检索结果-内蒙古大学图书馆

THE RESEARCH OF RAINFALL PREDICTION MODELS BASED ON MATLAB NEURAL NETWORK

THE RESEARCH OF RAINFALL PREDICTION MODELS BASED ON MATLAB N...

2011 IEEE International Conference on Cloud Computing and Intelligence Systems(2011年第一届IEEE云计算与智能系统国际会议 IEEE CCIS2011)

作者： Guang Liu Xianggen Gan Lihong Chen Dongbao Yang Jiangxi Vocational &Technical College of Information Application Nanchang China Nanchang Meteorological Bureau Nanchang China Xinyu Meteorological Bureau Xinyu China

The continuously cloudy or rainy forecast is an important basis that is used to make choice of wheat harvest time but multiple regression weather forecast models hardly content the rate of required accuracy. Matlab neural network toolbox is composed of a series of typical neural network activation functions that make computing network output into calling activation functions. BP artificial neural network that is based on Matlab platform and utilizes error back propagation algorithm to revise network weight has dynamic frame characteristics and is convenient for constructing network and programming. After it has been trained by input forecast samples, network forecast model that has three neural cells possesses very good generalization capability. After we contrast fitting rate and accuracy rate of network model with ones of regression model, network model has a distinct advantage over regression model.

关键词： forecast models BP network learning algorithm network training

来源：评论

学校读者我要写书评

暂无评论

Influences of Perturbation of training Pattern Pairs on Morphological Bidirectional Associative Memories

Influences of Perturbation of training Pattern Pairs on Morp...

引用

2011 Fourth International Conference on Intelligent Computation Technology and Automation(2011年第四届智能计算技术与自动化国际会议 ICICTA 2011)

作者： Chunmei He School of Information Engineering East China Jiaotong University Nanchang 330013 China

ISBN: (纸本)9781612842899

An important Issue in design and implementation a neural network is that perturbations of training pattern pairs may cause some disadvantages to outputs. How the perturbations of training pattern pairs in Morphological Bidirectional Associative Memories (MBAMs) influence on the outputs is discussed in this paper. We define the outputs' max error to evaluate the robustness of the MBAMs. The related theorem and example show that the MBAMs have good robustness on the perturbation of training pattern pairs. This is of important sense in MBAMs' practical applications, such as analysis of the networks' performances, selection or establishment of the learning algorithms and acquisition the training pattern pairs.

关键词： Neural network Morphology Bidirectional associative memories(MBAMs) Perturbation learning algorithm Training pattern pairs Robustness

来源：评论

学校读者我要写书评

暂无评论

Hysteretic Neural Network and its Applications in Associative Memory

Hysteretic Neural Network and its Applications in Associativ...

引用

2011 2nd Asia-Pacific Conference on Wearable Computing Systems

作者： Liu Wei Lu Lifen School of Mechanical and Electronic Engineering Tianjin Polytechnic University School of Electrical Engineering and Automation Tianjin Polytechnic University

A hysteretic neural network is proposed based on the associative memory principle of Hopfield neural network. The hysteretic character make the neurons in the hysteretic neural network have better holding property to the original states, which decreases the possibility of changing the states mistakenly, and enhances the accuracy and the successful rate of associative memory. Furthermore, a learning algorithm for multi-values patterns associative memory is proposed based Hebb rules. The weight matrix is designed dynamically according to the sample patterns and input pattern. Using the learning algorithm, the hysteretic neural network can realize any multi-values patterns associative memory. The simulation results prove the validity of the algorithm.

关键词： hysteresis neural network associative memory learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A learning algorithm for metasearching using rough set theory

A learning algorithm for metasearching using rough set theor...

引用

International Conference on Computer and Information Technology (ICCIT)

作者： Rashid Ali M. M. Sufyan Beg Department of Computer Engineering Aligarh Muslim University Aligarh India Department of Computer Engineering JMI New Delhi India

ISBN: (纸本)1424415500

Metasearching is the process of combining search results of different search systems into a single set of ranked results, which is expected to be better than results of best of the participating search systems. In this paper, we present a supervised learning algorithm for metasearching. Our algorithm learns the ranking rules on the basis of user feedback based metasearching for the queries in the training set. We use rough set theory to mine the ranking rules. The ranking rules are validated using cross validation. The best of the ranking rules is then used to estimate the results of metasearching for the other queries. We compare our method with modified Shimura technique. We claim that our method is more useful than modified Shimura technique as it models userpsilas preference.

关键词： Metasearching learning algorithm Rough set User feedback

来源：评论

学校读者我要写书评

暂无评论

Dimension Reduction by Manifold learning for Evolutionary learning with Redundant Sensory Inputs

Dimension Reduction by Manifold Learning for Evolutionary Le...

引用

2010 IEEE World Congress on Computational Intelligence

作者： Handa, Hisashi Kawakami, Hiroshi Okayama Univ Grad Sch Nat Sci & Technol Okayama 7008530 Japan Kyoto Univ Grad Sch Informat Kyoto 6068530 Japan

ISBN: (纸本)9781424481262

The optimization of the number and the alignment of sensors is quite important task for designing intelligent agents/robotics. Even though we could use excellent learning algorithms, it will not work well if the alignment of sensors is wrong or the number of sensors is not enough. In addition, if a large number of sensors are available, it will cause the delay of learning. In this paper, we propose the use of Manifold learning for Evolutionary learning with redundant sensory inputs in order to avoid the difficulty of designing the allocation of sensors. The proposed method is composed of two stages: The first stage is to generate a mapping from higher dimensional sensory inputs to lower dimensional space, by using Manifold learning. The second stage is using Evolutionary learning to learn control scheme. The input data for Evolutionary learning is generated by translating sensory inputs into lower dimensional data by using the mapping.

关键词： dimension reduction evolutionary computation evolutionary learning higher dimensional sensory input mapping intelligent robotics intelligent robots learning (artificial intelligence) learning algorithm manifold learning number optimization optimisation redundant sensory input sensor allocation sensor placement sensors sensors alignment sensory input translation

来源：评论

学校读者我要写书评

暂无评论

Power Entangling and Matching in Cognitive Wireless Mesh Networks by Applying Conjecture Based Multi-agent QQ-learning Approach

Power Entangling and Matching in Cognitive Wireless Mesh Net...

引用

Globecom Workshops

作者： Chen, Xianfu Zhao, Zhifeng Zhang, Honggang Zhejiang Univ York Zhejiang Lab Cognit Radio & Green Commun Hangzhou 310027 Peoples R China

ISBN: (纸本)9781424488650

As the scarce spectrum resource is becoming overcrowded, cognitive wireless mesh networks express great flexibility to improve the spectrum utilization by opportunistically accessing the authorized frequency bands. One of the critical challenges for realizing such networks is how to adaptively match transmit powers and allocate frequency resources among secondary users (SUs) of the licensed frequency bands whilst maintaining the Quality-of-Service (QoS) requirement of the primary users (PUs), even in mutually entangled interference environment. In this paper, we discuss the non-cooperative power allocation matching problem in cognitive wireless mesh networks formed by a number of clusters with the consideration of energy efficiency. Due to the secondary users' selfish and spontaneous features, the problem is modeled as a stochastic learning process. We extend the conventional single-agent Q-learning to a multi-user context, coined as QQ-learning, using the framework of stochastic games. Within the multi-agent QQ-learning processes, a learning SU performs Q-function updates based on the conjecture about the other SUs' behaviors. This learning algorithm provably converges given certain restrictions that arise during learning procedure. Numerical experiments are used to verify the performance of our algorithm and demonstrate its effectiveness of improving the energy efficiency.

关键词： Q-function updates cognitive radio cognitive wireless mesh networks energy efficiency frequency bands learning (artificial intelligence) learning algorithm learning procedure multi-agent systems multiagent QQ-learning approach multiagent QQ-learning proce

来源：评论

学校读者我要写书评

暂无评论

Control chart pattern recognition using an optimized neural network and efficient features

引用

ISA TRANSACTIONS 2010年第3期49卷 387-393页

作者： Ebrahimzadeh, Ata Ranaee, Vahid Babol Univ Technol Fac Elect & Comp Engn Babol Sar *** Iran

Automatic recognition of abnormal patterns in control charts has seen increasing demands nowadays in manufacturing processes. This study investigates the design of an accurate system for control chart pattern (CCP) recognition from two aspects. First, an efficient system is introduced that includes two main modules: the feature extraction module and the classifier module. The feature extraction module uses the entropies of the wavelet packets. These are applied for the first time in this area. In the classifier module several neural networks, such as the multilayer perceptron and radial basis function, are investigated. Using an experimental study, we choose the best classifier in order to recognize the CCPs. Second, we propose a hybrid heuristic recognition system based on particle swarm optimization to improve the generalization performance of the classifier. The results obtained clearly confirm that further improvements in terms of recognition accuracy can be achieved by the proposed recognition system. (C) 2010 ISA. Published by Elsevier Ltd. All rights reserved.

关键词： Control chart pattern recognition Wavelet decomposition entropies Neural networks learning algorithm Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

algorithms for optimal dyadic decision trees

引用

MACHINE learning 2010年第1期80卷 85-107页

作者： Hush, Don Porter, Reid Los Alamos Natl Lab Grp ISR 2 Los Alamos NM 87545 USA

A dynamic programming algorithm for constructing optimal dyadic decision trees was recently introduced, analyzed, and shown to be very effective for low dimensional data sets. This paper enhances and extends this algorithm by: introducing an adaptive grid search for the regularization parameter that guarantees optimal solutions for all relevant trees sizes, replacing the dynamic programming algorithm with a memoized recursive algorithm whose run time is substantially smaller for most regularization parameter values on the grid, and incorporating new data structures and data pre-processing steps that provide significant run time enhancement in practice.

关键词： Decision tree Classification learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Prediction of the hot deformation behavior for Aermet100 steel using an artificial neural network

引用

COMPUTATIONAL MATERIALS SCIENCE 2010年第3期48卷 626-632页

作者： Ji, Guoliang Li, Fuguo Li, Qinghua Li, Huiqu Li, Zhi Henan Polytech Univ Sch Mat Sci & Engn Jiaozuo 454000 Peoples R China Northwestern Polytech Univ Sch Mat Sci & Engn Xian 710072 Peoples R China Beijing Inst Aeronaut Mat Beijing 100095 Peoples R China

Using the experimental data obtained from hot compression tests in the temperature range 800-1200 degrees C, strain range 0.05-0.90, and strain rate range 0.01-50 s(-1), an artificial neural network (ANN) model is developed to predict the hot deformation behavior of the ultrahigh strength steel of Aermet100. The inputs of the neural network are strain, strain rate and temperature, whereas flow stress is the output. The developed feed-forward back-propagation ANN model is trained with Levenberg-Marquardt learning algorithm. The performance of the ANN model is evaluated using a wide variety of standard statistical indices. Results show that the ANN model can efficiently and accurately predict hot deformation behavior of Aermet100. Finally the extrapolation ability and noise sensitivity of the ANN model are also investigated. It is found that the extrapolation ability is very high in the proximity of the training domain, and the noise tolerance ability very robust. (C) 2010 Elsevier B.V. All rights reserved.

关键词： Aermet100 steel Hot deformation Artificial neural network learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Evaluation of fuzzy regression models by fuzzy neural network

引用

JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS 2010年第3期234卷 825-834页

作者： Mosleh, M. Otadi, M. Abbasbandy, S. Islamic Azad Univ Dept Math Firuozkooh Branch Firuozkooh Iran Islamic Azad Univ Dept Math Sci & Res Branch Tehran 14515775 Iran

In this paper, a novel hybrid method based on fuzzy neural network for approximate fuzzy coefficients (parameters) of fuzzy linear and nonlinear regression models with fuzzy output and crisp inputs, is presented. Here a neural network is considered as a part of a large field called neural computing or soft computing. Moreover, in order to find the approximate parameters, a simple algorithm from the cost function of the fuzzy neural network is proposed. Finally, we illustrate our approach by some numerical examples. (C) 2010 Elsevier B.V. All rights reserved.

关键词： Fuzzy neural networks Fuzzy regression model Fuzzy number Feedforward neural network learning algorithm

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：