检索结果-内蒙古大学图书馆

Self-learning Scheduling Approach for Wireless Sensor Network

Self-learning Scheduling Approach for Wireless Sensor Networ...

The 2010 2nd International Conference on Future computer and Communication(第二届未来计算机与通信国际会议 ICFCC 2010)

作者： Jianjun Niu State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China Beijing Special Engineering Design and Research Institute Beijing China

ISBN: (纸本)9781424458219;9781424458240

Energy efficiency is one of key issues of wireless sensor network (VVSN). In this paper, we propose a self-learning scheduling approach (SSA) to reduce energy consumption for wireless sensor network (WSN). This approach integrates sleep scheduling together with packet transmission scheduling to reduce energy consumption. It enables nodes to learn continuous transmission parameters and sleep parameter through interacting with the WSN. The continuous value of transmission parameter is achieved by our extension of Q-learning method, and the value of sleep parameter can be calculated from the transmission parameter. We valid this approach in a MAC protocol and compare some network performances between the SSA and SMAC protocol. The simulation results show that our SSA performs much better than SMAC protocol in these QoS metrics.

关键词： Wireless sensor network scheduling reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A swarm intelligence based searching strategy for articulated 3D human body tracking

A swarm intelligence based searching strategy for articulate...

引用

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Xiaoqin Zhang Weiming Hu Xiangyang Wang Yu Kong Nianhua Xie Hanzi Wang Haibin Ling Steve Maybank College of Mathematics & Information science Wenzhou University Zhejiang China Institute of Automation National Laboratory of Pattern Recognition Beijing China School of Communication and Information Engineering Shanghai University Shanghai China School of Computer Science Beijing Institute of Technology Beijing China School of Computer Science University of Adelaide Australia Department of Computer and Information Science Temple University Philadelphia USA School of Computer Science and Information Systems Birkbeck College London UK

This paper proposes an annealed particle swarm optimization based particle filter algorithm for articulated 3D human body tracking. In our algorithm, a sampling covariance and an annealing factor are incorporated into the velocity updating equation of particle swarm optimization (PSO). The sampling covariance and the annealing factor are initiated with appropriate values at the beginning of the PSO iteration, and `annealing' is carried out at reasonable steps. Experiments with multi-camera walking sequences from the Brown dataset show that: 1) the proposed tracker can effectively alleviate the problem of inconsistency between the image likelihood and the true model; 2) the tracker is also robust to noise and body self-occlusion.

关键词： Particle swarm optimization Humans Annealing Particle filters Particle tracking Sampling methods Equations Image sampling Legged locomotion Noise robustness

来源：评论

学校读者我要写书评

暂无评论

Grasping simulation of an underactuated finger mechanism for larm hand

引用

International Journal of Modelling and Simulation 2010年第1期30卷 87-97页

作者： Yao, S. Wu, L. Ceccarelli, M. Carbone, G. Lu, Z. School of Automation Science and Electrical Engineering Beihang University Beijing China College of Information Engineering Central University for Nationalities Beijing China State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China Beijing University of Aeronautics and Astronautics China and University of Cassino Italy LARM: Laboratory of Robotics and Mechatronics Cassino United States

In this paper, the grasp operation of an underactuated finger mechanism is simulated with the aim to characterize and analyze its performance. The design of the proposed mechanism is based on spring systems that give suitable underactuation characteristics. A CAD model is proposed and then it is used in a procedure for numerical simulation. Simulation results show suitable capability for grasping a wide range of objects in size and shape by operating the mechanism inside the finger body. The achieved grasp has been simulated as a human-like functionality with a grasp contact in each phalanx.

关键词： computer aided design

来源：评论

学校读者我要写书评

暂无评论

Equivalence knowledge cumularspharolith and multiple approximate reasoning in R-logic ℂR

Equivalence knowledge cumularspharolith and multiple approxi...

引用

2009 WRI World Congress on computer science and information Engineering, CSIE 2009

作者： Yalin, Zheng Guang, Yang Research Center of Intelligent Information Technology Department of Computer Science and Technology Dongguan University of Science and Technology Dongguan 523808 China State Key Laboratory for Intelligent Technology and Systems Department of Automation Tsinghua University Beijing 100084 China

ISBN: (纸本)9780769535074

By casting off the direct restriction of topological structure, this paper presents another matching scheme between the input A* and the knowledge A → B based on the equivalence relation on formulae set F(S) and the corresponding equivalence classification F(S)/R = {[A]R |A ∈ F(S)} therefore, obtains another algorithm of approximate reasoning - the IV-type R-algorithm. The paper presents the IV-type R-algorithm for the simple approximate reasoning model and the multiple approximate reasoning model in the frame of R-logic ℂR. © 2008 IEEE.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Maximum Margin Feature Selection with manifold regularization

Unsupervised Maximum Margin Feature Selection with manifold ...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Bin Zhao James Kwok Fei Wang Changshui Zhang State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Automation Tsinghua University Beijing China Department of Computer Science and Engineering HKUST Hong Kong China

Feature selection plays a fundamental role in many pattern recognition problems. However, most efforts have been focused on the supervised scenario, while unsupervised feature selection remains as a rarely touched research topic. In this paper, we propose manifold-based maximum margin feature selection (M3FS) to select the most discriminative features for clustering. M3FS targets to find those features that would result in the maximal separation of different clusters and incorporates manifold information by enforcing smoothness constraint on the clustering function. Specifically, we define scale factor for each feature to measure its relevance to clustering, and irrelevant features are identified by assigning zero weights. Feature selection is then achieved by the sparsity constraints on scale factors. Computationally, M3FS is formulated as an integer programming problem and we propose a cutting plane algorithm to efficiently solve it. Experimental results on both toy and real-world data sets demonstrate its effectiveness.

关键词： Filters Pattern recognition Clustering algorithms Face recognition Laplace equations Laboratories Linear programming Feature extraction Unsupervised learning Supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Structural Health Monitoring System Using Wireless Sensor Network

A Structural Health Monitoring System Using Wireless Sensor ...

引用

International Conference on Wireless Communications, Networking and Mobile Computing (WiCom)

作者： Jianjun Niu Zhidong Deng Fengguang Zhou Zongsheng Cao Zhanqing Liu Fangzhou Zhu State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory of Information Science and Technology Department of Computer Science and Technology Tsinghua University China Beijing Special Engineering Design and Research Institute China

Wireless sensor network (WSN) based structural health monitoring (SHM) system attracts increasing interest in recent years. However, the restricted bandwidth, memory and energy pose great challenges to the application of SHM in large scale building. Supported by a real engineering project, a WSN based prototype of SHM system is designed in this paper. Acceleration data, synchronously sampled in each sensor node, are transported to a data processing computer through a base station. In order to achieve a high network throughput, a time division multiple access (TDMA) approach is proposed to reduce the packet collision and energy consumption. 17 sensor nodes, one base station and a processing computer are distributed to validate the prototype system. Test results present that the approach, we proposed, can reduce the signal collision and increase data throughput. The prototype is feasible to the SHM project of a large scale building.

关键词： Monitoring Wireless sensor networks Prototypes Large-scale systems Base stations Throughput Time division multiple access Bandwidth Application software Buildings

来源：评论

学校读者我要写书评

暂无评论

Equivalence Knowledge Cumularspharolith and Multiple Approximate Reasoning in R - Logic CR

Equivalence Knowledge Cumularspharolith and Multiple Approxi...

引用

computer science and information Engineering, CSIE, WRI World Congress on FLAGGED

作者： Yalin Zheng Guang Yang State Key Laboratory of Intelligent Technology and Systems Department of Automation Faculty of Information Science and Technology Tsinghua University Beijing China Research Center of Intelligent Information Technology Department of Computer Science and Technology Faculty of Software Dongguan University of Science and Technology Dongguan China

By casting off the direct restriction of topological structure, this paper presents another matching scheme between the input A * and the knowledge A rarr B based on the equivalence relation R on formulae set F(S) and the corresponding equivalence classification F(S)/R = { [A] R | A isin F(S)} therefore, obtains another algorithm of approximate reasoning - the IV-type R-algorithm. The paper presents the IV-type R-algorithm for the simple approximate reasoning model and the multiple approximate reasoning model in the frame of R-logic C R .

关键词： Logic Chromium computer science Intelligent structures Knowledge engineering information technology Laboratories Intelligent systems automation information science

来源：评论

学校读者我要写书评

暂无评论

Motion planning with obstacle avoidance for kinematically redundant manipulators based on two recurrent neural networks

Motion planning with obstacle avoidance for kinematically re...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Xiaolin Hu Jun Wang Bo Zhang Department of Computer Science and Technology Tsinghua University Beijing China State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Beijing China Department of Mechanical and Automation Engineering Chinese University of Hong Kong New Territories Hong Kong China

Inverse kinematic motion planning of redundant manipulators by using recurrent neural networks in the presence of obstacles and uncertainties is a real-time nonlinear optimization problem. To tackle this problem, two subproblems should be resolved in real time. One is the determination of critical points on a given manipulator closest to obstacles, and the other is the computation of joint velocities of the manipulator which can direct the manipulator following a desired trajectory and away from obstacles if it is getting close to them. Different from our previous approaches where the critical points on the manipulator were assumed to be known, these points are to be computed by using a recurrent neural network in the paper. A time-varying quadratic programming problem is formulated for avoiding polyhedral obstacles. In view that the problem is not strictly convex, an existing recurrent neural network, general projection neural network, is applied for solving it. By introducing a velocity smoothing technique into our previous quadratic programming formulation of the joint velocity assignment problem, a recently developed recurrent neural network, improved dual neural network, is proposed to solve it, which features lower structural complexity compared with existing neural networks. Moreover, The effectiveness of the proposed neural networks is demonstrated by simulations on the Mitsubishi PA10-7C manipulator.

关键词： Recurrent neural networks Neural networks Quadratic programming Manipulators Laboratories Kinematics Smoothing methods Paper technology information science Technology planning

来源：评论

学校读者我要写书评

暂无评论

Approximate Knowledge Mass and Extended automation Reasoning System in Type II Topological Logic

Approximate Knowledge Mass and Extended Automation Reasoning...

引用

International Conference on Fuzzy systems and Knowledge Discovery (FSKD)

作者： Yalin Zheng Guang Yang Jing Zheng Peican Huang State Key Laboratory for Intelligent Technology and Systems Department of Automation Faculty of Information Science and Technology Tsinghua University Beijing China Research Center of Intelligent Information Technology Department of Computer Science and Technology Faculty of Software Dongguan University of Science and Technology Dongguan China Research Center of Dongguan Economy Department of Economy and Commerce Dongguan University of Science and Technology Dongguan China Research Center of Intelligent Information Technology Department of Computer Science and Technology Faculty of Software Dongguan University of Science and Technology Dongguan China

This paper introduces and investigate the type II true level k knowledge circle, extended type II knowledge base, extended type II automatic reasoning system and the level (k,j) perfectness of extended type II knowled... 详细信息

关键词： automation Automatic logic units Fuzzy logic Fuzzy systems information technology computer science Laboratories Intelligent systems information science Business

来源：评论

学校读者我要写书评

暂无评论

Enhanced Biologically Inspired Model

Enhanced Biologically Inspired Model

引用

26th IEEE Conference on computer Vision and Pattern Recognition (CVPR 2008), vol.7

作者： Yongzhen Huang Kaiqi Huang Liangsheng Wang Dacheng Tao Tieniu Tan Xuelong Li National Laboratory of Pattern Recognition Institute of Automation Chinese Academy and Sciences Beijing China Biometrics Research Centre Department of Computing Hong Kong Polytechnic University Hong Kong China School of Computer Science and Information Systems Birkbeck University of London London UK

It has been demonstrated by Serre et al. that the biologically inspired model (BIM) is effective for object recognition. It outperforms many state-of-the-art methods in challenging databases. However, BIM has the following three problems: a very heavy computational cost due to dense input, a disputable pooling operation in modeling relations of the visual cortex, and blind feature selection in a feedforward framework. To solve these problems, we develop an enhanced BIM (EBIM), which removes uninformative input by imposing sparsity constraints, utilizes a novel local weighted pooling operation with stronger physiological motivations, and applies a feedback procedure that selects effective features for combination. Empirical studies on the CalTech5 database and CalTech101 database show that EBIM is more effective and efficient than BIM. We also apply EBIM to the MIT-CBCL street scene database to show it achieves comparable performance in comparison with the current best performance. Moreover, the new system can process images with resolution 128 × 128 at a rate of 50 frames per second and enhances the speed 20 times at least in comparison with BIM in common applications.

关键词： Biological system modeling Spatial databases Image databases Brain modeling Object recognition Visual databases Computational efficiency Feedforward systems Feedback Layout

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：