检索结果-内蒙古大学图书馆

Boosted Pre-loaded Mixture of Experts for low-resolution face recognition

International Journal of Hybrid intelligent systems 2012年第3期9卷 145-158页

作者： Ebrahimpour, Reza Sadeghnejad, Naser Masoudnia, Saeed Arani, Seyed Ali Asghar Abbaszadeh School of Cognitive Sciences Institute for Research in Fundamental Sciences Tehran Iran Brain and Intelligent Systems Research Laboratory Department of Electrical and Computer Engineering Shahid Rajaee Teacher Training University Tehran Iran Central Tehran Branch and Young Researchers Club Islamic Azad University Tehran Iran

A modified version of Boosted Mixture of Experts (BME) for low-resolution face recognition is presented in this paper. Most of the methods developed for low-resolution face recognition focused on improving the resolution of face images and/or special feature extraction methods that can deal effectively with low-resolution problem. However, we focused on the classification step of face recognition process in this paper. Using Neural Networks (NN) combinations is an efficient approach to deal with complex classification problems, such as the low-resolution face recognition which involves high-dimensional feature sets and highly overlapped classes. Mixture of Experts (ME) and boosting methods are two of the most popular and interesting NN combining methods, which have great potential for improving performance in classification. A modified combining approach based on both features of ME and boosting is presented in order to deal with this complex classification problem efficiently. Previous works [1,2] made attempts to incorporate the complementary features of boosting method in ME training algorithm to boost the performance. These approaches called Boosted Mixture of Experts (BME) have some drawbacks. Based on the analysis of the problems of previous approaches, some modifications are suggested in this paper. A modification in the pre-loading (initialization) procedure of ME is proposed to address the limitations of previous approaches and overcome them using a two stages pre-loading procedure. In our suggested approach, both the error and confidence measures are used as the difficulty criteria in boosting-based partitioning of the problem space. Regarding the nature of this approach, we call the proposed method Boosted Pre-loaded Mixture of Experts (BPME). The proposed method is tested in a low-resolution face recognition problem and compared to the other variations of ME and boosting method. The experiments are conducted using low-resolution variations of two common

关键词： Neural Networks ensemble Mixture of Experts boosting Boosted Mixture of Experts low-resolution face recognition

来源：评论

学校读者我要写书评

暂无评论

Reports of the AAAI 2011 conference workshops

Reports of the AAAI 2011 conference workshops

引用

作者： Agmon, Noa Agrawal, Vikas Aha, David W. Aloimonos, Yiannis Buckley, Donagh Doshi, Prashant Geib, Christopher Grasso, Floriana Green, Nancy Johnston, Benjamin Kaliski, Burt Kiekintveld, Christopher Law, Edith Lieberman, Henry Mengshoel, Ole J. Metzler, Ted Modayil, Joseph Oard, Douglas W. Onder, Nilufer O'Sullivan, Barry Pastra, Katerina Precup, Doina Ramachandran, Sowmya Reed, Chris Sariel-Talay, Sanem Selker, Ted Shastri, Lokendra Singh, Satinder Smith, Stephen F. Srivastava, Siddharth Sukthankar, Gita Uthus, David C. Williams, Mary-Anne Department of Computer Science University of Texas at Austin United States Center for Knowledge Driven Information Systems Infosys Labs India Adaptive Systems Section Naval Research Laboratory Washington DC United States Department of Computer Science University of Maryland College Park United States EMC's Center of Excellence in Ireland Research Europe at EMC Ireland Department of Computer Science University of Georgia United States School of Informatics University of Edinburgh United Kingdom Department of Computer Science University of Liverpool United Kingdom Department of Computer Science University of North Carolina Greensboro United States Faculty of Engineering and Information Technology University of Technology Sydney Australia VeriSign Inc. United States Department of Computer Science University of Texas at El Paso United States Machine Learning Department Carnegie Mellon University United States Massachusetts Institute of Technology Media Laboratory United States Carnegie Mellon University's Silicon Valley Campus United States Darrell W. Hughes Program for Religion and Science Dialogue Oklahoma City University United States Department of Computing Science University of Alberta Canada College of Information Studies Institute for Advanced Computer Studies University of Maryland College Park United States Department of Computer Science Michigan Technological University United States Department of Computer Science University College Cork Ireland Cognitive Systems Research Insitute Athens Greece School of Computer Science McGill University Canada Stottler Henke Inc. United States School of Computing University of Dundee United Kingdom Department of Computer Engineering Istanbul Technical University Turkey Convergence Lab Infosys Technologies Ltd. United States Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor United States Robotics Institute Carnegie Mellon University United States University of Wisconsin

The AAAI-11 workshop program was held Sunday and Monday, August 7-18, 2011, at the Hyatt Regency San Francisco in San Francisco, California USA. The AAAI-11 workshop program included 15 workshops covering a wide range of topics in artificial intelligence. The titles of the workshops were Activity Context Representation: Techniques and Languages;Analyzing Microtext;Applied Adversarial Reasoning and Risk Modeling;Artificial Intelligence and Smarter Living: The Conquest of Complexity;Artifiicial Intelligence for Data Center Management and Cloud Computing;Automated Action Planning for Autonomous Mobile Robots;Computational Models of Natural Argument;Generalized Planning;Human Computation;Human-Robot Interaction in Elder Care;Interactive Decision Theory and Game Theory, 2010;Language-Action Tools for Cognitive Artificial Agents: Integrating Vision, Action, and Language;Lifelong Learning from Sensorimotor Experience;Plan, Activity, and Intent Recognition;and Scalable Integration of Analytics and Visualization. This article presents short summaries of those events. Copyright © 2012, Association for the Advancement of Artificial Intelligence. All rights reserved.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Super-Bit Locality-Sensitive Hashing 12

Super-Bit Locality-Sensitive Hashing

引用

Annual Conference on Neural Information Processing systems

作者： Jianqiu Ji Jianmin Li Shuicheng Yan Bo Zhang Qi Tian State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology (TNList)Department of Computer Science and TechnologyTsinghua University Beijing 100084 China Department of Electrical and Computer Engineering National University of Singapore Singapore 117576 Department of Computer Science University of Texas at San AntonioOne UTSA Circle University of Texas at San Antonio San Antonio TX 78249-1644

ISBN: (纸本)9781627480031

Sign-random-projection locality-sensitive hashing (SRP-LSH) is a probabilistic dimension reduction method which provides an unbiased estimate of angular similarity, yet suffers from the large variance of its estimation. In this work, we propose the Super-Bit locality-sensitive hashing (SBLSH). It is easy to implement, which orthogonalizes the random projection vectors in batches, and it is theoretically guaranteed that SBLSH also provides an unbiased estimate of angular similarity, yet with a smaller variance when the angle to estimate is within (0, n/2]. The extensive experiments on real data well validate that given the same length of binary code, SBLSH may achieve significant mean squared error reduction in estimating pairwise angular similarity. Moreover, SBLSH shows the superiority over SRP-LSH in approximate nearest neighbor (ANN) retrieval experiments.

关键词： unbiased estimate hashing Angle REDUCTION METHODS observational data

来源：评论

学校读者我要写书评

暂无评论

Doubly selective channel estimation for amplify-and-forward relay networks

Doubly selective channel estimation for amplify-and-forward ...

引用

IEEE Conference on Wireless Communications and Networking

作者： Gongpu Wang Feifei Gao Jiaru Lin Chintha Tellambura School of Computer and Information Technology Beijing Jiaotong University China National Mobile Communications Research Laboratory South East University Nanjing China State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Automation Tsinghua University Beijing China Key Laboratory of Universal Wireless Communications Ministry of Education China Department of Electrical and Computer Engineering University of Alberta Edmonton Canada

In this paper, the estimation of doubly selective channel is considered for amplify-and-forward (AF) relay networks. The complex exponential basis expansion model (CE-BEM) is chosen to describe the time-varying channel, from which the infinite channel parameters are mapped onto finite ones. Since direct estimation of these coefficients encounters high computational complexity and large spectral cost, we develop an efficient estimator targeting at some specially defined channel parameters. The training sequence design that can minimize the channel estimation mean-square error is also proposed.

关键词： Training Channel estimation Relays Wireless communication Educational institutions Estimation Vectors

来源：评论

学校读者我要写书评

暂无评论

{\cal U}Boost: Boosting with the Universum

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2012年第4期34卷 825-832页

作者： Chunhua Shen Peng Wang Fumin Shen Hanzi Wang Australian Center for Visual Technologies and School of Computer Science University of Adelaide North Terrace SA Australia School of Automation Science and Electrical Engineering Beihang University Beijing China School of Computer Science and Technology Nanjing University of Science and Technology of PLA Nanjing China Cognitive Science Department School of Information Science and Technology and Fujian Key Laboratory of the Brain-like Intelligent Systems Xiamen University Xiamen Fujian China School of Computer Science University of Adelaide SA Australia

It has been shown that the Universum data, which do not belong to either class of the classification problem of interest, may contain useful prior domain knowledge for training a classifier [1], [2]. In this work, we design a novel boosting algorithm that takes advantage of the available Universum data, hence the name UBoost. UBoost is a boosting implementation of Vapnik's alternative capacity concept to the large margin approach. In addition to the standard regularization term, UBoost also controls the learned model's capacity by maximizing the number of observed contradictions. Our experiments demonstrate that UBoost can deliver improved classification accuracy over standard boosting algorithms that use labeled data alone.

关键词： Boosting Training Educational institutions Optimization Algorithm design and analysis Histograms Accuracy

来源：评论

学校读者我要写书评

暂无评论

Residual muscle contraction and prosthetic socket interface force in a transtibial amputee upon the osteomyoplastic procedure - A preliminary study

Residual muscle contraction and prosthetic socket interface ...

引用

2012 ISSNIP Biosignals and Biorobotics Conference: Biosignals and robotics for Better and Safer Living, BRC 2012

作者： Mai, Anh Commuri, Sesh Day, Jonathan Dionne, Carol Ertl, William J. J. School of Electrical and Computer Engineering University of Oklahoma Norman OK 73019 United States Intelligent and Robotic Systems United States Department of Orthopaedic Surgery and Rehabilitation Orthotic/Prosthetic Section University of Oklahoma Health Sciences Center Oklahoma City OK 73117 United States Mechanical Therapy Research Laboratory Department of Rehabilitation Sciences United States College of Allied Health University of Oklahoma Health Sciences Center Oklahoma City OK 73117 United States Department of Orthopedic Surgery and Rehabilitation United States College of Medicine University of Oklahoma Health Sciences Center Oklahoma City OK 73117 United States

ISBN: (纸本)9781467324762

In the Transtibial Osteomyoplastic Amputation (TOA) technique, the fibular end and the tibial end are connected to each other by a bone bridge in order to stabilize the bony anatomy of the residual limb. In addition, during the myoplasty procedure, the ends of the muscles are secured to one another and to the bony foundations to re-establish the length-tension relationship. In contrast to conventional amputation techniques in which the muscles are cut and the length-tension relationship is lost overtime, the TOA procedure is anticipated to allow muscles to actively contract and return blood to the heart more efficiently [1]. In this study, the outcomes of the TOA procedure were investigated by measuring electromyography signals from the tibialis anterior and gastrocnemius muscles on the amputated leg as well as the interface force inside the prosthetic socket at the end-bearing level of a transtibial amputee. The subject had undergone the TOA procedure and the study was conducted while the subject walked on different terrain (level ground with different speeds, stairs, and incline) with two different kinds of prosthetic feet. Preliminary results showed that (1) the residual muscles appeared to be active while walking on various terrain, and (2) the activation level of the residual tibialis anterior muscle was found to be related to the force variation inside the prosthetic socket. © 2012 IEEE.

关键词： Muscle

来源：评论

学校读者我要写书评

暂无评论

New simplified model for an under-actuated quadruped robot in bounding motion

New simplified model for an under-actuated quadruped robot i...

引用

2011 2nd International Conference on Control, Instrumentation and Automation, ICCIA 2011

作者： Kazemi, Hamed Majd, Vahid Johari Moghaddam, Majid M. Intelligent Control Systems Laboratory School of Electrical and Computer Engineering Tarbiat Modares University Tehran Iran Robotics and Mechatronics Laboratory Mechanical Engineering Department Tarbiat Modares University Tehran Iran

ISBN: (纸本)9781467316903

In this paper, a quadruped robot is studied in bounding motion. A new simplified model of quadruped robot in bounding motion with four actuated and two unactuated joints is developed. The kinetic and potential energies of the under-actuated mechanical model of the quadruped robot are obtained and the dynamics of the robot model is derived using the Lagrangian method. It is shown that the dynamical equation of the proposed simplified model belongs to a class of second-order nonholonomic mechanical systems. The main motivation of this paper is to obtain quadruped model in bounding motion such that one can apply different control methods directly or after transformation in the obtained dynamic equations. Utilizing MATLAB, dynamics of the planar model has been simulated in backward and forward states. Physical parameters of the Little-Dog robot as an instance of the quadruped robot are considered in simulation The simulation is without control and therefore is unstable but it illustrates robot's manner in bounding motion before instability. © 2011 IEEE.

关键词： Potential energy

来源：评论

学校读者我要写书评

暂无评论

Integrated Approach to Hypersonic Vehicle Modeling

Integrated Approach to Hypersonic Vehicle Modeling

引用

Chinese Control Conference

作者： Xiaofeng Su Yingmin Jia Junping Du Fashan Yu The Seventh Research Division and the Department of Systems and Control Beihang University (BUAA) Key Laboratory of Mathematics Informatics and Behavioral Semantics (LMIB) Ministry of Education SMSS Beihang University (BUAA) Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia School of Computer Science and Technology Beijing University of Posts and Telecommunications School of Electrical Engineering and Automation Henan Polytechnic University

ISBN: (纸本)9781467325813

This paper is devoted to the modeling problem of hypersonic vehicle with significant couplings. An integrated approach is developed to analytically model the dynamics of hypersonic vehicle, in which the effects of variable mass, spherical rotating earth, and couplings among the sub-models are considered. Furthermore, a preliminary analysis is conducted using the general data of a hypersonic vehicle. The simulation results show that the maximum of the Coriolis force can reach values up to 7.02% of the vehicle weight, and that the thermal load determined by the nonuniform aerodynamic heating and the properties of the structure has a significant influence on the elastic deformation.

关键词： Hypersonic vehicle modeling Inertial dynamics Aerodynamics Elasticity Heating hypersonic vehicles Aerodynamics elasticity Coriolis force Vehicle weight Heating Couplings Thermal loading elastic deformation

来源：评论

学校读者我要写书评

暂无评论

Stochastic H_2 Optimal Control of Discrete-Time Markov Jump systems with Periodic Coefficients

Stochastic H_2 Optimal Control of Discrete-Time Markov Jump ...

引用

American Control Conference

作者： Hongji Ma Yingmin Jia Junping Du Fashan Yu Seventh Research Division and the Department of Systems and Control Beihang University (BUAA) Beijing 100191 China Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia School of Computer Science and Technology Beijing University of Posts and Telecommunications Beijing 100876 China School of Electrical Engineering and Automation Henan Polytechnic University Jiaozuo 454000 Henan China

ISBN: (纸本)9781457710957

In this paper, the H_2 optimal state-feedback control problem is investigated for discrete-time Markov jump systems subject to periodic coefficients and multiplicative noise. First of all, an exhaustive analysis is pursued to set up an H_2 performance criterion (H_2 norm), which can be characterized by the periodic solutions of two generalized Lyapunov equations. Based on the obtained H_2 norm, the H_2 optimal state-feedback controller is designed in terms of the stabilizing solution of a discrete-time generalized Riccati equation with periodic coefficients. Moreover, this stabilizing solution can be computed efficiently by the available iterative algorithm.

关键词： Markov processes Noise Educational institutions Riccati equations Optimal control

来源：评论

学校读者我要写书评

暂无评论

Optimization of Power System Stabilizer Parameters using Population-Based Incremental Learning

Optimization of Power System Stabilizer Parameters using Pop...

引用

IEEE Energy Conversion Congress and Exposition

作者： Komla A Folly Ganesh K. Venayagamoorthy Department of Electrical Engineering University of Cape Town South Africa Holcombe Dept. of Electrical and Computer Engineering Real-Time Power and Intelligent Systems Laboratory Clemson University Clemson SC 29634 USA

ISBN: (纸本)9781467308021

Population-based incremental learning (PBIL) has been recently applied to a range of optimization problems in controller designs with promising results. It combines aspects of genetic algorithm with competitive learning. The learning rate in the standard PBIL is generally fixed which makes it difficult for the algorithm to explore the search space effectively. In this paper, the standard PBIL is improved by using a combination of adaptive and fixed learning rate that varies according to the generation. The adaptive-fixed (AF) algorithm can adjust the learning rate automatically according to the degree of evolution of the search. The objective of the power system stabilizer (PSS) design is to achieve adequate stability over a wide range of power system operating conditions. The proposed controller is compared with conventional PBIL with fixed learning rate (PBIL) and tested under various operating conditions. Simulation results show that the AFPBIL based PSS provides a more efficient search capability and gives a better damping and adequate dynamic performance of the system than the conventional PBIL based PSS.

关键词： PSS Population-Based PBIL

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：