检索结果-内蒙古大学图书馆

APPLICATION OF NEURAL NETWORKS TO SIGNAL PREDICTION IN NUCLEAR-POWER-PLANT

IEEE TRANSACTIONS ON NUCLEAR SCIENCE 1993年第5期40卷 1337-1341页

作者： KIM, WJ CHANG, SH LEE, BH Department of Nuclear Engineering Korea Advanced Institute of Science and Technology Taejon South Korea

This paper describes the feasibility study of an artificial neural network for signal prediction. The purpose of signal prediction is to estimate the value of undetected next time step signal. As the prediction method, based on the idea of auto regression, a few previous signals are inputs to the artificial neural network and the signal value of next time step is estimated with the outputs of the network. The artificial neural network can be applied to the nonlinear system and answers in short time. The training algorithm is a modified backpropagation model, which can effectively reduce the training time. The target signal of the simulation is the steam generator water level, which is one of the important parameters in nuclear power plants. The simulation result shows that the predicted value follows the real trend well.

关键词： Neural networks Artificial neural networks Power generation Prediction methods Nonlinear systems backpropagation algorithms Power system modeling Nuclear power generation Signal generators Predictive models

来源：评论

学校读者我要写书评

暂无评论

A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction

引用

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS 1999年第1期29卷 62-72页

作者： Chen, CLP Wan, JZ Wright State Univ Dept Comp Sci & Engn Dayton OH 45435 USA USAF Wright Lab Mat Directorate MLIM Wright Patterson AFB OH 45433 USA Lexis Nexis Data Cent Dayton OH 45343 USA

A fast learning algorithm is proposed to find an optimal weights of the flat neural networks (especially, the functional-link network). Although the hat networks are used for nonlinear function approximation, they can be formulated as linear systems. Thus, the weights of the networks can be solved easily using a linear least-square method. This formulation makes it easier to update the weights instantly for both a new added pattern and a new added enhancement node. A dynamic stepwise updating algorithm is proposed to update the weights of the system on-the-fly. The model is tested on several time-series data including an infrared laser data set, a chaotic time-series, a monthly flour price data set, and a nonlinear system identification problem. The simulation results are compared to existing models in which more complex architectures and more costly training are needed. The results indicate that the proposed model is very attractive to real-time processes.

关键词： Heuristic algorithms Neural networks Radial basis function networks backpropagation algorithms Function approximation Linear systems Laser modes Chaos Nonlinear systems Equations

来源：评论

学校读者我要写书评

暂无评论

TONE RECOGNITION OF ISOLATED CANTONESE SYLLABLES

引用

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING 1995年第3期3卷 204-209页

作者： LEE, T CHING, PC CHAN, LW CHENG, YH MAK, B The Department of Electronic Engineering Chinese University of Hong Kong Sha Tin Hong Kong China Department of Computer science Chinese University of Hong Kong Hong Kong China Motorola Semiconductors Hong Kong Limited Hong Kong China

Tone identification is essential for the recognition of Chinese language, specifically for Cantonese which is well known of being very rich in tones. This paper presents an efficient method for tone recognition of isolated Cantonese syllables, Suprasegmental feature parameters are extracted from the voiced portion of a monosyllabic: utterance and a three-layer feedforward neural network is used to classify these feature vectors. Using a phonologically complete vocabulary of 234 distinct syllables, the recognition accuracy for single-speaker and multispeaker is given by 89.0% and 87.6% respectively.

关键词： Natural languages Neural networks Feature extraction Feedforward neural networks Speech recognition Multi-layer neural network Vocabulary backpropagation algorithms Neurons Computer science

来源：评论

学校读者我要写书评

暂无评论

A COMPUTER-SIMULATION STUDY OF DIFFRACTION TOMOGRAPHY

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 1983年第7期30卷 377-386页

作者： DEVANEY, AJ Schlumberger-Doll Research Center Ridgefield CT USA

The filtered backprojection algorithm of X-ray tomography and the filtered backpropagation algorithm developed recently by the author for diffraction tomography are tested in computer simulations of ultrasonic tomography of two-dimensional objects for which the Rytov approximation is valid. It is found that the filtered backprojection algorithm gives unsatisfactory results even for wavelengths much smaller than the smallest scale over which the object varies. The filtered back-propogation algorithm yields, in all cases studied, high-quality reconstructions which are simply low-pass filtered versions of the actual object profile. It is shown that the filtered backpropagation algorithm can be approximated by a modified backprojection algorithm having essentially the same computation requirements as filtered backprojection, but yielding considerably higher quality object reconstructions.

关键词： Computer simulation backpropagation algorithms X-ray diffraction Ultrasonic imaging X-ray tomography Low pass filters Image reconstruction Acoustic diffraction Reconstruction algorithms Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

OUT-OF-STEP PREDICTION BASED ON ARTIFICIAL NEURAL NETWORKS

引用

ELECTRIC POWER SYSTEMS RESEARCH 1995年第2期34卷 135-142页

作者： ABDELAZIZ, AY IRVING, MR ELARABATY, AM MANSOUR, MM Department of Electrical Power and Machines Ain Shams University Cairo Egypt Department of Electrical Engineering and Electronics Brunel University Uxbridge UB8 3PH UK

The application of artificial intelligence to power systems has resulted in an overall improvement of solutions in many generators based implementations. This paper presents a new approach to the prediction (detection) of out-of-step synchronous, on artificial neural networks (ANNs). The paper describes the ANN architecture adopted as well as the selection of input features for training the ANN. A feedforward model of the neural network based on the stochastic back-propagation training algorithm has been used. The capabilities of the developed algorithm for the prediction of the out-of-step condition have been tested through computer simulation for a typical case study. The results of using the proposed algorithm reveal a high classification performance.

关键词： SYNCHRONOUS GENERATOR STABILITY NEURAL NETWORKS backpropagation algorithms

来源：评论

学校读者我要写书评

暂无评论

TRAINING FEEDFORWARD NETWORKS WITH THE MARQUARDT ALGORITHM

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1994年第6期5卷 989-993页

作者： HAGAN, MT MENHAJ, MB

The Marquardt algorithm for nonlinear least squares is presented and is incorporated into the backpropagation algorithm for training feedforward neural networks. The algorithm is tested on several function approximation problems, and is compared with a conjugate gradient algorithm and a variable learning rate algorithm. It is found that the Marquardt algorithm is much more efficient than either of the-other techniques when the network contains no more than a few hundred weights.

关键词： backpropagation algorithms Least squares methods Neural networks Approximation algorithms Convergence Least squares approximation Feedforward neural networks Testing Function approximation Acceleration

来源：评论

学校读者我要写书评

暂无评论

A CONSTRUCTIVE ALGORITHM FOR BINARY NEURAL NETWORKS - THE OIL-SPOT ALGORITHM

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第3期6卷 794-797页

作者： MASCIOLI, FMF MARTINELLI, G INFO-COM Department University of Rome Rome Italy

This paper presents a constructive training algorithm for supervised neural networks. The algorithm relies on a topological approach, based on the representation of the mapping of interest onto the binary hypercube of the input space. It dynamically constructs a two-layer neural network by involving successively binary examples. A convenient treatment of real-valued data is possible by means of a suitable real-to-binary codification. In the case of target functions that have efficient halfspace union representations, simulations show that the constructed networks result optimized in terms of number of neurons.

关键词： Neural networks Hypercubes Neurons Computer architecture backpropagation algorithms Computational efficiency Graph theory Approximation algorithms NP-hard problem Smoothing methods

来源：评论

学校读者我要写书评

暂无评论

Feedforward networks training speed enhancement by optimal initialization of the synaptic coefficients

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 2001年第2期12卷 430-434页

作者： Yam, JYF Chow, TWS City Univ Hong Kong Dept Elect Engn Kowloon Hong Kong Peoples R China

This letter aims at determining the optimal bias and magnitude of initial weight vectors based on multidimensional geometry. This method ensures the outputs of neurons are in the active region and the range of the activation function is fully utilized. In this letter, very thorough simulations and comparative study were performed to validate the performance of the proposed method. The obtained results on five well-known benchmark problems demonstrate that the proposed method deliver consistent good results compared with other weight initialization methods.

关键词： Neurons Least squares methods Least squares approximation Piecewise linear techniques Multidimensional systems Geometry Neural networks Feedforward neural networks backpropagation algorithms Nonhomogeneous media

来源：评论

学校读者我要写书评

暂无评论

USE OF A QUASI-NEWTON METHOD IN A FEEDFORWARD NEURAL-NETWORK CONSTRUCTION ALGORITHM

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第1期6卷 273-277页

作者： SETIONO, R HUI, LCK Department of Information Systems and ComputerScience National University of Singapore Singapore

Interest in algorithms which dynamically construct neural networks has been growing in recent years. This paper describes an algorithm for constructing a single hidden layer feedforward neural network. A distinguishing feature of this algorithm is that it uses the quasi-Newton method to minimize the sequence of error functions associated with the growing network. Experimental results indicate that the algorithm if very efficient and robust. The algorithm was tested on two test problems. The first was the n-bit parity problem and the second was the breast cancer diagnosis problem from the University of Wisconsin Hospitals. For the n-bit parity problem, the algorithm was able to construct neural network having less than n hidden units that solved the problem for n = 4,...,7. For the cancer diagnosis problem, the neural networks constructed by the algorithm had small number of hidden units and high accuracy rates on both the training data and the testing data.

关键词： Intelligent networks Neural networks Feedforward neural networks Testing Heuristic algorithms Robustness Breast cancer Hospitals backpropagation algorithms Training data

来源：评论

学校读者我要写书评

暂无评论

Long Short-Term Memory Spiking Neural Networks for Classification of Snoring and Non-snoring Sound Events

引用

Chinese Journal of Electronics 2024年第3期33卷 793-802页

作者： Rulin ZHANG Ruixue LI Jiakai LIANG Keqiang YUE Wenjun LI Yilin LI Electronics and Information College Hangzhou Dianzi University

Snoring is a widespread occurrence that impacts human sleep *** is also one of the earliest symptoms of many sleep *** is accurately detected,making further screening and diagnosis of sleep problems *** is frequently ignored because of its underrated and costly detection *** a result,this research offered an alternative method for snoring detection based on a long short-term memory based spiking neural network(LSTM-SNN) that is appropriate for large-scale home detection for *** designed acquisition equipment to collect the sleep recordings of 54 subjects and constructed the sleep sound database in the home *** Mel frequency cepstral coefficients(MFCCs) were extracted from these sound signals and encoded into spike trains by a threshold encoding *** were classified automatically as non-snoring or snoring sounds by our LSTM-SNN *** used the backpropagation algorithm based on an alternative gradient in the LSTM-SNN to complete the parameter *** categorization percentage reached an impressive 93.4%,accompanied by a remarkable 36.9% reduction in computer power compared to the regular LSTM model.

关键词： Costs Databases Computational modeling backpropagation algorithms Sleep apnea Encoding Recording

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：