检索结果-内蒙古大学图书馆

An application of neural networks in microeconomics: input-output mapping in a power generation subsector of the US electricity industry

引用

EXPERT SYSTEMS WITH APPLICATIONS 2009年第2期36卷 2317-2326页

作者： Erbas, Bahar Celikkol Stefanou, Spiro E. TOBB Univ Econ & Technol Dept Econ TR-06530 Ankara Turkey Penn State Univ Dept Agr Econ & Rural Sociol University Pk PA 16802 USA

The use of the artificial neural networks ill economics and business goes back to 1950s, while the major bulk of the applications have been developed in more recent years. Reviewing this literature indicates that the field of business benefits from the neural networks ill a wide spectrum from prediction to classification, as most of the applications in economics primarily focus oil the predictive power of file neural networks. Time series analysis and forecasting, econometries, macroeconomics constitute file main areas of economics, where there is all increasing interest ill application of neural networks. Although their promising contributions to the area of microeconomics. the applications Of neural networks ill this area are limited in number. This study provides a microeconomic application of an artificial neural network by input-output mapping for 82 US major investor-owned electric utilities using fossil-fuel fired steam electric power generation for the year 1996. We construct a multilayer feed-forward neural network (MFNN) with back-propagation to represent the relationship between a set of inputs and an electricity production as ill output. The network is trained and tested by using approximately 80 percent and 20 percent of the data, respectively. The network is trained with 97% accuracy and performance of the network in testing is 96%. Therefore, this network can be used in calculating electricity output for the given inputs in this subsector of the US electricity market, and these estimations call be employed in policy design and planning. (C) 2007 Elsevier Ltd. All rights reserved.

关键词： Microeconomics input-output mapping Electricity industry Multilayer feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

A static neural network for input-output mapping of power electronic circuits

A static neural network for input-output mapping of power el...

引用

IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives

作者： Mohagheghi, Salman Harley, Ronald G. Habetler, Thomas G. Divan, Deepak IEEE

ISBN: (纸本)9781424410613

This paper investigates the effectiveness of a static neural network for input-output mapping of power electronic circuits. The neural network is a multilayer perceptron (MLP) that is trained to form a mapping between the inputs and outputs of a power electronic circuit. The circuit consists of a full bridge diode rectifier, together with the source inductance and the output filter. Dynamic models have been used for the rectifier diodes. The ultimate objective of the designed neural network is to provide an indication when the performance properties of one or more components in the rectifier circuit have changed. Simulation results are provided that indicate the neural network is capable of mapping the inputs and outputs of the circuit and detect operating conditions that are different from the original condition.

关键词： multilayer perceptron neural network input-output mapping switching circuits identification

来源：评论

学校读者我要写书评

暂无评论

Effects of an input-output mapping practice task on EFL learners' acquisition of two grammatical structures

引用

SYSTEM 2013年第2期41卷 443-461页

作者： Shegar, Chitra Zhang, Lawrence Jun Low, Ee Ling Nanyang Technol Univ Natl Inst Educ Singapore 637616 Singapore Univ Auckland Fac Educ Sch Curriculum & Pedag Auckland 1150 New Zealand

One of the key goals in SLA research is investigating methods of instruction to bring about the acquisition of targeted structures in unplanned language use. This has led researchers to investigate the relative effectiveness of different approaches such as consciousness-raising (C-R), production practice, and recasts. However, a critical review of the research of these approaches has shown that many of these studies have not investigated the impact of instruction on unplanned language use. Neither have they investigated how a series of language activities involving tasks would impact unplanned language use. To address this gap, the present study examined the effects of an input-output mapping practice task on EFL learners' acquisition of two target structures, the 3rd person singular "s" morpheme and do/auxiliary wh-questions, on unplanned language use among 34 English learners of Asian backgrounds. The input-output mapping practice task comprised a series of language activities involving C-R, production practice, and recasts to facilitate the acquisition of the target structures. The results indicate that the input-output mapping practice task had a significant and lasting impact on the acquisition of the two structures. The meaning-focused activities and exposure with the control group had a significant and lasting impact only on the acquisition of the target structure, do/auxiliary wh-questions. These findings are discussed with reference to the recent literature in instructed SLA. Recommendations for further research are also made. (c) 2013 Elsevier Ltd. All rights reserved.

关键词： Instructed SLA EFL learners input-output mapping Unplanned language use Grammatical structures

来源：评论

学校读者我要写书评

暂无评论

Enhanced inferable capability in state estimation of dynamic systems exhibiting hysteresis/inelastic behavior under the limit of minimal sensor

引用

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2025年 225卷

作者： He, Xinhao Li, Dan Gu, Jiancheng Dang, Ji Unjoh, Shigeki Tohoku Univ Grad Sch Engn Dept Civil & Environm Engn Sendai Japan Southeast Univ Sch Civil Engn Dhaka Peoples R China Nanjing Tech Univ Dept Civil Engn Nanjing Peoples R China Saitama Univ Grad Sch Sci & Engn Dept Civil & Environm Engn Saitama Japan

As the dynamics of modern infrastructures grow increasingly complex, the application of structural health monitoring (SHM) techniques to these dynamic systems presents a crucial challenge-how to derive maximal system information from limited sensor deployments. This study addresses this challenge by applying Lie symmetry analysis on nonlinear input-output (I-O) mappings, formed by dynamic systems and sensor layouts. Specifically, we focus on systems characterized by Bouc-Wen type hysteresis behaviors, under minimal sensor deployments. We introduce differentiable unidirectional and bidirectional Bouc-Wen models to enhance the maximum inferable capability of I-O mappings in these systems and extend their application to other nonlinear hysteresis models. The utility of the proposed differentiable hysteresis models is demonstrated through three Bayesian estimation scenarios under the limit of minimal sensor, involving numerical and experimental data from a typical dynamic example with unidirectional hysteresis behavior, as well as a hybrid simulation test and a shaking table test example with bidirectional hysteresis behavior.

关键词： Structural Health Monitoring Minimal Sensor input-output mapping Symmetry Analysis Differentiable Bouc-Wen Model

来源：评论

学校读者我要写书评

暂无评论

A note on systems with ordinary and impulsive controls

引用

IMA JOURNAL OF MATHEMATICAL CONTROL AND INFORMATION 2016年第2期33卷 147-162页

作者： Soledad Aronna, M. Rampazzo, Franco IMPA Rio De Janeiro Brazil Univ Padua Dipartimento Matemat Padua Italy

We investigate an everywhere defined notion of solution for control systems whose dynamics depend non-linearly on the control u and state x, and are affine in the time derivative. u. For this reason, the input u, which is allowed to be Lebesgue integrable, is called impulsive, while a second, bounded measurable control v is denominated ordinary. The proposed notion of solution is derived from a topological (non-metric) characterization of a former concept of solution which was given in the case when the drift is v-independent. Existence, uniqueness and representation of the solution are studied, and a close analysis of effects of (possibly infinitely many) discontinuities on a null set is performed as well.

关键词： impulse controls pointwise defined measurable solutions input-output mapping commutative control systems

来源：评论

学校读者我要写书评

暂无评论

MAXIMUM A POSTERIORI DECISION AND EVALUATION OF CLASS PROBABILITIES BY BOLTZMANN PERCEPTRON CLASSIFIERS

引用

PROCEEDINGS OF THE IEEE 1990年第10期78卷 1620-1628页

作者： YAIR, E GERSHO, A UNIV CALIF SANTA BARBARA CTR INFORMAT PROC RESDEPT ELECT & COMP ENGNSANTA BARBARACA 93106

It is shown that neural network architectures may offer a valuable alternative to the Bayesian classifier. With neural networks, the a posteriori probabilities are computed with no a priori assumptions about the probability distribution functions (PDFs) that generate the data. Rather than assuming certain types of PDFs for the input data, the neural classifier uses a general type of input-output mapping which is then designed to optimally comply with a given set of examples called the training set. It is demonstrated that the a posteriori class probabilities can be efficiently computed by a deterministic feedforward network which is called the Boltzmann perceptron classifier (BPC). Maximum a posteriori (MAP) classifiers are also constructed as a special case of the BPC. Structural relationships between the BPC and a conventional multilayer perceptron (MLP) are given, and it is demonstrated that rather intricate boundaries between classes can be formed even with a relatively modest number of network units. Simulation results show that the BPC is comparable in performance to a Bayesian classifier

关键词： Boltzmann perceptron classifiers decision theory input-output mapping neural classifier neural nets neural network pattern recognition probability probability distribution functions

来源：评论

学校读者我要写书评

暂无评论

Simultaneous inversion for a diffusion coefficient and a spatially dependent source term in the SFADE

引用

INVERSE PROBLEMS IN SCIENCE AND ENGINEERING 2016年第5期24卷 832-859页

作者： Jia, Xianzheng Li, Gongsheng Sun, Chunlong Du, Dianhu Shandong Univ Technol Sch Sci Zibo Peoples R China

This paper deals with an inverse problem of determining a diffusion coefficient and a spatially dependent source term simultaneously in one-dimensional (1-D) space fractional advection-diffusion equation with final observations using the optimal perturbation regularization algorithm. An implicit finite difference scheme for solving the forward problem is set forth, and a fine estimation to the spectrum radius of the coefficient matrix of the difference scheme is given with which unconditional stability and convergence are proved. The simultaneous inversion problem is transformed to a minimization problem, and existence of solution to the minimum problem is proved by continuity of the input-output mapping. The optimal perturbation algorithm is introduced to solve the inverse problem, and numerical inversions are performed with the source function taking on different forms and the diffusion coefficient taking on different values, respectively. The inversion solutions give good approximations to the exact solutions demonstrating that the optimal perturbation algorithm with the Sigmoid-type regularization parameter is efficient for the simultaneous inversion problem in the space fractional diffusion equation.

关键词： Space fractional advection-diffusion equation (SFADE) inverse problem simultaneous inversion finite difference scheme input-output mapping optimal perturbation regularization algorithm

来源：评论

学校读者我要写书评

暂无评论

Use of MATLAB neural networks toolbox in a character recognition problem

引用

COMPUTER APPLICATIONS IN ENGINEERING EDUCATION 2005年第1期13卷 66-71页

作者： Trebar, M Univ Ljubljana Fac Chem & Informat Sci Dhaka 1000 Bangladesh

We present the use of the MATLAB Neural Network Toolbox (NN Toolbox) in simulations of neural networks. We suggest ways for undergraduate students to solve a character recognition problem with feed-forward neural networks. The software provides the user with a very simple way to define several neural network architectures with different parameters, The solution of the character recognition problem is described from the beginning: collecting the data, data encoding, defining the input-output mapping architecture to the training, and testing the neural networks with the NN Toolbox. (c) 2005 Wiley Periodicals, Inc.

关键词： character recognition input-output mapping data encoding neural networks

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network for monitoring the asymmetric half bridge DC-DC converter

引用

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS 2012年第1期43卷 788-792页

作者： Gnanasaravanan, A. Rajaram, M. Anna Univ Madras 600025 Tamil Nadu India Anna Univ Technol Tirunelveli Madras Tamil Nadu India

This paper investigates the effectiveness of an Artificial Neural Network (ANN) while training as an asymmetric half bridge DC-DC converter circuit used in sensitive applications. The ANN is trained to form a mapping between the inputs and outputs of converter circuit using back propagation algorithm. After training the Artificial Neural Network monitor the asymmetric half bridge converter in order to detect the performance deviations. The ultimate objective of the designed Neural network is to perform like the trained converter circuit when the circuit is changed from its original conditions. Such information can be valuable for many sensitive power electronic applications. Typical simulation results are provided that indicates the effectiveness of the proposed scheme. Crown Copyright (C) 2012 Published by Elsevier Ltd. All rights reserved.

关键词： Artificial Neural Network (ANN) Identification input-output mapping Multi Layer Perceptron (MLP) Asymmetric converter

来源：评论

学校读者我要写书评

暂无评论

Approach to design a compact reversible low power binary comparator

引用

IET COMPUTERS AND DIGITAL TECHNIQUES 2014年第3期8卷 129-139页

作者： Babu, Hafiz Md Hasan Saleheen, Nazir Jamal, Lafifa Sarwar, Sheikh Muhammad Sasao, Tsutomu Univ Dhaka Dept Comp Sci & Engn Dhaka Bangladesh Univ Memphis Dept Comp Sci Memphis TN 38152 USA Meiji Univ Dept Comp Sci Kawasaki Kanagawa 2148571 Japan

Reversible logic has captured significant attention in recent time as reducing power consumption is the main concern of digital logic design. It consumes less power by recovering bit loss from its unique input-output mapping. In this study, the authors propose a reversible low power n-bit binary comparator. An algorithm is presented for constructing a compact reversible n-bit binary comparator circuit. The authors also propose two new reversible gates, namely, Babu-Jamal-Saleheen (BJS) and Hasan-Lafifa-Nazir (HLN) gates, to optimise the comparator. In addition, several theorems on the numbers of gates, garbage outputs, quantum cost, ancilla input, power, delay and area of the reversible n-bit comparator have been presented. The simulation results of the proposed comparator show that the circuit works correctly and gives significantly better performance than the existing ones. The comparative study shows that, as an example, for a 64-bit comparator, the proposed design achieves the improvement of 24.4% in terms of number of gates, 19.9% in terms of garbage outputs, 7.7% in terms of quantum cost, 25.77% in terms of area and 3.43% in terms of power over the existing best one. Area and power analysis also show that the proposed design is the most compact as well as a low power circuit.

关键词： comparators (circuits) logic design logic gates performance evaluation power aware computing compact reversible low power n-bit binary comparator design reversible logic power consumption reducing digital logic design bit loss recovering input-output mapping reversible gates Babu-Jamal-Saleheen-Sarwar gates Hasan-Laflfa-Nazir-Sheikh gates garbage outputs quantum cost ancilla input delay

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：