检索结果-内蒙古大学图书馆

NN-LEAP:: A neural network-based model for controlling leachate flow-rate in a municipal solid waste landfill site

ENVIRONMENTAL MODELLING & SOFTWARE 2006年第8期21卷 1190-1197页

作者： Karaca, Ferhat Ozkaya, Bestamin Yildiz Tech Univ Fac Civil Engn Dept Environm Engn TR-34349 Istanbul Turkey Fatih Univ Dept Environm Engn Istanbul Turkey

A method is proposed for modeling leachate flow-rate in a municipal solid waste (MSW) landfill site, based on a popular neural network - the backpropagation algorithm (neural network-based leachate prediction method;NN-LEAP). After backpropagation training, the neural network model predicts flow-rates based on meteorological data. Depending on output value, relevant control strategies and actions are activated. To illustrate and validate the proposed method, a case study was carried out, based on the data obtained from the Istanbul Odayeri landfill site. As a critical model parameter (neural network outputs), daily flow-rate of leachate from the landfill site was considered. The Levenberg-Marquardt algorithm was selected as the best of 13 backpropagation algorithms. The optimal neural network architecture has been determined, and the advantages, disadvantages and further developments are discussed. (c) 2005 Elsevier Ltd. All rights reserved.

关键词： neural network backpropagation algorithm leachate flow-rate modeling

来源：评论

学校读者我要写书评

暂无评论

Accelerating neural network training using weight extrapolations

引用

NEURAL NETWORKS 1999年第9期12卷 1285-1299页

作者： Kamarthi, SV Pittner, S Northeastern Univ Dept Mech Ind & Mfg Engn Snell Eng Ctr 334 Boston MA 02115 USA

The backpropagation (BP) algorithm for training feedforward neural networks has proven robust even for difficult problems. However, its high performance results are attained at the expense of a long training time to adjust the network parameters, which can be discouraging in many real-world applications. Even on relatively simple problems, standard BP often requires a lengthy training process in which the complete set of training examples is processed hundreds or thousands of times. In this paper, a universal acceleration technique for the BP algorithm based on extrapolation of each individual interconnection weight is presented. This extrapolation procedure is easy to implement and is activated only a few times in between iterations of the conventional BP algorithm. This procedure, unlike earlier acceleration procedures, minimally alters the computational structure of the BP algorithm. The viability of this new approach is demonstrated on three examples. The results suggest that it leads to significant savings in computation time of the standard BP algorithm. Moreover, the solution computed by the proposed approach is always located in close proximity to the one obtained by the conventional BP procedure. Hence, the proposed method provides a real acceleration of the BP algorithm without degrading the usefulness of its solutions. The performance of the new method is also compared with that of the conjugate gradient algorithm, which is an improved and faster version of the BP algorithm. (C) 1999 Elsevier Science Ltd. All rights reserved.

关键词： multilayer neural networks backpropagation algorithm convergence acceleration extrapolation methods parameter estimation linear regression conjugate gradient method relative entropy

来源：评论

学校读者我要写书评

暂无评论

DSmishSMS-A System to Detect Smishing SMS

引用

NEURAL COMPUTING & APPLICATIONS 2023年第7期35卷 4975-4992页

作者： Mishra, Sandhya Soni, Devpriya Jaypee Inst Informat Technol Dept Comp Sci & Engn & Informat Technol Sect 128 Noida India

With the origin of smart homes, smart cities, and smart everything, smart phones came up as an area of magnificent growth and development. These devices became a part of daily activities of human life. This impact and growth have made these devices more vulnerable to attacks than other devices such as desktops or laptops. Text messages or SMS (Short Text Messages) are a part of smartphones through which attackers target the users. Smishing (SMS Phishing) is an attack targeting smartphone users through the medium of text messages. Though smishing is a type of phishing, it is different from phishing in many aspects like the amount of information available in the SMS, the strategy of attack, etc. Thus, detection of smishing is a challenge in the context of the minimum amount of information shared by the attacker. In the case of smishing, we have short text messages which are often in short forms or in symbolic forms. A single text message contains very few smishing-related features, and it consists of abbreviations and idioms which makes smishing detection more difficult. Detection of smishing is a challenge not only because of features constraint but also due to the scarcity of real smishing datasets. To differentiate spam messages from smishing messages, we are evaluating the legitimacy of the URL (Uniform Resource Locator) in the message. We have extracted the five most efficient features from the text messages to enable the machine learning classification using a limited number of features. In this paper, we have presented a smishing detection model comprising of two phases, Domain Checking Phase and SMS Classification Phase. We have examined the authenticity of the URL in the SMS which is a crucial part of SMS phishing detection. In our system, Domain Checking Phase scrutinizes the authenticity of the URL. SMS Classification Phase examines the text contents of the messages and extracts some efficient features. Finally, the system classifies the messages using Back

关键词： Smishing Phishing Paytm SMS scam Mobile security Machine learning backpropagation algorithm Cyber security Covid-19 SMS Scam

来源：评论

学校读者我要写书评

暂无评论

SHORT-TERM LOAD FORECASTING USING AN ARTIFICIAL NEURAL NETWORK

引用

IEEE TRANSACTIONS ON POWER SYSTEMS 1992年第1期7卷 124-132页

作者： LEE, KY CHA, YT PARK, JH KURZYN, MS PARK, DC MOHAMMED, OA PUSAN NATL UNIV DEPT ELECT ENGNPUSAN 609735SOUTH KOREA FLORIDA INT UNIV MIAMIFL 33199 VICTORIA COLL CLAYTONVICAUSTRALIA

Artificial Neural Network (ANN) Method is applied to forecast the short-term load for a large power system. The load has two distinct patterns: weekday and weekend-day patterns. The weekend-day pattern include Saturday, Sunday, and Monday loads. A nonlinear load model is proposed and several structures of ANN for short-term load forecasting are tested. Inputs to the ANN are past loads and the output of the ANN is the load forecast for a given day. The network with one or two hidden layers are tested with various combination of neurons, and results are compared in terms of forecasting error. The neural network, when grouped into different load patterns, gives good load forecast.

关键词： NEURAL NETWORK LOAD FORECASTING backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Artificial-neural-network-based fast valving control in a power-generation system

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 1997年第2期10卷 139-155页

作者： Han, YD Wang, ZH Chen, Q Tan, SH NATL UNIV SINGAPORE DEPT ELECT ENGNSINGAPORE 119260SINGAPORE TSING HUA UNIV BEIJING 100084PEOPLES R CHINA

This paper presents an artificial-neural-network-based controller to realize fast valving in a power-generation plant A backpropagation. algorithm is used to train the feedforward neural-network controller The hardware implementation and the test results of the controller on a physical pilot-scale power system set-up are described in detail. Compared with some conventional fast valving methods applied to the same system, test results (both in a computer simulation and on a physical pilot-scale power system set-up) show that the neural-network controller has quite satisfactory generalisation capability, feasibility and reliability, as well as accuracy. (C) 1997 Elsevier Science Ltd.

关键词： power-generation systems fast valving transient stability artificial neural networks backpropagation algorithm pilot-scale power systems set-ups hardware implementation

来源：评论

学校读者我要写书评

暂无评论

PARALLEL SIMULATION OF MULTILAYERED NEURAL NETWORKS ON DISTRIBUTED-MEMORY MULTIPROCESSORS

MICROPROCESSING AND MICROPROGRAMMING

引用

MICROPROCESSING AND MICROPROGRAMMING 1990年第3期29卷 185-195页

作者： YOON, H NANG, JH MAENG, SR KOREA INST SCI & TECHNOL DEPT COMP SCI SEOUL 130650 SOUTH KOREA

In this paper, we present a parallel simulation of a fully connected multilayered neural network using the backpropagation learning algorithm on a distributed-memory multiprocessor system. In our system, the neurons on each layer are partitioned into p disjoint sets and each set is mapped on a processor of a p -processor system. A fully distributed backpropagation algorithm, necessary communication pattern among the processors, and their time/space complexities are investigated. The p -processor speed-up of the backpropagation algorithm over a single processor is also analyzed theoretically which can be used as a basis in determining the most cost-effective or optimal number of processors. The experimental results with a network of Transputers are also presented to demonstrate the usefulness of our system.

关键词： Neural network Parallel processing backpropagation algorithm Distributed-memory multiprocessor Performance analysis

来源：评论

学校读者我要写书评

暂无评论

Neural network modelling of Abbott-Firestone roughness parameters in honing processes

引用

INTERNATIONAL JOURNAL OF SURFACE SCIENCE AND ENGINEERING 2017年第6期11卷 512-530页

作者： Sivatte-Adroer, Maurici Buj-Corral, Irene Llanas-Parra, Xavier Univ Politecn Cataluna Dept Mech Engn Sch Engn Vilanova I la Geltru EPSEVG Av Victor Balaguer 1 Barcelona 08800 Spain Univ Politecn Cataluna Dept Mech Engn Sch Engn Barcelona ETSEIB Av Diagonal 647 E-08028 Barcelona Spain Univ Politecn Cataluna Sch Engn Vilanova I la Geltru EPSEVG Automat Control Dept Av Victor Balaguer 1 Barcelona 08800 Spain

In present study, three roughness parameters defined in the Abbott-Firestone or bearing area curve, Rk, Rpk and Rvk, were modelled for rough honing processes by means of artificial neural networks (ANN). Input variables were grain size and density of abrasive, pressure of abrasive stones on the workpiece's surface, tangential or rotation speed of the workpiece and linear speed of the honing head. Two strategies were considered, either use of one network for modelling the three parameters at the same time or use of three networks, one for each parameter. Overall best neural network consists of three networks, one for each roughness parameter, with one hidden layer having 25, nine and five neurons for Rk, Rpk and Rvk respectively. However, use of one network for the three roughness parameters would allow addressing an indirect model. In this case, best solution corresponds to two hidden layers having 26 and 11 neurons.

关键词： surface roughness honing artificial neural networks ANN backpropagation algorithm Abbott-Firestone roughness parameters back propagation algorithm grain size density of abrasive linear speed tangential speed pressure

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Entropy Based Neuro-Wavelet Identifier-Cum-Quantifier for Discrimination of Gases/Odors

引用

IEEE SENSORS JOURNAL 2011年第7期11卷 1548-1555页

作者： Kumar, Ravi Das, R. R. Mishra, V. N. Dwivedi, R. Banaras Hindu Univ Inst Technol Dept Elect Engn Varanasi 221005 Uttar Pradesh India

In this paper, a new approach to design of an odor/gas identifier-cum-quantifier is presented. Dynamic response curves of an oxygen-plasma treated thick-film tin oxide sensor array exposed to four different gases were subjected to continuous wavelet transform (CWT). Appropriate wavelet coefficients were selected using multiscale principal component analysis (MSPCA). Fuzzy entropy and fuzzy subsethood values were calculated for the individual odor/gas and for the particular concentration band of each odor/gas, respectively. The quantitative information was encoded in the fuzzy subsethood values of the particular concentration bands in the output feature space, whereas the fuzzy entropy values were used to normalize the training data set consisting of MSPCA selected wavelet coefficients. A feedforward neural network was trained with a backpropagation algorithm with the training data containing the wavelet coefficients normalized with fuzzy entropies of individual odors/gases. The target data set was made up of the fuzzy subsethood values of the particular concentration band. The proposed network achieved identification and quantification of odors/gases with a 100% success rate. Also, fuzzy entropy based normalization helped to achieve 100% identification/quantification with a reduced number of sensors in the array.

关键词： backpropagation algorithm fuzzy entropy multi-scale principal component analysis oxygen plasma tin oxide sensors wavelet transform

来源：评论

学校读者我要写书评

暂无评论

THE EFFECT OF WEIGHT PRECISION AND RANGE ON NEURAL-NETWORK CLASSIFIER PERFORMANCE

引用

NEUROCOMPUTING 1994年第5-6期6卷 541-549页

作者： YOO, H PIMMEL, RL UNIV ALABAMA TUSCALOOSAAL 35401 UNIV MISSOURI COLUMBIAMO 65201

This study investigates the precision and range requirements for weights in feed-forward neural network classifiers using backpropagation training with simulated signals where we could control the difficulty of the problem. We found that a precision of five bits and a range equal to four times the mean weight magnitude produced the same performance as continuous weights. However, we noted that the required precision and range depended strongly on the problem difficulty, the network complexity, and the relationship between these two factors. We also found that uniformly distributed discrete weights produced better performance than non-uniformly distributed ones.

关键词： PATTERN CLASSIFICATION DISCRETE WEIGHTS FEEDFORWARD NETWORKS backpropagation algorithm COMPANDING WEIGHTS

来源：评论

学校读者我要写书评

暂无评论

On fault tolerant training of feedforward neural networks

引用

NEURAL NETWORKS 1997年第3期10卷 539-553页

作者： Arad, BS ElAmawy, A LOUISIANA STATE UNIV DEPT ELECT & COMP ENGNBATON ROUGELA 70803

This paper presents an extensive study of fault tolerant training of feedforward artificial neural networks. We present several versions of a very robust training algorithm and report the results of their simulations. Our algorithm is shown to outperform all existing training algorithms in its ability to tolerate different fault types and larger number of hidden unit failures. We show that the generalization ability of the proposed algorithm is substantially better than that of the standard backpropagation algorithm and is comparable with that of other existing fault tolerant algorithms. The algorithm is based on the backpropagation algorithm with built-in measures for extensive fault tolerant training. A novel concept presented in this paper is that of training the network for fault types beyond the limits of the activation function. We demonstrate that training for such unrealistic fault types enables the network to be more tolerant to realistic fault types within the limits of the activation function. Further, tradeoffs between training time, enhanced fault tolerance, and generalization properties are studied. (C) 1997 Elsevier Science Ltd.

关键词： artificial neural network fault tolerant training efficiency generalization backpropagation algorithm feedforward network neuron failure fault types

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：