检索结果-内蒙古大学图书馆

作者： Eshel Faraggi Robert L. Jernigan Andrzej Kloczkowski

We have studied the ability of three types of neural networks to predict the closeness of a given protein model to the native structure associated with its sequence. We show that a partial combination of the levenberg–marquardt algorithm and the back-propagation algorithm produced the best results, giving the lowest error and largest Pearson correlation coefficient. We also find, as previous studies, that adding associative memory to a neural network improves its performance. Additionally, we find that the hybrid method we propose was the most robust in the sense that other configurations of it experienced less decline in comparison to the other methods. We find that the hybrid networks also undergo more fluctuations on the path to convergence. We propose that these fluctuations allow for better sampling. Overall we find it may be beneficial to treat different parts of a neural network with varied computational approaches during optimization. less

关键词： Protein Structure Analysis Steepest Descent Method Protein Structure Prediction Neural network levenberg–marquardt algorithm Associative memory Model quality assessment

来源：评论

学校读者我要写书评

暂无评论

Study on conducted EMI noise source modelling applied in electromagnetic compatibility analysis based on GA in cooperation with LM

引用

IET POWER ELECTRONICS 2020年第5期13卷 927-935页

作者： Zhou Mengxia Zhao Yang Yan Jingrui Yan Wei Sun Minghui Wu Xianqiang Xiao Baoming Nanjing Normal Univ Sch Elect & Automat Engn Nanjing Peoples R China State Grid Lianyungang Power Supply Co Lianyungang Peoples R China Nanjing Univ Aeronaut & Astronaut Key Lab New Energy Generat & Power Convers 169 Sheng Tai West Rd Nanjing Peoples R China State Grid Elect Power Res Inst Nanjing Branch Nanjing Jiangsu Peoples R China

In this study, a new method employing scattering parameters (SPs) method, genetic algorithm (GA) and levenbergmarquardt algorithm (LM) is proposed for modelling conducted electromagnetic interference (EMI) noise source impedance. On the basis of the impedance information extracted by traditional SP method, GA is adopted to optimise the impedance information by taking advantage of the fast convergence speed. The obtained values of the RCL parameter are used as a set of initial values. Then, by using the advantage of the high precision of the LM, the initial values obtained by the GA are iteratively calculated. Better results can be obtained by using this combination method. This method improves the processing accuracy while ensuring the processing speed and contributes to the design of conduction EMI filter.

关键词： electromagnetic compatibility electromagnetic interference genetic algorithms conducted EMI noise source electromagnetic compatibility analysis GA scattering parameters method genetic algorithm levenberg–marquardt algorithm electromagnetic interference noise source impedance impedance information fast convergence speed RCL parameter initial values combination method conduction EMI filter

来源：评论

学校读者我要写书评

暂无评论

Prediction of number of insured having work accident in Turkish construction industry: a neural network fitting approach

引用

PROCEEDINGS OF THE INSTITUTION OF CIVIL ENGINEERS-MANAGEMENT PROCUREMENT AND LAW 2024年第4期177卷 193-206页

作者： Demirkesen, Sevilay Gebze Tech Univ Dept Civil Engn TR-41400 Kocaeli Turkiye

Accurate forecasting of work accidents is of paramount importance in promoting workplace safety and improving risk management strategies. This study proposes a novel approach based on a neural network fitted with the levenberg-marquardt algorithm to predict future accident numbers in 22 different occupational groups within the Turkish construction industry. By utilizing historical official data spanning the years 2014 to 2022, the aim is to provide insights into the potential accident rates that may arise in different job categories. The constructed neural network model consists of two hidden layers. Leveraging the powerful capabilities of the levenberg-marquardt algorithm, the network is trained to effectively capture the complex dynamics underlying work accidents in the construction industry. The findings demonstrate the effectiveness of the proposed approach in forecasting future accident numbers with a high degree of precision. The neural network model successfully leverages the temporal trends and underlying factors present in the historical data. By employing an advanced neural network framework and the levenberg-marquardt algorithm, this study offers a robust methodology for predicting work accident rates across diverse job categories. The results obtained from this study can guide the development of targeted preventive measures, tailored training programs, and efficient resource allocation strategies.

关键词： construction industry construction management future prediction levenberg–marquardt algorithm neural network fitting project management safety & hazards work accidents

来源：评论

学校读者我要写书评

暂无评论

Numerical Investigation of Optimization algorithms for Adapting the Hydrodynamic Model Based on the Results of Well Tests

引用

Mathematical Models and Computer Simulations 2023年第2期15卷 289-296页

作者： Maykov, D.N. Makarov, S.S. SIAM MASTER Ltd Izhevsk Russian Federation Udmurt Federal Research Center Ural Branch Russian Academy of Sciences Izhevsk Russian Federation

Abstract: This study presents a numerical investigation of optimization algorithms for the adaptation of hydrodynamic models based on well test results. The considered optimization algorithms are based on the levenberg–marquardt (LM) method and have differences in the updating method of the Hessian’s main diagonal and the calculation of the Jacobian. Two algorithms are presented in the pseudocode form, which allow us to configure variations of the LM method. Functions that transform the unconditional LM optimization into a conditional one are proposed. A comparative analysis of the speed and quality of the calculation for well bottom flow rates for ten wells with a different type of profile in terms of the number of analytical model function calls, calculation time, and average relative error show positive results when using the proposed numerical optimization algorithms. © 2023, Pleiades Publishing, Ltd.

关键词： adaptation of the hydrodynamic model Broyden’s method Hessian update levenberg–marquardt algorithm numerical investigation pressure transient analysis search with bounds

来源：评论

学校读者我要写书评

暂无评论

A novel sensitivity-based method for damage detection of a structural element

引用

Asian Journal of Civil Engineering 2020年第6期21卷 1079-1093页

作者： Amiri, H.R. Esfandiari, M.J. Dehghan Manshadi, S.H. Urgessa, G. Department of Civil Engineering Yazd Branch Islamic Azad University Yazd Iran Department of Civil Environmental and Infrastructure Engineering George Mason University Fairfax VA United States

A novel and efficient method is presented for identifying the location and severity of damage in structural elements using vibration modes and circular natural frequency. This method is based on sensitivity analysis of the structure and allows for model updating of a given structural finite element construct using the iterative process of the levenberg–marquardt algorithm. The proposed approach is superior in its capability of locating and estimating the severity of structural damage in the presence of noise or incomplete response. The efficiency and performance of the proposed method are assessed through numerical case studies. © 2020, Springer Nature Switzerland AG.

关键词： Damage detection Finite element method Inverse problems levenberg–marquardt algorithm Model updating Optimization Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Extraction, analysis and desaturation of gmelina seed oil using different soft computing approaches

引用

South African Journal of Chemical Engineering 2016年 22卷 6-16页

作者： Uzoh, F. Chigozie Onukwuli, D. Okechukwu Chemical Engineering Department Faculty of Engineering Nnamdi Azikiwe University Awka Nigeria

Artificial Neural Network (ANN)-Genetic algorithm (GA) interface and Response Surface Methodology (RSM) have been compared as tools for simulation and optimization of gmelina seed oil extraction process. A multi-layer feed-forward levenberg marquardt back-propagation algorithm was incorporated for developing a predictive model which was optimized using GA. Design Expert simulation and optimization tools were also incorporated for a detailed simulation and optimization of the same process using Response surface methodology (RSM). It was found that oil yield increased with rise in temperature, time and volume of solvent but decreased with increase in seed particle size. The maximum oil yield obtained using the numerical optimization techniques show that 49.2% were predicted by the RSM at the optimum conditions of;60 °C temperature, extraction time 60 min, 150 μm seed particle size, 150 ml solvent volume and 49.8% by ANN-GA at extraction temperature 40 °C, extraction time 40 min, 200 μm seed particle size, 100 ml solvent volume, respectively. The prediction accuracy of both models were more than 95%. Models validation experiments indicate that the predicted and the actual were in close agreement. The extract was analyzed to examine its physico-chemical properties (acid value, iodine value, peroxide value, viscosity, saponification value, moisture and ash content, refractive index, smoke, flash and fire points and specific gravity) and structural elucidation by standard methods and instrumental techniques. Results revealed that the oil is non-drying and edible. Desaturation of the oil further reveal its potential in alkyd resin synthesis. © 2016 The Authors

关键词： Artificial neural network Genetic algorithm Gmelina seed oil levenberg–marquardt algorithm Optimization Response surface methodology

来源：评论

学校读者我要写书评

暂无评论

A Preconditioned Krylov Subspace Iterative Methods for Inverse Source Problem by Virtue of a Regularizing LM-DRBEM

引用

International Journal of Applied and Computational Mathematics 2020年第4期6卷 1-17页

作者： El Madkouri, Abdessamad Ellabib, Abdellatif FST LAMAI UCA Av. Abdelkarim Elkhattabi B.P. 549 Marrakech 40000 Morocco

In this paper, we investigate an effectual methodology to solve the problem of identifying the source term standing on a combined discontinuous dual reciprocity boundary element method with a regularized levenberg–marquardt algorithm. The mathematical model is described by optimizing the variation between the measured potential in some points within the problem domain and the estimated one by the discontinuous dual reciprocity boundary element approximation. To provide a qualitative evaluation, the derived dense and non symmetric matrix system of the forward problem is solved by virtue of the LU factorization and using some preconditioned Krylov subspace iterative algorithms, expressly the biconjugate gradient stabilized, the generalized minimum residual and the squared conjugate gradient method. Due to noise interference, a regularized levenberg–marquardt algorithm is adopted to retrieve the unknown source term. Extensive experiments evince greater effectiveness and stability criteria of the proposed approach. © 2020, Springer Nature India Private Limited.

关键词： Boundary element method Inverse problem Krylov subspace levenberg–marquardt algorithm Preconditioned iterative methods Source term recovery

来源：评论

学校读者我要写书评

暂无评论

Robust Control Design of Active Suspension System for Quarter Car with Neural Network and Ziegler–Nichols Tuning Method 6th

Robust Control Design of Active Suspension System for Quarte...

引用

6th International Conference on Advanced Production and Industrial Engineering, ICAPIE 2021

作者： Saifi, Danish Kumar, Pramod Department of Mechanical Engineering Galgotias University Uttar Pradesh Greater Noida203201 India

ISBN: (纸本)9789811696121

The primary aim of this type of Active suspensions system is to overcome the excitation of the road. It can be improved riding by controlling the accumulator force. The suspension absorbs high vibration which is come from the road to the car tire. In short, due to mathematical modal may, aspect can be computed or evaluated like constant road handling, smooth-riding, and much more possibility factor. A nonlinear surface is important for changing the system damping. The main goals are to keep smooth riding from irregular road profile. A neural network and a PID controller are used to control the Quarter car model. The levenberg–marquardt method with 10 neurons can provide the best results or many according to the requirement. Also known as damp least squares are a levenberg–marquardt algorithm. With the help of a Neural Network (NN), a steady-state error can be reduced. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Active suspension system levenberg–marquardt algorithm Neural network Overshooting PID controller Quarter car

来源：评论

学校读者我要写书评

暂无评论

Real-time prediction of waves using neural networks trained by particle swarm optimization

引用

Journal of Ocean and Climate 2016年第2期7卷 70-79页

作者： Deepthi I Gopinath GS Dwarakish Department of Applied Mechanics and Hydraulics National Institute of Technology Karnataka Mangalore India

This work investigates the strength of artificial neural network that is trained by an optimization technique called particle swarm optimization in the task of time series prediction of weekly and monthly significant wave heights. The suggested approach has been implemented at the location of New Mangalore Port in India. Three years of wave data measured during 2005–2007 are analyzed. It is found that the network trained with the help of the particle swarm optimization produces more accurate predictions of the significant wave heights and further with lesser amount of data than the traditionally trained feed-forward back-propagation network.

关键词： Artificial neural network feed-forward back-propagation particle swarm optimization levenberg–marquardt algorithm

来源：评论

学校读者我要写书评

暂无评论

Handwritten optical character recognition by hybrid neural network training algorithm

引用

The Journal of Photographic Science 2019年第7期67卷 359-373页

ABSTRACTABSTRACTHandwritten optical character recognition (OCR) is the renowned research area in several fields, like writers identification, bank cheques, and so on. Literature works presented the handwritten OCR for various languages. This paper proposes a hybrid neural network training algorithm for English handwritten OCR. Initially, the noise in the input image is removed using the median filter, and the image is resized. Then, the feature sets, positional, and structural descriptors are extracted from the input image. Once the feature sets are extracted, the proposed FLM-based neural network identifies the handwritten character. The FLM proposed by combining the Firefly and the levenberg–marquardt (LM) algorithm for training the neural network. Finally, the proposed FLM-based neural network is integrated within the feed forward neural network, and the classification of character is done with 95% accuracy based on the size of training data, number of hidden neurons and number of hidden layers.

关键词： FLM based neural network H-descriptors D-descriptors firefly algorithm levenberg–marquardt algorithm Optical Character Recognition median filter Feed forward neural network

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：