检索结果-内蒙古大学图书馆

World Congress on Intelligent Control and Automation (WCICA)

作者： Yuan Quan Lu Yuchang State Key Lab. of Intelligent Technol. & Syst. Tsinghua Univ. Beijing China The State Key Laboratory of Intelligent Technology and System Tsinghua University Beijing China

The traditional method based on aerodynamics and expertise for weather forecast focuses on present data, but the historical database is not utilized. The paper presents research on weather forecasting through the historical database. Because the atmosphere pattern is a complex, nonlinear system, the traditional method is not an effective method. The multi-layer neural network is a potent method for resolving this problem. With the backpropagation neural networks the atmosphere pattern is divided into five patterns based on the rainfall. Comments on this method and a special atmosphere pattern are given at the end of the paper.

关键词： Weather forecasting Neural networks Atmosphere laboratories Intelligent systems Deductive databases Computer science Aerodynamics technology forecasting Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Heterogeneous Mechanism for Hyper-Distributed Hyper-Parallel Al Processing

引用

Journal of Computer Science & technology 1999年第3期14卷 234-241页

作者：帅典勋 Department of Computer Science East-China University of Science and Technology Shanghai P.R. China State Key Laboratory of Intelligence and System Tsinghua University Beijing P.R. China

This paper proposes an asynchronous heterogeneous propagation approach of concurrent competitive waves for hyper-distributed hyper-parallel heuris tic problem-solving. This approach is much more powerful than the synchronous homogeneous mechanisms and the asynchronous superimposition algorithms, and has universal validity and availability. The basic conception, concurrent algorithm and its properties are discussed. The theory and conclusions drawn in this paper are of essential importance for the hardware implementation of hyper-distributed hyper-parallel processing based on chaotic cellular networks.

关键词： asynchronous heterogeneous competitive waves hyper-distributed hyper-parallel processing concurrent algorithm heuristic search implicit AND/OR graph

来源：评论

学校读者我要写书评

暂无评论

A new distinguishing algorithm of connected character image based on Fourier transform 5

A new distinguishing algorithm of connected character image ...

引用

5th International Conference on Document Analysis and Recognition, ICDAR 1999

作者： Zhu, Xiaoyan Shi, Yifan Wang, Song State Key Lab of Intelligent Technology and System Department of Computer Science and Technology Tsinghua University China

ISBN: (纸本)0769503187

Segmentation is the most difficult problem in a handwritten character recognition system and often contributes major errors to its performance. To reach a balance of speed and accuracy, a filter distinguishing a connected image from an isolated image is required for multi-stage segmentation. The Fourier spectrum is promising in this problem. Since it is influenced by the stroke width, we propose a Fourier spectrum standardization method. Based on the standardized Fourier spectrum, a set of features and a fine-tuned criterion are presented to classify connected/isolated images. A theoretical analysis proves their rationality. Experimental results demonstrate that this criterion is better than other methods. © 1999 IEEE.

关键词： Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Neural network based classifiers for a vast amount of data 3rd

Neural network based classifiers for a vast amount of data

引用

3rd Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 1999

作者： Zhang, Ling Zhang, Bo State Key Lab of Intelligent Technology and Systems Artificial Intelligence Institute Anhui University Anhui China State Key Lab of Intelligent Technology and Systems Dept. of Computer Science Tsinghua University Beijing China

ISBN: (纸本)3540658661

When using neural networks to train a large number of data for classification, there generally exists a learning complexity problem. In this paper, a new geometrical interpretation of McCulloch-Pitts (M-P) neural model is presented. Based on the interpretation, a new constructive learning approach is discussed. Experimental results show that the new algorithm can greatly reduce the learning complexity and can be applied to real classification problems with a vast amount of data. © Springer-Verlag Berlin Heidelberg 1999.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Concurrent Competitive Wave Approach toHyper-Distributed Hyper-Parallel AIProcessing

引用

Journal of Computer Science & technology 1997年第6期12卷 543-554页

作者：帅典勋 Department of Computer Science East China University of Science and Technology Shanghai State Key Laboratory of Intelligence Technology and System Tsinghua University Beijing

This paper preseflts a new approach of the synchronous homogeneous concurrent propagation of competitive waves for the purpose of hyper-distributed hyper-parallel heuristic problem-solving. The concurrent algorithm, mechanism and their properties are given. In comparison with the traditional AI algorithms, the approach is featured by the knowledge-based problem-solving in the distributed parallel environment, the feasibility for hardware implementation and the various applications.

关键词： Hyper-distributed hyper-parallel processing synchronous homogeneous competitive wave heuristic search implicit AND/OR graph concurrent algorithm

来源：评论

学校读者我要写书评

暂无评论

Hyper-Distributed Hyper-Parallel Implementation of Heuristic Search ofImplicit AND/OR Graph

引用

Journal of Computer Science & technology 1997年第6期12卷 532-542页

作者：帅典勋 Department of Computer Science East China University of Science and Technology Shanghai State Key Laboratory of Intelligence Technology and System Tsinghua University Beijing

This paper presents the hierarchic chaotic cellular networks for the hardware implementation of hyper-distributed hyper-parallel intelligent problem solving based on competitive wave propagation. By using the bifurcation and the synchronization of distributed chaotic dynamic systems, and by improving the Chua's circuit, the mechanism and the algorithms of heuristic search of an implicit AND/OR graph are realized in a hyper-distributed hyper-parallel environment. This paper's approach has many advantages in comparison with other traditional systolic structures based on symbolic logic algorithms.

关键词： Chaos Chua's circuit synchronization bifurcation heuristic search Petri network

来源：评论

学校读者我要写书评

暂无评论

Application of new genetic strategy to dynamic control of a mobile robot

Application of new genetic strategy to dynamic control of a ...

引用

IEEE International Conference on Intelligent Processing systems, ICIPS

作者： Meng Qing Chun Jia Peifa Ji Hongbo Dong Hao Hu Yane State Key Laboratory of Intelligence Technology & System Tsinghua University China Department of Computer Yantai University Yantai China Department of Computer Science Tsinghua University Beijing China

ISBN: (纸本)0780342534

A new genetic strategy, called a 'genetic algorithm with symmetric code', and its application to robot dynamic optimal control are introduced. This strategy is developed from symmetric code theory. According to the property of a mobile robot's dynamic model, symmetric codes are introduced into the genetic strategy. Two theorems are presented which offer sufficient and necessary conditions for satisfying the final conditions of linear and angular velocities. The problem of trajectory planning of the robot with the existence of obstacles is expressed in the form of an optimal control problem with constraints. The minimum energy used by the robot is taken as the criterion. Included are comparisons of different crossover and encoding techniques. In the four phases of simulation, the new genetic strategy shows itself to be efficient and capable for the trajectory planning of mobile robots and to be more powerful than classical genetic techniques.

关键词： Mobile robots Orbital robotics Genetic algorithms Optimal control Path planning Application software Robot control Control systems Iterative algorithms Constraint optimization

来源：评论

学校读者我要写书评

暂无评论

A rough set approach for planner evaluation

A rough set approach for planner evaluation

引用

IEEE International Conference on systems, Man and Cybernetics

作者： B.K. Sy Wang Jiaxin Pattern Analysis and Machine Intelligence Group System Design Engineering Department University of Waterloo Waterloo ONT Canada Department of Computer Science CUNY Flushing NY USA The State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China

This paper discusses a rough set approach for evaluating solutions of scheduling problems. Algorithms for solving scheduling problems are planners and the scheduling problems are modelled as constraint satisfaction problems. Conventional approach for the analysis of algorithms often focuses on the time and representational complexities, and assumes an identical cost on all operations. The proposed rough set approach augments conventional approaches for the analysis of algorithms in two ways: 1) it permits the consideration of different costs arising from different operations; and 2) it allows one to define a new utility for a complexity analysis.

关键词： Algorithm design and analysis Processor scheduling Set theory Machine intelligence Computer science Costs Search problems Educational institutions Pattern analysis system analysis and design

来源：评论

学校读者我要写书评

暂无评论

Multiple experts recognition system based on neural network

Multiple experts recognition system based on neural network

引用

13th International Conference on Pattern Recognition, ICPR 1996

作者： Wang, Song Zhu, Xiaoyan Jin, Yijiang Key National Lab. of Artificial Intelligence Technology and System Department of Computer Science and Technology Tsinghua University Beijing 100084 China

ISBN: (纸本)081867282X

For numeral recognition, when a single classifier cannot provide a decision which is 100 percent correct, multiple classifier should be able to achieve higher accuracy. This is because group decisions are generally better than any individual's. In this paper, as evidence, the differences between a ANN classifier and a traditional classifier are discussed. Based on this concept combination methods were developed, which can aggregate the decisions obtained from individual, derive the best final decisions. But different combination methods lead to different performance: accuracy, efficiency and so on. A ANN combining algorithm is developed. The authors analyze it and a voting algorithm within experiments. First experiments on 10000 samples of handwritten numerals have powerfully shown that the results of two different individual classifiers with same features are disparate in performance. Second experiment have discussed two disparate combination methods in contrast. © 1996 IEEE.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

EnIter: Enhancing Iterative Multi-View Depth Estimation with Universal Contextual Hints

引用

ACM Transactions on Multimedia Computing, Communications, and Applications 1000年

作者： Qianqian Du Hui Yin Lang Nie Yanting Liu Jin Wan State Key Laboratory of Advanced Rail Autonomous Operation Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence Beijing Jiaotong University Beijing China State Key Laboratory of Advanced Rail Autonomous Operation Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence Frontiers Science Center for Smart High-speed Railway System Beijing Jiaotong University Beijing China School of Computer Science and Technology Beijing Jiaotong University Beijing China Key Laboratory of Beijing for Railway Engineering School of Computer Science and Technology Beijing Jiaotong University Beijing China Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan) Qilu University of Technology Shandong Academy of Sciences) Jinan China

Iterative inference approaches have shown promising success in the task of multi-view depth estimation. However, these methods put excessive emphasis on the universal inter-view correspondences while neglecting the correspondence ambiguity in regions of low texture and depth discontinuous areas. Thus, they are prone to produce inaccurate or even erroneous depth estimations, which is further exacerbated cumulative errors especially in the iterative pipeline, providing unreliable information in many real-world scenarios. In this paper, we revisit this issue from the intra-view Contextual Hints and introduce a novel enhancing iterative approach, named EnIter. Concretely, at the beginning of each iteration, we present a Depth Intercept (DI) modulator to provide more accurate depth by aggregating neighbor uncertainty, correlation volume of reference and normal. This plug and play modulator is effective at intercepting the erroneous depth estimations with implicit guidance from the universal correlation contextual hints, especially for the challenging regions. Furthermore, at the end of each iteration, we refine the depth map with another plug and play modulator termed as Depth Refine (DR). It mines the latent structure knowledge of reference Contextual Hints and establishes one-way dependency using local attention from reference features to depth, yielding delicate depth in details. Extensive experiment demonstrates that our method not only achieves state-of-the-art performance over existing models but also exhibits remarkable universality in popular iterative pipelines, e.g., CasMVS, UCSNet, TransMVS, UniMVS.

关键词： Depth estimation Contextual hints Iterative inference Cumulative errors

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：