检索结果-内蒙古大学图书馆

International Joint conference on Neural Networks (IJCNN'99)

作者： Pasika, Hugh Haykin, Simon Clothiaux, Eugene Stewart, Ron McMaster Univ Hamilton Ont Canada

Cloud base height is a continuous variable that falls within the range of zero to fourteen kilometers and is useful for understanding the earth's radiation budget. Recent advances in LIDAR (laser radar) technology have provided accurate cloud base height measurements. However, new sensor development and deployment are costly processes. This paper is motivated by a desire to make LIDAR output of cloud base height information available at a network of ground based meteorological stations without actually installing LIDAR sensors. To accomplish this, fifty-seven sensors ranging from multispectral satellite information to standard atmospheric measurements such as temperature and humidity, are fused in what can only be termed as a very complex, non-linear environment. The result is an accurate prediction of cloud base height. Thus, a virtual sensor is created. This fusion is performed via neural network architectures. More specifically the choices of learning algorithms reflect the state-of-the-art in neural network design and include;as local methods, the regularized Radial Basis Function (RBF) network and the Support Vector Machine (SVM). Global methods include the Node Decoupled Extended Kalman Filter trained multi-layer perception (NDEKF-MLP), and as a benchmark, the venerable backpropagation algorithm. Overall, the support vector machine has shown itself to be the method of choice especially when complexity was considered. Excessive storage requirements occurred in the RBF case and the global methods required large committee machines to overcome the effects of local minima.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

General software design for multisensor data fusion

General software design for multisensor data fusion

引用

Proceedings of the 1999 sensor fusion: architectures, algorithms, and applications III

作者： Junliang, Zhang Yuming, Zhao 54th Research Inst of Electronic Industry Shijiazhuang China

In this paper a general method of software design for multisensor data fusion is discussed in detail, which adopts object-oriented technology under UNIX operation system. The software for multisensor data fusion is divided into six functional modules: data collection, database management, GIS, target display and alarming data simulation etc. Furthermore, the primary function, the components and some realization methods of each modular is given. The interfaces among these functional modular relations are discussed. The data exchange among each functional modular is performed by interprocess communication IPC, including message queue, semaphore and shared memory. Thus, each functional modular is executed independently, which reduces the dependence among functional modules and helps software programming and testing. This software for multisensor data fusion is designed as hierarchical structure by the inheritance character of classes. Each functional modular is abstracted and encapsulated through class structure, which avoids software redundancy and enhances readability.

关键词： Computer software

来源：评论

学校读者我要写书评

暂无评论

Bio-fusion for intelligent system control

Bio-fusion for intelligent system control

引用

Proceedings of the 1999 sensor fusion: architectures, algorithms, and applications III

作者： Norseen, John D. Kropotov, Juri D. Kremen, Inna Z. Lockheed Martin Aeronautical Co

We present a realistic neural network - the canonical cortical module - built on basic principles of cortical organization. These principles are: opponent cells principle, assembly principle, canonical cortical circuit principle and modular principle. When applied to visual images, the network explains orientational and spatial frequency filtering functions of neurons in the striate cortex. Two patterns of joint distribution of opponent cells in the inhibitory cortical layer are presented: pinwheel and circular. These two patterns provide two Gestalt descriptions of local (within the frames of one module) visual image: circle-ness and cross-ness. These modules were shown to have a power for shape detection and texture discrimination. They also provide an enhancement of signal-to-noise ratio of input images. Being modality independent, the canonical cortical module seems to be good tool for bio-fusion for intelligent system control.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

What is conditional event algebra and why should you care?

What is conditional event algebra and why should you care?

引用

conference on Signal Processing, sensor fusion, and Target Recognition VIII

作者： Goodman, IR Mahler, RPS Nguyen, HT SPAWAR Syst Ctr San Diego CA USA

ISBN: (纸本)081943194X

Building practical intelligent-system algorithms requires appropriate tools for capturing the basic features of highly complex real-world environments. One of the most important of these tools, probability theory, is a calculus of events (e.g. EVENT = 'A fire-control radar of type A is detected' with Prob(EVENT) = 0.80). Conditional Event Algebra (CEA) is a relatively new inference calculus which rigorously extends standard probability theory to include events which are contingent-e.g. rules such as 'If fire-control radar A is detected, then weapon B will be launched';or conditionals such as 'observation Z given target state X.' CEA allows one to (1) probabilistically model a contingent event;(2) assign a probability Prob(COND_EVENT) = 0.50 to it;and (3) compute with such conditional events and probabilities using the same basic rules that govern ordinary events and probabilities. Since CEA is only about ten years old, it has achieved visibility primarily among specialists in expert-systems theory and mathematical logic. Recently, however, it has become clear that CEA has potentially radical implications for engineering practice as well. The purpose of this paper is to bring this promising new tool to the attention of the wider engineering community. We will give a tutorial introduction to CEA, based on simple motivational examples, and describe its potential applications in a number of practical engineering problems.

关键词： data fusion intelligent systems probabilistic systems conditional events

来源：评论

学校读者我要写书评

暂无评论

Intelligent fusion control throughout varying thermal regions

Intelligent fusion control throughout varying thermal region...

引用

Proceedings of the 1999 IEEE Industry applications conference - 34th IAS Annual Meeting

作者： Hartman, D.A. DeLapp, D.R. Cook, G.E. Barnett, R.J. Los Alamos Natl Lab Los Alamos United States

An intelligent monitoring and control system is presented that regulates the total heat input in order to maintain constant fusion zone geometry under varying thermal regions. The integrity and quality of the final fused joint rely heavily on the geometrical properties of the fusion zone, in particular the width-to-depth ratio. Assessment of the joint geometry is performed using Rayleigh's suspended droplet analogy in which the mass, and hence the volume, of the droplet is related to the natural resonant frequency of the molten region. A non-intrusive, non-contact, top-side sensor collects the arc light reflected from the oscillations of the molten metal's surface. An improved approach for inducing and monitoring the oscillations of a molten weld pool is presented. A software-based phase-locked loop (PLL) technique enables synchronized excitation of the molten pool. Improved locking and tracking characteristics in the presence of noise, signal distortions, and harmonic conditions are achieved through the use of intelligent signal monitoring algorithms which co-exist in parallel and cooperate with the PLL. Dynamic reconfiguration of the PLL's digital filter coefficients allows superior tracking performance over a wide range of resonant frequency conditions. A fuzzy logic rule set, modeled after expert human welding knowledge, regulates the total heat input to the fusion process in order to demonstrate this unique synchronous excitation, monitoring, and control technique. A detailed discussion regarding each component's contribution to the overall system is provided. Finally, an in-depth comparison between various open- and closed-loop experiments of the joining process is discussed.

关键词： Intelligent control

来源：评论

学校读者我要写书评

暂无评论

A review of high-level multisensor fusion: approaches and applications

A review of high-level multisensor fusion: approaches and ap...

引用

International conference on Multisensor fusion and Integration for Intelligent Systems (MFI)

作者： R.C. Luo K.L. Su Intelligent Automation Laboratory Department of Electrical Engineering National Chung Cheng University Chiayi Taiwan

The potential advantages in multisensor fusion can be obtained more accurately, concerning feature that are impossible to perceive with individual sensors, as well as in less time, and at a lower cost. The characterization most commonly encountered in the rapidly growing multisensor fusion literature based on levels of detail in the information is that of the now well known triple low level (data level), medium level (feature level) and high level (decision level). The development of high-level multisensor fusion representations is very important, in the construction of advanced intelligent systems. The paper begins with a review on the fundamental principles about high-level multisensor fusion, together with some of the applications. Finally, we compare the decision algorithms in the high-level multisensor fusion.

关键词： sensor fusion Inference algorithms Intelligent sensors Bayesian methods Humans Intelligent systems sensor systems Automation Laboratories sensor phenomena and characterization

来源：评论

学校读者我要写书评

暂无评论

Review of high-level multisensor fusion: Approaches and applications

IEEE International Conference on Multisensor Fusion and Inte...

引用

IEEE International conference on Multisensor fusion and Integration for Intelligent Systems 1999年 25-31页

作者： Luo, Ren C. Su, Kuo L.

ISBN: (纸本)0780358015

The need for intelligent systems that can be important in the future trends. It is impossibly arrived at the goal, but be combined with multi sensor fusion. The potential advantages in multisensor fusion can be obtained more accurately, concerning feature that are impossible to perceive with individual sensors, as well as in less time, and at a lesser cost. The characterization most commonly encountered in the rapidly growing multisensor fusion literature based on level of detail in the information is that of the now well known triple low level (data level), medium level (feature level) and high level (decision level). The development of high-level multisensor fusion representations is very important, in order to construct advanced intelligent systems. The paper begins with review on the fundamental principles about high-level multisensor fusion, and has been employed in some applications in the object. Finally, we compare with the decision algorithms each other in the high-level multisensor fusion.

关键词： sensor data fusion

来源：评论

学校读者我要写书评

暂无评论

On the order of processing sensors in sequential implementations of fusion algorithms

On the order of processing sensors in sequential implementat...

引用

American Control conference (ACC)

作者： L.Y. Pao L. Trailovic Department of Electrical and Computer Engineering University of Colorado Boulder USA

We examine the order of sensor processing in the sequential multisensor probabilistic data association (MSPDA) filter for target tracking applications. If two sensors of different qualities are used, simulations and a... 详细信息

关键词： sensor fusion Time measurement Target tracking Covariance matrix Gaussian noise Analytical models Additive noise Riccati equations Filters Application software

来源：评论

学校读者我要写书评

暂无评论

Neural networks for sensor fusion in remote sensing

Neural networks for sensor fusion in remote sensing

引用

International Joint conference on Neural Networks (IJCNN)

作者： H. Pasika S. Haykin E. Clothiaux R. Stewart McMaster University Hamilton ONT Canada Pennslyvania State University PA USA Environment Canada Downsview ONT Canada

Cloud base height is a continuous variable that falls within the range of zero to fourteen kilometers and is useful for understanding the Earth's radiation budget. Advances in LIDAR (laser radar) technology have provided accurate cloud base height measurements. However, new sensor development and deployment are costly processes. The paper is motivated by a desire to make LIDAR output of cloud base height information available at a network of ground based meteorological stations without actually installing LIDAR sensors. To accomplish this, fifty-seven sensors ranging from multispectral satellite information to standard atmospheric measurements such as temperature and humidity, are fused in what can only be termed as a very complex, non-linear environment. The result is an accurate prediction of cloud base height. Thus, a virtual sensor is created. This fusion is performed via neural network architectures. More specifically the choices of learning algorithms reflect the state-of-the-art in neural network design and include; as local methods, the regularized radial basis function (RBF) network and the support vector machine (SVM). Global methods include the node decoupled extended Kalman filter trained multi-layer perception (NDEKF-MLP), and as a benchmark, the venerable backpropagation algorithm. Overall, the support vector machine has shown itself to be the method of choice especially when complexity was considered, Excessive storage requirements occurred in the RBF case and the global methods required large committee machines to overcome the effects of local minima.

关键词： Neural networks sensor fusion Remote sensing Laser radar Clouds Support vector machines Temperature sensors Backpropagation algorithms Earth Laser fusion

来源：评论

学校读者我要写书评

暂无评论

Experiments in the control of perception in multi-sensor system

Experiments in the control of perception in multi-sensor sys...

引用

International conference on Multisensor fusion and Integration for Intelligent Systems (MFI)

作者： T. Celinski B. McCarragher Department of Engineering Faculty of Engineering and Information Technology Australian National University Canberra Australia

The paper presents a new approach to management of multiple sensors and perception algorithms in a multi-sensor robotic system. The approach involves real-time selection of process monitors by a sensory Perception Controller. The selection is based on the minimization of the expected cost of perception with constraints on the uncertainty of perception. The effectiveness and usefulness of the approach is evaluated through experiments involving a range of sensing modalities which may typically be encountered in robotic applications.

关键词： Control systems Intelligent sensors sensor systems Intelligent robots Robot sensing systems sensor phenomena and characterization sensor arrays Intelligent systems Information technology Technology management

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：