检索结果-内蒙古大学图书馆

The Journal of Machine Learning Research 2016年第1期17卷

作者： Kevin Murphy Bernhard Schölkopf Shiliang Zhang Hui Jiang Lirong Dai Google MPI for Intelligent Systems National Engineering Laboratory for Speech and Language Information Processing University of Science and Technology of China Hefei Anhui China Department of Electrical Engineering and Computer Science York UniversityToronto OntarioCanada

In this paper, we propose a novel model for high-dimensional data, called the Hybrid Orthogonal Projection and Estimation (HOPE) model, which combines a linear orthogonal projection and a finite mixture model under a unified generative modeling framework. The HOPE model itself can be learned unsupervised from unlabelled data based on the maximum likelihood estimation as well as discriminatively from labelled data. More interestingly, we have shown the proposed HOPE models are closely related to neural networks (NNs) in a sense that each hidden layer can be reformulated as a HOPE model. As a result, the HOPE framework can be used as a novel tool to probe why and how NNs work, more importantly, to learn NNs in either supervised or unsupervised ways. In this work, we have investigated the HOPE framework to learn NNs for several standard tasks, including image recognition on MNIST and speech recognition on TIMIT. Experimental results have shown that the HOPE framework yields significant performance gains over the current state-of-the-art methods in various types of NN learning problems, including unsupervised feature learning, supervised or semi-supervised learning.

关键词： PCA mixture models neural networks orthogonal projection unsupervised learning von Mises-Fisher (vMF) model

来源：评论

学校读者我要写书评

暂无评论

Multi-source information fusion model in rule-based Gaussian-shaped fuzzy control inference system incorporating Gaussian density function

Multi-source information fusion model in rule-based Gaussian...

引用

作者： Li, Zairan He, Ting Cao, Luying Wu, Tunhua McCauley, Pamela Balas, Valentina E. Shi, Fuqian Tianjin Key Laboratory of Process Measurement and Control School of Electrical Engineering and Automation Tianjin University Tianjin China Wenzhou Vocational and Technical College Wenzhou China College of Information and Engineering Wenzhou Medical University Wenzhou325035 China Department of Industrial Engineering and Management Systems University of Central Florida OrlandoFL United States Department of Automation and Applied Informatics Aurel Vlaicu University of Arad Romania

An increasing number of applications require the integration of data from various disciplines, which leads to problems with the fusion of multi-source information. In this paper, a special information structure formalized in terms of three indices (the central presentation, population or scale, and density function) is proposed. Single and mixed Gaussian models are used for single source information and their fusion results, and a parameter estimation method is also introduced. Furthermore, fuzzy similarity computing is developed for solving the fuzzy implications under a Mamdani model and a Gaussian-shaped density function. Finally, an improved rule-based Gaussian-shaped fuzzy control inference system is proposed in combination with a nonlinear conjugate gradient and a Takagi-Sugeno (T-S) model, which demonstrated the effectiveness of the proposed method as compared to other fuzzy inference systems. © 2015 - IOS Press and the authors. All rights reserved.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

A modified region growing based algorithm to vessel segmentation in magnetic resonance angiography

A modified region growing based algorithm to vessel segmenta...

引用

IEEE Long Island systems, Applications and Technology Conference (LISAT)

作者： Muder M. Almi'ani Buket D. Barkana Department of Computer Information Systems Al-Hussein Bin Talal University Signal Processing Research Group Laboratory University of Bridgeport Bridgeport CT USA Department of Electrical Engineering Signal Processing Research Group Laboratory University of Bridgeport Bridgeport CT USA

The progress of medical imaging instrumentation has stirred the development of new computer-aided methods of image processing and analysis for better understanding and interpretation of medical images for differential diagnosis, intervention, and treatment monitoring. Image processing and analysis methods have been used to help physicians to make important medical decisions through physician-computer interaction. A modified region growing algorithm is proposed to extract cerebral vessels using a magnetic resonance angiography (MRA) database. To improve the performance of the image segmentation method, as a pre-processing step, image enhancement methods are applied by the gamma correction technique and spatial operations. This step improves the detection of gray-level discontinuities in MRA images. The traditional region growing method is modified by extending the neighborhood as 24 pixels and by defining a filling protocol to label vascular structure. The performance of the proposed algorithm is compared with that of the traditional region growing method and four other segmentation methods. Our proposed method outperformed the other methods. The minimum and maximum errors of the modified region growing method is calculated as zero and 0.82, respectively while the traditional region growing method has 1.85 and 21.91.

关键词： Image segmentation Blood vessels Angiography Filling Magnetic resonance Protocols

来源：评论

学校读者我要写书评

暂无评论

[email protected] : Analysis and results of evolving competitions for domestic and service robots

引用

Artificial Intelligence 2015年 229卷 258-281页

作者： Luca Iocchi Dirk Holz Javier Ruiz-del-Solar Komei Sugiura Tijn van der Zant Department of Computer Control and Management Engineering Sapienza University of Rome Italy Autonomous Intelligent Systems Group University of Bonn Germany Department of Electrical Engineering & Advanced Mining Technology Center Universidad de Chile Chile Information Services Platform Laboratory National Institute of Information and Communications Technology Japan Cognitive Robotics Laboratory University of Groningen The Netherlands

Scientific competitions are becoming more common in many research areas of artificial intelligence and robotics, since they provide a shared testbed for comparing different solutions and enable the exchange of research results. Moreover, they are interesting for general audiences and industries. Currently, many major research areas in artificial intelligence and robotics are organizing multiple-year competitions that are typically associated with scientific conferences. One important aspect of such competitions is that they are organized for many years. This introduces a temporal evolution that is interesting to analyze. However, the problem of evaluating a competition over many years remains unaddressed. We believe that this issue is critical to properly fuel changes over the years and measure the results of these decisions. Therefore, this article focuses on the analysis and the results of evolving competitions. In this article, we present the [email protected] competition, which is the largest worldwide competition for domestic service robots, and evaluate its progress over the past seven years. We show how the definition of a proper scoring system allows for desired functionalities to be related to tasks and how the resulting analysis fuels subsequent changes to achieve general and robust solutions implemented by the teams. Our results show not only the steadily increasing complexity of the tasks that [email protected] robots can solve but also the increased performance for all of the functionalities addressed in the competition. We believe that the methodology used in [email protected] for evaluating competition advances and for stimulating changes can be applied and extended to other robotic competitions as well as to multi-year research projects involving Artificial Intelligence and Robotics.

关键词： Robotic competitions Artificial intelligence and robotics Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A data-driven approach to predict daily risk of Clostridium difficile infection at two large academic health centers

引用

Open Forum Infectious Diseases 2017年第SUPPL_1期4卷 S403-S404页

作者： Makar, Maggie Oh, Jeeheh Fusco, Christopher Marchesani, Joseph McCaffrey, Robert Rao, Krishna Ryan, Erin E Washer, Laraine West, Lauren R Young, Vincent B Guttag, John Hooper, David C Shenoy, Erica S Wiens, Jenna Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge Massachusetts Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge Massachusetts Computer Science and Engineering University of Michigan Ann Arbor Michigan Information Systems Partners HealthCare Boston Massachusetts Department of Internal Medicine Division of Infectious Diseases University of Michigan Medical School Ann Arbor Michigan Division of Infectious Diseases Massachusetts General Hospital Boston Massachusetts Infection Control Unit Massachusetts General Hospital Boston Massachusetts Harvard Medical School Boston Massachusetts Department of Medicine Division of Infectious Diseases Massachusetts General Hospital Boston Massachusetts Medical Practice Evaluation Center Department of Medicine Massachusetts General Hospital Boston Massachusetts

来源：评论

学校读者我要写书评

暂无评论

Bilateral Teleoperation of Multiple Agents with Formation control

引用

IEEE/CAA Journal of Automatica Sinica 2014年第2期1卷 141-148页

作者： Jing Yan Xian Yang Cailian Chen Xiaoyuan Luo Xinping Guan Institute of Electrical Engineering Yanshan University Department of Automation Shanghai Jiao Tong Universityand Key Laboratory of System Control and Information ProcessingMinistry of Education of China

This paper studies the formation problem for multislave teleoperation system over general communication networks,where multiple mobile slave agents are coupled with a single master robot. The forward and backward network transmission time delays are assumed to be asymmetric and *** to the quantization in the network, a dynamic quantization strategy is provided to quantize the output signals of the master robot and slave agents before transmitting. Then, a novel masterslave protocol is designed to achieve the formation task under variable time delays and quantization. Additionally, the sufficient conditions for stability are presented to show that the formation protocol can stabilize the master-slave system under variable time delays and quantization. Finally, simulation are performed to show effectiveness of the main results.

关键词： Robots Quantization (signal) Delay effects Protocols Stability analysis Delays Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

RETRACTED: Dual-mode predictive flexible rotor control for active magnetic bearings with input constraints

引用

Journal of Vibration and control 2016年第20期23卷 NP2页

作者： Yue Wu Jie Zhao Hai-Tao Zhang Ming-Can Fan Xi Yu Guangdong HUST Industrial Technology Research Institute Guangdong Province Key Lab of Digital Manufacturing Equipment ChinaKey Laboratory of Image Processing and Intelligent Control School of Automation State Key Laboratory of Digital Manufacturing Equipments and Technology Huazhong University of Science and Technology China Key Laboratory of Image Processing and Intelligent Control School of Automation State Key Laboratory of Digital Manufacturing Equipments and Technology Huazhong University of Science and Technology China Department of Mathematics Huizhou University China School of Electrical and Information Engineering Xi'an Technology University China

来源：评论

学校读者我要写书评

暂无评论

Experimental Verification of a Multi-robot Distributed control Algorithm with Containment and Group Dispersion Behaviors: the Case of Dynamic Leaders

引用

IEEE/CAA Journal of Automatica Sinica 2014年第1期1卷 54-60页

作者： Hejin Zhang Zhiyun Zhao Ziyang Meng Zongli Lin Department of Automation and Key Laboratory for System Control and Information Processing of Ministry of Education Shanghai Jiao Tong University the Access Linnaeus Centre School of Electrical Engineering Royal Institute of Technology Charles L. Brown Department of Electrical and Computer Engineering University of Virginia

This paper studies the containment and group dispersion control for a multi-robot system in the presence of dynamic leaders. Each robot is represented by a doubleintegrator dynamic model and a distributed control algorithm is developed to drive the multi-robot system to follow a group of dynamic leaders with containment and group dispersion behaviors. The effectiveness of the algorithm is then verified on a multi-robot control platform.

关键词： Heuristic algorithms Mobile robots Robot kinematics Trajectory Dispersion Decentralized control

来源：评论

学校读者我要写书评

暂无评论

Space QUEST mission proposal: Experimentally testing decoherence due to gravity

arXiv

引用

arXiv 2017年

作者： Joshi, Siddarth Koduru Pienaar, Jacques Ralph, Timothy C. Cacciapuoti, Luigi McCutcheon, Will Rarity, John Giggenbach, Dirk Lim, Jin Gyu Makarov, Vadim Fuentes, Ivette Scheidl, Thomas Beckert, Erik Bourennane, Mohamed Bruschi, David Edward Cabello, Adan Capmany, Jose Carrasco-Casado, Alberto Diamanti, Eleni Dusek, Miloslav Elser, Dominique Gulinatti, Angelo Hadfield, Robert H. Jennewein, Thomas Kaltenbaek, Rainer Krainak, Michael A. Lo, Hoi-Kwong Marquardt, Christoph Milburn, Gerard Peev, Momtchil Poppe, Andreas Pruneri, Valerio Renner, Renato Salomon, Christophe Skaar, Johannes Solomos, Nikolaos Stipčević, Mario Torres, Juan P. Toyoshima, Morio Villoresi, Paolo Walmsley, Ian Weihs, Gregor Weinfurter, Harald Zeilinger, Anton Zukowski, Marek Ursin, Rupert Institute for Quantum Optics and Quantum Information Austrian Academy of Sciences Boltzmanngasse 3 ViennaA-1090 Austria Centre for Quantum Computation & Communication Technology Department of Physics University of Queensland St LuciaQLD4072 Australia European Space Agency Keplerlaan 1 - P.O. Box 299 AG Noordwijk ZH2200 Netherlands Department of Electrical and Electronic Engineering University of Bristol Merchant Venturers Building Woodland Road BristolBS8 1UB United Kingdom German Aerospace Center Institute of Communications and Navigation Muenchner Strasse 20 Wessling82234 Germany Institute for Quantum Computing Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada Institute for Quantum Computing Department of Physics and Astronomy University of Waterloo WaterlooONN2L 3G1 Canada Precision Engineering Department Fraunhofer IOF Albert-Einstein-Straße 7 Jena07745 Germany Physics department Stockholm University Albanova universitetscentrum Universitetsvägen 10 Stockholm114 18 Sweden York Centre for Quantum Technologies Department of Physics University of York HeslingtonYO10 5DD United Kingdom University of Seville SevillaE-41012 Spain iTEAM Research Institute Universitat Politcnica de Valencia Valencia46022 Spain 4-2-1 Nukui-Kitamachi Koganei Tokyo184-8795 Japan CNRS Universite Pierre et Marie Curie Paris75005 France Department of Optics Faculty of Science Palacky University 17. Iistopadu 12 Olomouc772 00 Czech Republic Max Planck Institute for the Science of Light Bldg. 24 Günther-Scharowsky Str. 1 ErlangenD-91058 Germany Piazza Leonardo da Vinci 32 Milano20133 Italy School of Engineering University of Glasgow GlasgowG12 8LT United Kingdom Vienna Center of Quantum Science and Technology Faculty of Physics University of Vienna Boltzmanngasse 5 ViennaA-1090 Austria NASA Goddard Space Flight Center GreenbeltMD20771 United States Center for Quantum Information and Quantum Con

Models of quantum systems on curved space-times lack sufficient experimental verification. Some speculative theories suggest that quantum properties, such as entanglement, may exhibit entirely different behavior to purely classical systems. By measuring this effect or lack thereof, we can test the hypotheses behind several such models. For instance, as predicted by Ralph and coworkers [T C Ralph, G J Milburn, and T Downes, Phys. Rev. A, 79(2):22121, 2009;T C Ralph and J Pienaar, New Journal of Physics, 16(8):85008, 2014], a bipartite entangled system could decohere if each particle traversed through a different gravitational field gradient. We propose to study this effect in a ground to space uplink scenario. We extend the above theoretical predictions of Ralph and coworkers and discuss the scientific consequences of detecting/failing to detect the predicted gravitational decoherence. We present a detailed mission design of the European Space Agency's (ESA) Space QUEST (Space - Quantum Entanglement Space Test) mission, and study the feasibility of the mission scheme. Copyright © 2017, The Authors. All rights reserved.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

Scheduling of Electric Vehicle Charging Request and Power Allocation at Charging Stations with Renewable Energy 33

Scheduling of Electric Vehicle Charging Request and Power Al...

引用

第三十三届中国控制会议

作者： LI Jingwei YANG Bo XU Yang CHEN Cailian GUAN Xinping ZHANG Weidong Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Department of Electrical Engineering and Automation Shanghai Jiao Tong University

ISBN: (纸本)9781479947249

Smart grid, a concept proposed in 2003, is now attracting more and more attention because of its ability to integrate intensive information and renewable energy generating infrastructures. This paper focuses on scheduling charging process between multiple electric vehicles and charging stations in smart grid with renewable energy and storage devices. From the perspective of the whole system, the goal of minimizing the time average electricity cost with time-varying electricity price can be reached in this paper. With the participation of storage devices, charging-station-private renewable generation and electric vehicles power demands, we mathematically formulate a stochastic optimal problem and address it by employing Lyapunov optimization methods. Through mathematical derivation, stability of storage devices is achieved. Meanwhile, the upper bound for time average electricity cost can be calculated. The feature of our research is the independence on stochastic distribution of demand and renewable generation. Simulation results show the convergence of storage device state of charging（SOC） and illustrate the efficiency and performance of our algorithm.

关键词： Smart grid EV guidance renewable generation energy storage device Lyapunov optimization

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：