检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks

作者： Yu-Ting Liu Yang-Yin Lin Shang-Lin Wu Chun-Hsiang Chuang Mukesh Prasad Chin-Teng Lin Institute of Electrical Control Engineering Brain Research Center National Chiao-Tung University Hsinchu Taiwan Department of Computer Science National Chiao-Tung University Hsinchu Taiwan

This study presents a fuzzy prediction system for the forecasting and estimation of driving fatigue, which utilizes a functional-link-based fuzzy neural network (FLFNN) to predict the drowsiness (DS) level in car driving task. The cognitive state in car driving task is one of key issue in cognitive neuroscience because fatigue driving usually causes enormous losses nowadays. The damage can be extremely decreased by the assistant of various artificial systems. Many Electroencephalography (EEG)-based interfaces have been widely developed recently due to its convenient measurement and real-time response. However, the improvement of recognition accuracy is still confined to some specific problems (e.g., individual difference). In order to solve this issue, the proposed methodology in this paper utilizes a nonlinear fuzzy neural network structure to increase the adaptability in the real-world environment. Therefore, this study is further to analysis the brain activities in car driving, which is constructed in a simulated three-dimensional virtual-reality (VR) environment. Finally, through the development of brain cognitive model in car driving task, this system can predict the cognitive state effectively before drivers' action and then provide correct feedback to users. This study also compared the result with the-state-of-art systems, including Linear Regression (LR), Multi-Layer Perceptron Neural Network (MLPNN) and Support Vector Regression (SVR). Results of this study demonstrate the effectiveness of the proposed FLFNN model.

关键词： Electroencephalography Brain modeling Fuzzy neural networks Input variables Biological neural networks Vehicles Independent component analysis

来源：评论

学校读者我要写书评

暂无评论

Optimal power allocation for heterogeneous data traffic in NAF relay-assisted uplink transmission

Optimal power allocation for heterogeneous data traffic in N...

引用

International Symposium on Communications and Information Technologies (ISCIT)

作者： Peng Gong Haiqiao Wu Ping Li Wenbo Shi Duk Kyung Kim Beijing Institute of Technology National Key Lab. of Mechatronic Engineering and Control Beijing China Northeastern University School of Computer and Communication Engineering Qinhuangdao China Department of Information and Communication Engineering Inha University Nam-gu Incheon Korea

ISBN: (纸本)9781479944156

For the future wireless networks, heterogeneous data traffic services, i.e., variant bit-rate (VBR) service and constant bit rate (CBR) service are needed to be supported. The optimal power allocation algorithm for the non-orthogonal AF (NAF) Relays-assisted multicast transmission, which may be suitable for the VBR service, has been investigated in [2]. However, the power allocation algorithms for the cases of CBR service and heterogeneous data traffics service are not considered. In this paper, a power allocation problem is addressed by considering the heterogeneous data traffic with VBR and CBR services in the uplink data transmission, where Different from assumption of infinite length of spreading code in [2], a finite length of spreading code is considered and the interference among the signals from mobile terminal and relays exists. And then, an optimal power allocation algorithm is proposed by solving its inverse problem. Simulation results demonstrate the efficiency of the proposed algorithm.

关键词： Relays Mobile communication Algorithm design and analysis Three-dimensional displays Resource management Power demand Radio access networks

来源：评论

学校读者我要写书评

暂无评论

Leaderless Consensus in Networks of Flexible–Joint Manipulators

引用

IFAC Proceedings Volumes 2014年第3期47卷 6656-6661页

作者： Emmanuel Nuño Daniela Valle Ioannis Sarras Luis Basañez Department of Computer Science. CUCEI University of Guadalajara. Guadalajara Mexico Electronics Department. CUCEI University of Guadalajara. Guadalajara Mexico Automatic Control Department SUPELEC. Gif-sur-Yvette France Institute of Industrial and Control Engineering Technical University of Catalonia. Barcelona Spain

This work studies the leaderless consensus problem in networks composed of non-identical flexible-joint robot manipulators. Using standard functional analysis, i.e., Barbâlat's Lemma, it is established that a simple control law provides a solution to the leaderless consensus problem. The network is modeled as an undirected graph and the interconnection can exhibit variable time-delays. The proposed controller consists of two different terms, one that dynamically compensates the robot gravity and another which ensures the desired consensus objective. This last term is a simple Proportional plus damping scheme. Simulations, using a network with nine 2-degrees of freedom manipulators, are provided to support the theoretical contributions of this work.

关键词： Network of Robots Flexible Arms Decentralized control Time-Delays

来源：评论

学校读者我要写书评

暂无评论

Semi-randomized hashing for large scale data retrieval

Semi-randomized hashing for large scale data retrieval

引用

International Conference on Data Science and Advanced Analytics (DSAA)

作者： Haichuan Yang Xiao Bai Jun Zhou Peng Ren Jian Cheng Lu Bai School of Computer Since and Engineering Beihang University China School of Information and Communication Technology Griffith University Australia College of Information and Control Engineering China University of Petroleum China Institute of Automation Chinese Academy of Sciences China Department of Computer Science University of York UK

In information retrieval, efficient accomplishing the nearest neighbor search on large scale database is a great challenge. Hashing based indexing methods represent each data instance as a binary string to retrieve the approximate nearest neighbors. In this paper, we present a semi-randomized hashing approach to preserve the Euclidean distance by binary codes. Euclidean distance preserving is a classic research problem in hashing. Most hashing methods used purely randomized or optimized learning strategy to achieve this goal. Our method, on the other hand, combines both randomized and optimized strategies. It starts from generating multiple random vectors, and then approximates them by a single projection vector. In the quantization step, it uses the orthogonal transformation to minimize an upper bound of the deviation between real-valued vectors and binary codes. The proposed method overcomes the problem that randomized hash functions are isolated from the data distribution. What's more, our method supports an arbitrary number of hash functions, which is beneficial in building better hashing methods. The experiments show that our approach outperforms the alternative state-of-the-art methods for retrieval on the large scale dataset.

关键词： Vectors Euclidean distance Binary codes Training Equations Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

A single-station location method based on long baseline interferometer

A single-station location method based on long baseline inte...

引用

International Symposium on Communications and Information Technologies (ISCIT)

作者： Li Ping Wang Guohong Xiaopeng Yan Gong Peng Wenbo Shi Liu Jian Beijing Institute of Technology National Key Lab. of Mechatronic Engineering and Control Beijing China Northeastern University School of Computer and Communication Engineering Qinhuangdao China China Electronics Technology Group Corporation Zhejiang China

ISBN: (纸本)9781479944156

Conventional long baseline interferometer based Direction of Arrival (DOA) requires multi-group long baselines and short baselines to deblur. In this paper, only using the time difference of arrival (TDOA) data of long baseline interferometer can cancel the debluring shortage and achieve high-precision DOA estimation. Meanwhile iterative filtering algorithm is adopted to extract high-precision changing rate of phase difference from the fuzzy phase difference data of long baseline. Combined with the measured DF and the change rate of phase difference, particle filter algorithm is utilized to achieve high-precision single-station passive location. Parameter measurement and the distribution of location error are verified through theoretical simulations. And the simulation results demonstrate the efficiency of the single-station location method based on long baseline interferometer.

关键词： Direction-of-arrival estimation Accuracy Filtering Atmospheric measurements Particle measurements

来源：评论

学校读者我要写书评

暂无评论

The Use of Intelligent Systems for Planning and Scheduling of Product Development Projects

引用

Procedia computer Science 2014年 35卷 1586-1595页

作者： Marcin Relich Wojciech Muszyński University of Zielona Gora Licealna 9 Zielona Gora 65-216 Poland Wrocław University of Technology Institute of Computer Engineering Control and Robotics Wybrzeże Wyspiańskiego 27 Wrocław 50-370 Poland

The paper investigates the use of intelligent systems to identify the factors that significantly influence the duration of new product development. These factors are identified on the basis of an internal database of a production enterprise and further used to estimate the duration of phases in product development projects. In the paper, some models and methodologies of the knowledge discovery process are compared and a method of knowledge acquisition from an internal database is proposed. The presented approach is dedicated to industrial enterprises that develop modifications of previous products and are interested in obtaining more precise estimates for project planning and scheduling. The example contains four stages of the knowledge discovery process including data selection, data transformation, data mining, and interpretation of patterns. The example also presents a performance comparison of intelligent systems in the context of variable reduction and preprocessing. Among data mining techniques, artificial neural networks and the fuzzy neural system are chosen to seek relationships between the duration of project phase and other data stored in the information system of an enterprise.

关键词： data mining knowledge acquisition pattern recognition fuzzy neural system artificial neural networks business intelligence systems

来源：评论

学校读者我要写书评

暂无评论

Parity space-based fault diagnosis of CCBII braking system

引用

Journal of Central South University 2013年第10期20卷 2922-2928页

作者：黄志武杨迎泽王晶李赟 School of Information Science and Engineering Central South University Institute of Communication Control and Safe Operation for Transportation SystemCentral South University Hunan Engineering Laboratory for Advanced Control and Intelligent Automation School of Computer Engineering Bethune-Cookman University

Fault diagnosis is a key issue of the CCBII(computer controlled brake II) braking system, because the CCBII braking system is very complicated and nonlinear, which may exhibit isolated and multi-component coupled faults. A parity space-based method was proposed for fault diagnosis of CCBII braking systems. Firstly, the mathematical models were established according to three function modules of CCBII braking systems where the air fluid theory was utilized. Then, parity vector and threshold function were designed for each output of the system so as to identify more system faults. Fault character matrix was built based on the causal relationship between the output and the fault according to the system function and internal structure. Finally, fault detection and isolation can be realized by the comparison of the observed system output and the fault character matrix. Simulation results show that the proposed method is entirely feasible and effective.

关键词： computer controlled brake II braking system FDI air fluid theory parity space

来源：评论

学校读者我要写书评

暂无评论

Estimates and measures of data communication and processing in nanoscaled classical and quantum physical systems 14

Estimates and measures of data communication and processing ...

引用

2014 14th IEEE International Conference on Nanotechnology, IEEE-NANO 2014

作者： Lyshevski, Sergey E. Reznik, Leonid Smith, Trevor C. Beisenbi, Mamyrbek A. Janar, Y. Jarasovna Mukataev, Nurlan S. Omarov, Arystan N. Department of Electrical Engineering Rochester Institute of Technology RochesterNY14623 United States Department of Computer Science Rochester Institute of Technology RochesterNY14623 United States Harris Corporation RochesterNY14618 United States Department of System Analyses and Control L.N. Gumilyov Eurasian National University Astana Kazakhstan OL-Technologies Ltd. 7 Alpamys Batyr Street Astana Kazakhstan

ISBN: (纸本)9781479956227

This paper studies fundamentals of classical, classical-quantum and quantum information technologies to advance sensing, data acquisition and computing. The overall goal is to define, analyze and evaluate classical and quantum-mechanical information measures pertained to data processing by low-power nanoelectronic devices, nanoICs, nano-waveguides, CMOS nanophotonics, etc. Electronic, optoelectronic and photonic systems operate on the electron-and photon-induced transductions. There are fundamental differences in physics, arithmetics, device- and system-level solutions as electrostatic and quantum phenomena are utilized. This paper analyzes multi-physics quantum → classical processing. We enable a knowledge base in cognizant areas across computer science and engineering. Our findings enable existing and future communication, sensing, information fusion, computing and processing platforms. Consistent tools and practical schemes facilitate developments of novel engineering solutions, technical readiness, technological capabilities and commercialization capacities. © 2014 IEEE.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Two-stage cubature Kalman filter for nonlinear system with random bias

Two-stage cubature Kalman filter for nonlinear system with r...

引用

International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)

作者： Lu Zhang Meilei Lv Zhuyun Niu Wenbi Rao School of Computer Science Wuhan University of Technology Wuhan China School of Electrical and Information Engineering Quzhou University Quzhou China North Automatic Control Technology Institute Taiyuan China

ISBN: (纸本)9781479967339

In contrast with UKF, the standard CKF can solve high-dimensional nonlinear filter problems. However, when the nonlinear systematic dimension increases, the accuracy of CKF will decline and the computational cost will increase rapidlly. Two-Stage Kalman filter can solve this problem, but it only applies to linear systems. This paper proposes a two-stage Cubature Kalman filter (TSCKF) which can solve high-dimensional nonlinear systems with random bias. The estimate of the TSCKF can be expressed as the output of the bias free filter and bias filter. The bias free filter doesn't consider the bias and its output is corrected by the bias filter. In comparison with Augmented state Cubature Kalman Filter (ASCKF), the TSCKF avoids dimension disaster effectively and has little computation to solve high-dimensional nonlinear filter problem.

关键词： Kalman filters Nonlinear systems Vectors Educational institutions Accuracy Estimation Covariance matrices

来源：评论

学校读者我要写书评

暂无评论

Bounded synchronization in resistive multi-terminal VSC-HVDC transmission systems

Bounded synchronization in resistive multi-terminal VSC-HVDC...

引用

IEEE Annual Conference on Decision and control

作者： Arnau Doria-Cerezo Josep M. Olm Mario di Bernardo Massimiliano Quaglia Emmanuel Nuno Department of Electrical Engineering and the Institute of Industrial and Control Engineering Universitat Politecnica de Catalunya 08028 Barcelona Spain Department of Applied Mathematics IV and the Institute of Industrial and Control Engineering Universitat Politecnica de Catalunya 08028 Barcelona Spain Department of Electrical Engineering and Information Technologies University of Naples Federico II 80125 Naples Italy Department of Computer Science CUCEI University of Guadalajara 44430 Guadalajara Mexico

ISBN: (纸本)9781467360890

Multi-terminal VSC-HVDC transmission is a promising solution to transport energy from the generating plants to the distribution stations, and the number and size of the corresponding power grids is expected to increase in the next years. Such a system presents challenging control problems that, so far, have been approached with classical control techniques. However, large scale systems of interconnected nodes fall within the framework of the emerging field of complex networks. This paper analyzes the stability of multi-terminal VSC-HVDC systems from a complex dynamical network perspective, and provides sufficient conditions to ensure bounded synchronization of its trajectories. The obtained results are validated via numerical simulations.

关键词： multiterminal Power grids HVDC transmission system Transmission systems Bounded Sufficient conditions

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：