

来源：评论

学校读者我要写书评

暂无评论

Experimental study on the effects of communication range on cooperative robotic search in complex environments

Experimental study on the effects of communication range on ...

引用

2009 2nd International Conference on Robot Communication and Coordination, RoboComm 2009

作者： Çaylrpunar, Ömer Gazi, Veysel Tavli, Bulent Cervera, Enric Witkowski, Ulf Penders, Jacques Dept. of Computer Engineering TOBB University of Economics and Technology Sögütözü Cad. No: 43 06560 Ankara Turkey Dept. of Electrical and Electronics Engineering TOBB University of Economics and Technology Sögütözü Cad. No: 43 06560 Ankara Turkey Dept. of Computer Science and Engineering Jaume-I University Campus Riu Sec 12071 Castelló Spain Heinz Nixdorf Institute University of Paderborn Fuerstenallee 1133102 Paderborn Germany Microsystems and Machine Vision Lab Sheffield Hallam University Pond Street Sheffield SI lWB United Kingdom

ISBN: (纸本)9789639799516

Communication has an important role in multirobot systems. It can facilitate cooperation, therefore, improve the performance of the system significantly. In this study we investigated the benefits of networked communication by experimentally evaluating the results of two search algorithms which are spiral search and informed random search. The experiments were performed in an experimental area containing obstacles and using e-puck robots where the communication ranges were "simulated" with the help of an overhead camera. Each robot was allowed to (i) keep an occupancy grid based local map of the environment containing also information about the cells it has visited and (ii) exchange this information with the other robots within its communication range. The effect of the size of communication range on the performance of the system defined as the time of completion of the search task (i.e, locating the target), was investigated.

关键词： Cooperative communication

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：