检索结果-内蒙古大学图书馆

Artificial neural networks controlled fast valving in a power generation plant

IEEE TRANSACTIONS ON NEURAL NETWORKS 1997年第2期8卷 373-389页

作者： Han, YD Xiu, LC Wang, ZH Chen, Q Tan, SH NATL UNIV SINGAPORE DEPT ELECT ENGN SINGAPORE 119260 SINGAPORE

This paper presents an artificial neural-network-based controller to realize the fast valving in a power generation plant. The backpropagation algorithm is used to train the feedforward neural networks controller. The hardware implementation and the test results of the controller on a physical pilot-scale power plant setup are described in detail. Compared with the conventional fast valving methods applied to the same system, test results both with the computer simulation and on a physical pilot-scale power plant setup demonstrate that the artificial neural-network controller has satisfactory generalization capability, reliability, and accuracy to be feasible for this critical control operation.

关键词： artificial neural networks backpropagation algorithm fast valving hardware implementation pilot-scale power plant setup power generation plant power system stability

来源：评论

学校读者我要写书评

暂无评论

A neural network-based approach for the prediction of urban SO₂ concentrations in the Istanbul metropolitan area

引用

INTERNATIONAL JOURNAL OF ENVIRONMENT AND POLLUTION 2010年第4期40卷 301-321页

作者： Akkoyunlu, Atilla Yetilmezsoy, Kaan Erturk, Ferruh Oztemel, Ercan Yildiz Tech Univ Dept Environm Engn Fac Civil Engn TR-34220 Istanbul Turkey Bogazici Univ Fac Engn TR-34342 Istanbul Turkey Marmara Univ Fac Engn Dept Ind Engn TR-34722 Istanbul Turkey

A three-layer Artificial Neural Network (ANN) model was developed to forecast air pollution levels. The subsequent SO2 concentration (24-hour averaged) being the Output parameter of this study was estimated by seven input parameters such as preceding SO2 concentrations (24-hour averaged), average daily temperature, sea-level pressure, relative humidity, cloudiness, average daily wind speed and daily dominant wind direction. After backpropagation training combined with Principal Component Analysis (PCA), the proposed model predicted subsequent SO2 values based oil measured data. ANN testing Outputs were proven to be satisfactory with correlation coefficients of about 0.770, 0.744 and 0.751 for the winter, summer and overall data, respectively.

关键词： ANN artificial neural network BP backpropagation algorithm modelling meteorological data SO2

来源：评论

学校读者我要写书评

暂无评论

A novel approach to diagnose diabetes based on the fractal characteristics of retinal images

引用

IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE 2003年第3期7卷 163-170页

作者： Cheng, SC Huang, YM Natl Cheng Hung Univ Dept Engn Sci Tainan 701 Taiwan

A novel diagnostic scheme to develop quantitative indexes of diabetes is introduced in this paper. The fractal dimension of the vascular distribution is estimated because we discovered that the fractal dimension of a severe diabetic patient's retinal vascular distribution appears greater than that of a normal human's. The issue of how to yield an accurate fractal dimension is to use high-quality images. To achieve a better image-processing result, an appropriate image-processing algorithm is adopted in this paper. Another important fractal feature introduced in this paper is the measure of lacunarity, which describes the characteristics of fractals that have the same fractal dimension but different appearances. For those vascular distributions in the same fractal dimension, further classification can be made using the degree of lacunarity. In addition to the image-processing technique, the resolution of original image is also discussed here. In this paper, the influence of the image resolution upon the fractal dimension is explored. We found that a low-resolution image cannot yield an accurate fractal dimension. Therefore, an approach for examining the lower bound of image resolution is also proposed in this paper. As for the classification of diagnosis results, four different approaches are compared to achieve higher accuracy. In this study, the fractal dimension and the measure of lacunarity have shown their significance in the classification of diabetes and are adequate for use as quantitative indexes.

关键词： backpropagation algorithm classification diagnosis system fractal dimension genetic algorithm image processing lactmarity radial basis function network voting scheme

来源：评论

学校读者我要写书评

暂无评论

Breast cancer classification applying artificial metaplasticity algorithm

引用

NEUROCOMPUTING 2011年第8期74卷 1243-1250页

作者： Marcano-Cedeno, A. Quintanilla-Dominguez, J. Andina, D. Tech Univ Madrid Grp Automat Signals & Commun Madrid Spain

A novel improvement in neural network training for pattern classification is presented in this paper. The proposed training algorithm is inspired by the biological metaplasticity property of neurons and Shannon's information theory. This algorithm is applicable to artificial neural networks (ANNs) in general, although here it is applied to a multilayer perceptron (MLP). During the training phase, the artificial metaplasticity multilayer perceptron (AMMLP) algorithm assigns higher values for updating the weights in the less frequent activations than in the more frequent ones. AMMLP achieves a more efficient training and improves MLP performance. The well-known and readily available Wisconsin Breast Cancer Database (WBCD) has been used to test the algorithm. Performance of the AMMLP was tested through classification accuracy, sensitivity and specificity analysis, and confusion matrix analysis. The results obtained by AMMLP are compared with the backpropagation algorithm (BPA) and other recent classification techniques applied to the same database. The best result obtained so far with the AMMLP algorithm is 99.63%. (C) 2010 Elsevier B.V. All rights reserved.

关键词： Neural network backpropagation algorithm Pattern recognition Metaplasticity Breast cancer

来源：评论

学校读者我要写书评

暂无评论

Extreme learning machine versus classical feedforward network Comparison from the usability perspective

引用

NEURAL COMPUTING & APPLICATIONS 2021年第22期33卷 15121-15144页

作者： Markowska-Kaczmar, Urszula Kosturek, Michal Wroclaw Univ Sci & Technol Wybrzeie Wyspianskiego 27 PL-50370 Wroclaw Poland

Our research is devoted to answering whether randomisation-based learning can be fully competitive with the classical feedforward neural networks trained using backpropagation algorithm for classification and regression tasks. We chose extreme learning as an example of randomisation-based networks. The models were evaluated in reference to training time and achieved efficiency. We conducted an extensive comparison of these two methods for various tasks in two scenarios: center dot using comparable network capacity and center dot using network architectures tuned for each model. The comparison was conducted on multiple datasets from public repositories and some artificial datasets created for this research. Overall, the experiments covered more than 50 datasets. Suitable statistical tests supported the results. They confirm that for relatively small datasets, extreme learning machines (ELM) are better than networks trained by the backpropagation algorithm. But for demanding image datasets, like ImageNet, ELM is not competitive to modern networks trained by backpropagation;therefore, in order to properly address current practical needs in pattern recognition entirely, ELM needs further development. Based on our experience, we postulate to develop smart algorithms for the inverse matrix calculation, so that determining weights for challenging datasets becomes feasible and memory efficient. There is a need to create specific mechanisms to avoid keeping the whole dataset in memory to compute weights. These are the most problematic elements in ELM processing, establishing the main obstacle in the widespread ELM application.

关键词： Randomisation-based learning Extreme learning backpropagation algorithm Neural networks

来源：评论

学校读者我要写书评

暂无评论

Fully automatic alpha matte extraction using artificial neural networks

引用

NEURAL COMPUTING & APPLICATIONS 2020年第11期32卷 6843-6855页

作者： Rosas-Romero, Roberto Lopez-Rincon, Omar Starostenko, Oleg Univ Americas Puebla Dept Elect & Comp Engn Cholula 72810 Pue Mexico

The alpha matte is a two-dimensional map that is used to combine two images, one containing a foreground and the other containing a background. Alpha matte extraction is performed on green-screen images and requires user interaction to tune parameters in different preprocessing and postprocessing stages to refine an alpha matte. This paper tackles the problem of fully automatic extraction of the foreground on green-screen images with extraction of the corresponding alpha matte. The method is based on a multi-layer perceptron that assigns an alpha value, from a discrete set of ten alpha values, to each patch on a green-screen image. The approach for assigning an alpha value to an image patch is based on a set of features that enhance discrimination between foreground and background. The classifier is trained to learn to separate foreground objects from green-screen backgrounds as well as to generate the corresponding alpha matte map required for subsequent digital compositing. To test how the proposed approach handles alpha matte extraction under unsuitable conditions, a 64-image dataset was generated. The main contribution is that our method overcomes two challenges publicly posed within a dataset of green-screen image sequences, donated by Hollywood Camera Work LLC. Tests with this dataset generate high-quality visual results for those two cases. These results are confirmed by comparing the proposed fully automatic alpha matte extraction with that based on the use of Adobe After Effects Creative Cloud, an application which heavily depends on user interaction.

关键词： Alpha matting Digital compositing Green screen Machine learning backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

ONLINE LEARNING CONTROL OF AUTONOMOUS UNDERWATER VEHICLES USING FEEDFORWARD NEURAL NETWORKS

引用

IEEE JOURNAL OF OCEANIC ENGINEERING 1992年第4期17卷 308-319页

作者： VENUGOPAL, KP SUDHAKAR, R PANDYA, AS FLORIDA ATLANTIC UNIV DEPT ELECT ENGNBOCA RATONFL 33431 FLORIDA ATLANTIC UNIV DEPT COMP SCI & ENGNBOCA RATONFL 33431

We describe a neural network based learning control scheme for the motion control of autonomous underwater vehicles (AUV). The described scheme has a number of advantages over the classical control schemes and conventional adaptive control techniques. The dynamics of the controlled vehicle need not be fully known. The controller with the aid of a gain layer learns the dynamics and adapts fast to give the correct control action. The dynamic response and tracking performance could be accurately controlled by adjusting the network learning rate. A modified direct control scheme using multilayered neural network architecture is used in the studies with backpropagation as the learning algorithm. Results of simulation studies using nonlinear AUV dynamics is described in detail. Also, the robustness of the control system to sudden and slow varying disturbances in the dynamics is studied and the results are presented.

关键词： NEURAL NETWORKS UNDERWATER ROBOTICS AUTONOMOUS UNDERWATER VEHICLES LEARNING CONTROL DIRECT CONTROL backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Parameter tuning for dynamic digital twins in inverter-dominated distribution grid

引用

IET RENEWABLE POWER GENERATION 2020年第5期14卷 811-821页

作者： Song, Xinya Jiang, Teng Schlegel, Steffen Westermann, Dirk Technol Univ Ilmenau Dept Power Syst Gustav Kirchhoff Str 1 Ilmenau Germany

This research proposed the methods based on the neural network (NN) to build the digital twins (DT) of the inverter model. The proposed methods can be divided into two groups: firstly, an online tuner for the proportional-integral (PI) controller is formulated through backpropagation (BP) algorithm;and secondly an NN-based identifier is used to approximate the nonlinear functional dynamics of the targeted control loop of the inverter. The design of PI tuner is based on the deviation between the output of the model and the reference output from measurement data. Then, according to the difference, the tuner can calculate the appropriate parameter of the current and voltage controller to track the dynamic behaviour of the reference model. The NN identifier is, however, to replicate the dynamic character of the reference model by NN which is initially trained offline with extensive test data and afterwards is applied to online tuning. In order to compare the advantages of the methods by NN with the traditional ones, the system identification and parameter estimation are also utilised to build the DT of inverter model. The performance of these methods will contribute to illustrating that NN identifier is effective in the building of DT.

关键词： PI control online tuner inverter model inverter-dominated distribution grid current controller dynamic behaviour PI tuner system identification backpropagation neurocontrollers control system synthesis adaptive control nonlinear control systems parameter estimation neural network backpropagation algorithm nonlinear functional dynamics power distribution control reference output appropriate parameter NN-based identifier dynamic digital twins invertors voltage controller parameter tuning measurement data proportional–integral controller tuning targeted control loop

来源：评论

学校读者我要写书评

暂无评论

Predicting the performance of a desulfurizing bio-filter using an artificial neural network (ANN) model

引用

ENVIRONMENTAL ENGINEERING RESEARCH 2021年第6期26卷 67-76页

作者： Salehi, Reza Lestari, Retno Ambarwati Sigit 3495 St Domin Montreal PQ H2X 2X5 Canada 17 Agustus 1945 Univ Chem Engn Dept Semarang Jawa Tengah Indonesia

The aim of this study was to develop a model for predicting the performance of a desulfurizing bio-filter (BF), without requiring prior information about H2S biodegradation kinetics and mechanism. A single hidden layer artificial neural network (ANN) model was developed and validated using the gradient descent backpropagation (GDBP) learning algorithm coupled with a learning rate and a momentum factor. The ANN model inputs were gas flow rate, residence time, and axial position in the BF bed. The removal efficiency of H2S was the model output. Various structures for ANN model, differing in the number of hidden layer neurons, were trained and an early stopping validation technique, the K-fold cross-validation, was used to determine the optimal structure with the best generalization ability. The modeling results showed that there was a good agreement between the experimental data and the predicted values, with a determination coefficient (R2) of 94%. This implies that the ANN model might be an attractive and useful alternative tool for forecasting the performance of desulfurizing BFs.

关键词： Artificial neural network backpropagation algorithm Bio-filter Cross-validation Hydrogen sulfide removal

来源：评论

学校读者我要写书评

暂无评论

A dynamic ensemble learning algorithm for neural networks

引用

NEURAL COMPUTING & APPLICATIONS 2020年第12期32卷 8675-8690页

作者： Alam, Kazi Md Rokibul Siddique, Nazmul Adeli, Hojjat Khulna Univ Engn & Technol Dept Comp Sci & Engn Khulna 9203 Bangladesh Ulster Univ Sch Comp Engn & Intelligent Syst Derry BT48 7JL Londonderry North Ireland Ohio State Univ Dept Neurosci Columbus OH 43210 USA Ohio State Univ Dept Neurol Columbus OH 43210 USA Ohio State Univ Dept Biomed Informat Columbus OH 43210 USA

This paper presents a novel dynamic ensemble learning (DEL) algorithm for designing ensemble of neural networks (NNs). DEL algorithm determines the size of ensemble, the number of individual NNs employing a constructive strategy, the number of hidden nodes of individual NNs employing a constructive-pruning strategy, and different training samples for individual NN's learning. For diversity, negative correlation learning has been introduced and also variation of training samples has been made for individual NNs that provide better learning from the whole training samples. The major benefits of the proposed DEL compared to existing ensemble algorithms are (1) automatic design of ensemble;(2) maintaining accuracy and diversity of NNs at the same time;and (3) minimum number of parameters to be defined by user. DEL algorithm is applied to a set of real-world classification problems such as the cancer, diabetes, heart disease, thyroid, credit card, glass, gene, horse, letter recognition, mushroom, and soybean datasets. It has been confirmed by experimental results that DEL produces dynamic NN ensembles of appropriate architecture and diversity that demonstrate good generalization ability.

关键词： Neural network ensemble backpropagation algorithm Negative correlation learning Constructive algorithms Pruning algorithms

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

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

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：