检索结果-内蒙古大学图书馆

Hierarchical neuro-fuzzy models based on reinforcement learning for intelligent agents

Hierarchical neuro-fuzzy models based on reinforcement learn...

8th International Workshop on Artificial Neural Networks, IWANN 2005: computational intelligence and Bioinspired Systems

作者： Figueiredo, Karla Vellasco, Marley Pacheco, Marco Aurélio Department of Electronic and Telecommunication Engineering UERJ Rua São Francisco Xavier 524 CEP 20550-900 Rio de Janeiro RJ Brazil Applied Computational Intelligence Lab Department of Electrical Engineering - PUC-Rio Rua Marques de São Vicente 225 Rio de Janeiro 22453-900 RJ Brazil Department of Computer and Systems Engineering - UERJ Brazil

This work introduces two new neuro-fuzzy systems for intelligent agents called Reinforcement Learning - Hierarchical Neuro-Fuzzy Systems BSP (RL-HNFB) and Reinforcement Learning - Hierarchical Neuro-Fuzzy Systems Politree (RL-HNFP). By using hierarchical partitioning methods, together with the Reinforcement Learning (RL) methodology, a new class of Neuro-Fuzzy Systems (SNF) was obtained, which executes, in addition to automatically learning its structure, the autonomous learning of the actions to be taken by an agent. These characteristics have been developed in order to bypass the traditional drawbacks of neuro-fuzzy systems. The paper details the two novel RL_HNF systems and evaluates their performance in a benchmark application - the cart-centering problem. The results obtained demonstrate the capacity of the proposed models in extracting knowledge from the agent's direct interaction with large and/or continuous environments. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Determination of real options value by Monte Carlo simulation and fuzzy numbers

Determination of real options value by Monte Carlo simulatio...

引用

International Conference on Hybrid Intelligent Systems (HIS)

作者： J.G. Lazo Lazo M.M.B.R. Vellasco M.A.C. Pacheco ICA: Applied Computational Intelligence Laboratory Department of Electrical Engineering Pontifical Catholic University of Rio de Janeiro Rio de Janeiro Brazil

This work presents the development of a methodology based on Monte Carlo simulation, fuzzy numbers and in the real options theory to determine the real options value under technical and market uncertainties. The objective of the proposed methodology is to substantially reduce the computational time involved, facilitating the decision taking process. The methodology involves: fuzzy numbers, to represent certain types of uncertainties that does not have a known stochastic process that can correctly model them; stochastic processes to represent other uncertainties; and Monte Carlo simulation to generate a good approximation of the real option value. This methodology was evaluated in problems of expansion option in the area of oil exploration and production, attaining the same results provided by conventional techniques but with a significant reduction in the necessary computational time.

关键词： Uncertainty Stochastic processes Petroleum Investments computational intelligence Production Decision making Independent component analysis Laboratories Costs

来源：评论

学校读者我要写书评

暂无评论

A neural network based Wide Area Monitor for a power system

A neural network based Wide Area Monitor for a power system

引用

2005 IEEE Power engineering Society General Meeting

作者： Li, Xiaomeng Venayagamoorthy, Ganesh K. IEEE Real-Time Power and Intelligent Systems Laboratory University of Missouri Rolla MO 65409 United States Department of Electrical and Computer Engineering University of Missouri Rolla United States South African Institute of Electrical Engineers IEEE St. Louis Computational Intelligence Department of Task Force on Intelligent Control Systems Secretary of the Intelligent Systems Subcommittee IEEE Power Engineering Society

ISBN: (纸本)078039156X

With the deregulation of power industry, many tie lines between control areas are driven to operate near their maximum capacity, especially those serving heavy load centers. Wide area controllers (WACs) using wide-area or global signals can provide remote auxiliary control signals to local controllers such as automatic voltage regulators, power system stabilizers, etc to damp out inter-area oscillations. The power system is highly nonlinear system with fast changing dynamics. In order to have an efficient WAC, an online system monitor/predictor is required to provide inter-area information to the WAC from time to time. This paper presents the design of an online Wide Area Monitor (WAM) using a neural network called the Wide Area Neuroidentifier (WANI). The WANI is used to predict ahead the speed deviations of generators in the different areas using phasor measurement unit (PMU). Results are presented to show the effectiveness of the wide area monitor for different disturbances. © 2005 IEEE.

关键词： Wide area networks

来源：评论

学校读者我要写书评

暂无评论

A Portable Wireless DSP System for a Brain Machine Interface

A Portable Wireless DSP System for a Brain Machine Interface

引用

International IEEE/EMBS Conference on Neural engineering, CNE

作者： S. Darmanjian S. Morrison B. Dang K. Gugel J. Principe Computational Neuro Engineering Laboratory Applied Digital Design Laboratory Department of Electrical and Computer Engineering University of Florida Gainesville FL USA Texas Instrumenits Inc. Dallas TX USA Lockheed Martin IS&S San Jose CA USA Applied Digital Design Laboratory Department of Electrical and Computer Engineering University of Florida Gainesville FL USA Computational Neuro Engineering Laboratory Department of Electrical and Computer Engineering University of Florida Gainesville FL USA

In this paper, we present a design for a wearable DSP system that is capable of processing various neural-to-motor translation algorithms. The system first acquires the neural data through a high speed data bus in order to train and evaluate our prediction models. Then via a widely used protocol, the low-bandwidth output trajectory is wirelessly transmitted to a simulated robot arm. This system has been built and successfully tested with real data

关键词： Digital signal processing Hardware Trajectory Algorithm design and analysis Predictive models Robots Brain computer interfaces computer interfaces Wearable computers Laboratories

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE International Conference on Multi Topic

作者： Naeem Qaiser Mutawarra Hussain Nabeel Iqbal Amir Hussain Nadeem Qaiser Department of Computer and Information Sciences Pakistan Institute of Engineering and Applied Sciences Pakistan Centre for Advanced Studies in Engineering Islamabad Pakistan Computational Intelligence Research Group University of Stirling UK Department of Electrical Engineering Pakistan Institute of Engineering and Applied Sciences Pakistan

As observed from the literature survey, there is no commonly accepted quantitative definition of visual texture. As a consequence, researchers seeking a quantitative texture measure have been forced to search intuitively for texture features, and then attempt to evaluate their performance by different techniques. Dissimilarity analysis is one of the main requirements from the classifier design point of view and provides information of significant importance regarding feature extraction and selection strategies. This paper explores several texture features of historical and practical significance and presents their comprehensive dissimilarity analysis. An improved post processing scheme has also been proposed for Law's filter based feature extraction technique. Results, validated through dissimilarity measures, show a considerable improvement over existing scheme

关键词： Signal analysis Signal processing Gabor filters Feature extraction Image texture analysis Data mining Information analysis Image texture Microstructure Pixel

来源：评论

学校读者我要写书评

暂无评论

Network coding for wireless applications

Network coding for wireless applications

引用

Unmanned/Unattended Sensors and Sensor Networks II

作者： Lun, Desmond S. Ahmed, Ebad Brothers, L. Reggie DeBardelaben, James A. Effros, Michelle Ho, Tracey Karger, David Koetter, Ralf Lee, Anna MacMullan, Samuel J. Médard, Muriel Zhao, Fang Laboratory for Information and Decision Systems Massachusetts Institute of Technology Cambridge MA 02139 United States DARPA ATO 3701 N. Fairfax Dr. Arlington VA 22203 United States Johns Hopkins University Applied Physics Laboratory 11100 Johns Hopkins Rd. Laurel MD 20769 United States Data Compression Laboratory California Institute of Technology Pasadena CA 91125 United States Department of Electrical Engineering California Institute of Technology Pasadena CA 91125 United States Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge MA 02139 United States Coordinated Science Laboratory University of Illinois at Urbana-Champaign Urbana IL 61801 United States Lorenz Research Associates Inc. 4443 Brookfield Corporate Dr. Chantilly VA 20151 United States

The advent of network coding promises to change many aspects of networking. Network coding moves away from the classical approach of networking, which treats networks as akin to physical transportation systems. We overview some of the main features of network coding that are most relevant to wireless networks. In particular, we discuss the fact that random distributed network coding is asymptotically optimal for wireless networks with and without packet erasures. These results are extremely general and allow packet loss correlation, such as may occur in fading wireless channels. The coded network lends itself, for multicast connections, to a cost optimization which not only outperforms traditional routing tree-based approaches, but also lends itself to a distributed implementation and to a dynamic implementation when changing conditions, such as mobility, arise. We illustrate the performance of such optimization methods for energy efficiency in wireless networks and propose some new directions for research in the area.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Fast implementation of morphological operations using binary image block decomposition

引用

International Journal of Image and Graphics 2004年第2期4卷 183-202页

作者： Gatos, Basilios Perantonis, Stavros J. Papamarkos, Nikos Andreadis, Ioannis Computational Intelligence Laboratory Institute of Informatics and Telecommunications National Research Center Demokritos Athens153 10 Greece Department of Electrical and Computer Engineering Democritus University of Thrace Xanthi67 100 Greece

Morphological transformations are commonly used to perform a variety of image processing tasks. However, morphological operations are time-consuming procedures since they involve ordering and min/max computation of numbers resulting from image interaction with structuring elements. This paper presents a new method that can be used to speed up basic morphological operations for binary images. To achieve this, the binary images are first decomposed in a set of non-overlapping rectangular blocks of foreground pixels that have predefined maximum dimensions. Then off-line dilation and erosion of all rectangular blocks are arbitrary obtained and stored into suitable look-up array tables. By using the look up tables, the results of the morphological operations to the rectangular blocks are directly obtained. Thus, first all image blocks are replaced by their look-up array tables. Then the morphological operations are applied only to the limited number of the remaining pixels. Experimental results reveal that starting from a block represented binary image morphological operations can be executed with different types of structuring elements in significantly less CPU time. Using the block representation, we are able to perform dilation 16 times faster than non-fast implementations and 10 times faster than an alternative fast implementation based on contour processing. Significant acceleration is also recorded when using this approach for repeated application of dilation (for 10 iterations, dilation using the block representation is over 20 times faster than non-fast implementations and over four times faster than using the fast contour based approach). © 2004 World Scientific Publishing Company.

关键词： Binary images

来源：评论

学校读者我要写书评

暂无评论

Inference of genetic regulatory networks with recurrent neural network models

Inference of genetic regulatory networks with recurrent neur...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Rui Xu Xiao Hu D.C. Wunsch Applied Computational Intelligence Laboratory Department of Electrical and Computer Engineering University of Missouri Rolla Rolla MO USA

Large-scale gene expression data coming from microarray experiments provide us a new means to reveal fundamental cellular processes, investigate functions of genes, and understand relations and interactions among them. To infer genetic regulatory networks from these data with effective computational tools has become increasingly important Several mathematical models, including Boolean networks, Bayesian networks, dynamic Bayesian networks, and linear additive regulation models, have been used to explore the behaviors of regulatory networks. In this paper, we investigate the inference of genetic regulatory networks from time series gene expression in the framework of recurrent neural network model.

关键词： Genetics Recurrent neural networks Gene expression Bayesian methods computer networks Additives DNA Proteins Large-scale systems Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Time series prediction with recurrent neural networks using a hybrid PSO-EA algorithm

Time series prediction with recurrent neural networks using ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： X. Cai N. Zhang G.K. Venayagamoorthy D.C. Wunsch Applied Computational Intelligence Laboratory Department of Electrical and Computer Engineering University of Missouri Rolla Rolla MO USA

To predict the 100 missing values from the time series consisting of 5000 data given for the IJCNN 2004 time series prediction competition, we applied an architecture which automates the design of recurrent neural networks using a new evolutionary learning algorithm. This new evolutionary learning algorithm is based on a hybrid of particle swarm optimization (PSO) and evolutionary algorithm (EA). By combining the searching abilities of these two global optimization methods, the evolution of individuals is no longer restricted to be in the same generation, and better performed individuals may produce offspring to replace those with poor performance. The novel algorithm is then applied to the recurrent neural network for the time series prediction. The experimental results show that our approach gives good performance in predicting the missing values from the time series.

关键词： Recurrent neural networks Neurons Particle swarm optimization computer architecture Evolutionary computation Covariance matrix Genetic mutations computational intelligence Laboratories Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Quantum-inspired evolutionary algorithms and its application to numerical optimization problems

引用

11th International Conference on Neural Information Processing, ICONIP 2004

作者： Abs da Cruz, André V. Barbosa, Carlos R. Hall Pacheco, Marco Aurélio C. Vellasco, Marley ICA – Applied Computational Intelligence Lab Electrical Engineering Department Pontifícia Universidade Católica do Rio de Janeiro Brazil Department of Computer Science University College of London United Kingdom

ISBN: (纸本)3540239316

This work proposes a new kind of evolutionary algorithm inspired in the principles of quantum computing. This algorithm is an extension of a proposed model for combinatorial optimization problems which uses a binary representation for the chromosome. This extension uses probability distributions for each free variable of the problem, in order to simulate the superposition of solutions, which is intrinsic in the quantum computing methodology. A set of mathematical operations is used as implicit genetic operators over those probability distributions. The efficiency and the applicability of the algorithm are demonstrated through experimental results using the F6 function. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Probability distributions

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：