检索结果-内蒙古大学图书馆

A short-term load demand forecasting: Levenberg-Marquardt (LM), bayesian regularization (BR), and scaled conjugate gradient (SCG) optimization algorithm analysis

引用

JOURNAL OF SUPERCOMPUTING 2025年第1期81卷 1-30页

作者： Uwimana, Eustache Zhou, Yatong Sall, Ndiaye Mareme Hebei Univ Technol Sch Elect & Informat Engn Tianjin 300401 Peoples R China

Electrical load forecasting is of the utmost significance in the power business since it may serve as a reference for downstream operations such as power grid dispatch, resulting in substantial financial advantages. Presently, the urban energy sector incorporates the functioning of multiple load demand clusters, which contributes to the reduction of utility grid strain. However, the integrated functioning of numerous users results in dynamic load needs, necessitating accurate electric load forecasting for monitoring operations. Load forecasting is a multifaceted task that necessitates the use of approaches beyond statistical methods. The concept of cluster load demand forecasting is a novel application that is seldom addressed in the literature. This article examines different machine learning techniques, such as linear regression, support vector machines, Gaussian process regression, and artificial neural networks (ANN), to determine the most efficient approach for predicting short-term load demand in cluster loads. The effectiveness of these solutions is evaluated by quantifying several aspects, such as error metrics and computing time. This discovery demonstrates that the artificial neural network (ANN) produces highly accurate forecasting outcomes. Furthermore, three separate optimization strategies are utilized to choose the most effective ANN training algorithm: bayesian regularization, Levenberg-Marquardt, and scaled conjugate gradient. We assess the efficacy of optimization methods by running training, testing, validation, and error analysis. The results indicate that the ANN models based on the BR and LM optimization algorithms yield the most accurate electrical load demand forecasting results.

关键词： Artificial neural networks Levenberg-Marquardt bayesian regularization SCG Short-term load demand forecasting

来源：评论

学校读者我要写书评

暂无评论

A bayesian regularization neural network procedure to solve the language learning system

引用

KNOWLEDGE-BASED SYSTEMS 2025年 310卷

作者： Sabir, Zulqurnain Khansa, Samir Baltaji, Ghida Saeed, Tareq Lebanese Amer Univ Dept Comp Sci & Math Beirut Lebanon King Abdulaziz Univ Fac Sci Dept Math Financial Math & Actuarial Sci FMAS Res Grp POB 80203 Jeddah 21589 Saudi Arabia

The aim of this research is to provide the numerical performances of the language learning system (LLS) by applying the process of bayesian regularization neural network (BRNN). The division of the mathematical LLS is provided in three categories, familiar, unknown, and mastered. A design of dataset based on the Runge-Kutta is applied to lessen the mean square error (MSE). The division of the data is performed into training as 70 %, while the data for validation uses 20 % and 10 % for testing. The proposed BRNN is provided by taking the activation sigmoid function, fifteen neurons, and optimization through bayesian regularization to solve the LLS. The correctness of the BRNN solver is observed by the comparison of literature results and the negligible absolute error. Moreover, the consistency of the BRNN is observed through the statistical performances based on state transition, regression, MSE, and error histogram.

关键词： bayesian regularization Language learning Neural networks Mean square error Numerical solutions

来源：评论

学校读者我要写书评

暂无评论

A bayesian regularization intelligent computing scheme for the fractional dengue virus model

引用

EGYPTIAN INFORMATICS JOURNAL 2025年 29卷

作者： Gupta, Manoj Bhattarakosol, Pattarasinee Guru Ghasidas Vishwavidyalaya Dept Elect Engn SoS Engn & Technol Bilaspur Chhattisgarh India Chulalongkorn Univ Fac Sci Dept Math & Comp Sci Bangkok 10330 Thailand

This research's goal is to investigate the numerical assessments of a fractional order dengue viral model (FODVM) by using the artificial intelligence procedure of bayesian regularization neural networks (BRNNs). The FO derivatives present more precise results as compared to integer order for solving the DVM. The dynamics of the mathematical DVM form is considered into five classes. The computing stochastic BRNNs approach is presented for three variations with the selection of the data as testing 13%, authentication 11% and training 76% together with sixteen hidden neurons. The result's comparison is accessible in the form of overlapping, which is based on the BRNNs approach and reference Adam solutions. However, minor absolute error around 10-05 to 10-07 enhances the worth of the proposed solver. The BRNNs approach is used to minimize the mean square error for the mathematical FO-DVM. The obtained measurements of error histograms values, and regression coefficient calculated as 1 are presented to verify the efficiency of stochastic BRNNs approach.

关键词： Fractional order Dengue virus model bayesian regularization Artificial intelligence Neural networks Adam method

来源：评论

学校读者我要写书评

暂无评论

A bayesian regularization radial basis neural network novel procedure for the fractional economic and environmental system

引用

INTERNATIONAL JOURNAL OF COMPUTER MATHEMATICS 2025年第2期102卷 280-291页

作者： Chen, Qiliang Sabir, Zulqurnain Umar, Muhammad Baskonus, Haci Mehmet Chongqing Univ Technol Sch Econ & Finance Chongqing Peoples R China Lebanese Amer Univ Dept Comp Sci & Math Beirut Lebanon Hazara Univ Dept Stat & Math Mansehra Pakistan Harran Univ Fac Educ Dept Math & Sci Educ Sanliurfa Turkiye

The motive of current work is to design a novel radial basis bayesian regularization neural network (RB-BRNN) for solving the nonlinear fractional economic and environmental system (FEES). A radial basis activation function in the hidden layers is applied by taking 20 numbers of neurons. The mathematical FEES is presented in three classes, named as cost of control accomplishment, manufacturing elements competence and technical exclusion's diagnostics cost. A reference dataset is obtained using the Adams numerical results to reduce the mean square error (MSE) by taking the data for training 70%, while 15% is used for both testing and validation. The negligible absolute error values and comparison of the solutions develop the worth of computing RB-BRNN in order to solve the nonlinear dynamics of the FEES. Error diagrams, regression values, and the MSE performances are implemented to assess the precision of the designed solver.

关键词： Fractional radial basis economic/environmental bayesian regularization neural networks

来源：评论

学校读者我要写书评

暂无评论

Machine learning application with bayesian regularization for predicting pressure drop in R134a's annular evaporation and condensation

引用

JOURNAL OF THE BRAZILIAN SOCIETY OF MECHANICAL SCIENCES AND ENGINEERING 2025年第5期47卷 1-20页

作者： Colak, Andac Batur Bacak, Aykut Karakoyun, Yakup Koca, Aliihsan Dalkilic, Ahmet Selim Nigde Omer Halisdemir Univ Dept Informat Syst & Technol TR-51240 Nigde Turkiye Yildiz Tech Univ Fac Mech Engn Dept Mech Engn TR-34349 Istanbul Turkiye Van Yuzuncu Yil Univ Engn Fac Dept Mech Engn TR-65090 Van Turkiye Istanbul Tech Univ ITU Fac Mech Engn Dept Mech Engn TR-34437 Istanbul Turkiye

The study of condensation and evaporation in plain pipes is a significant area of engineering and scientific inquiry, as it has relevance for enhancing and developing various industrial procedures. This study utilized a bayesian artificial intelligence method to determine the pressure drop in a vertically oriented plain copper pipe during R134a's annular condensation and vaporization. The heat exchanger uses R134a and water in the tube and annulus sides, in turn. The tube has an inner diameter of 8 and a length of 500 mm. The training sets for artificial neural networks comprise R134a mass fluxes within the interval of 260-515 kg/m2s for in-tube condensation and 200-405 kg/m2s for evaporation. The obtained data on pressure drop during condensation and evaporation experiments were utilized in artificial neural network analysis using a differential pressure transducer in the test section. The study randomly divided 368 and 50 data points into training (85%) and testing (15%) sets for condensation and evaporation. The bayesian method, primarily applied on this subject, effectively forecasts pressure drop during experimental condensation and evaporation. Regarding margin of deviation analyses, the models' condensation and evaporation conditions display variations of approximately +/- 7.5 and +/- 8.9%, respectively. The artificial neural network training technique was optimized to achieve minimal mean squared error values of 1.4211E-06 after 32 iterations for condensation and 1.3511E-06 after 40 iterations for evaporation. The predicted pressure drop data has a deviation of +/- 10% with the experimental one for both condensation and evaporation. The artificial neural network model produced R-values of 0.99903 and 0.98451 for condensation and evaporation, correspondingly.

关键词： Machine learning Evaporation Pressure drop Condensation bayesian regularization

来源：评论

学校读者我要写书评

暂无评论

Are bayesian regularization methods a must for multilevel dynamic latent variables models?

引用

BEHAVIOR RESEARCH METHODS 2025年第2期57卷 1-28页

作者： Andriamiarana, Vivato V. Kilian, Pascal Brandt, Holger Kelava, Augustin Eberhard Karls Univ Tubingen Methods Ctr Hausserstr 11 D-72076 Tubingen Germany

Due to the increased availability of intensive longitudinal data, researchers have been able to specify increasingly complex dynamic latent variable models. However, these models present challenges related to overfitting, hierarchical features, non-linearity, and sample size requirements. There are further limitations to be addressed regarding the finite sample performance of priors, including bias, accuracy, and type I error inflation. bayesian estimation provides the flexibility to treat these issues simultaneously through the use of regularizing priors. In this paper, we aim to compare several bayesian regularizing priors (ridge, bayesian Lasso, adaptive spike-and-slab Lasso, and regularized horseshoe). To achieve this, we introduce a multilevel dynamic latent variable model. We then conduct two simulation studies and a prior sensitivity analysis using empirical data. The results show that the ridge prior is able to provide sparse estimation while avoiding overshrinkage of relevant signals, in comparison to other bayesian regularization priors. In addition, we find that the Lasso and heavy-tailed regularizing priors do not perform well compared to light-tailed priors for the logistic model. In the context of multilevel dynamic latent variable modeling, it is often attractive to diversify the choice of priors. However, we instead suggest prioritizing the choice of ridge priors without extreme shrinkage, which we show can handle the trade-off between informativeness and generality, compared to other priors with high concentration around zero and/or heavy tails.

关键词： bayesian regularization Sparsity Dynamic latent variable models Markov switching Intensive longitudinal data

来源：评论

学校读者我要写书评

暂无评论

bayesian regularization of Neural Network to Predict Leakage Current in a Salt Fog Environment

引用

IEEE TRANSACTIONS ON DIELECTRICS AND ELECTRICAL INSULATION 2018年第2期25卷 686-693页

作者： Al Khafaf, Nameer El-Hag, Ayman RMIT Univ Sch Elect & Comp Engn Melbourne Vic Australia Amer Univ Sharjah Dept Elect Engn Sharjah U Arab Emirates

Leakage current (LC) has been monitored extensively to assess the surface conditions of both ceramic and non-ceramic insulators. It has been reported that LC is highly correlated with insulator surface damage and the occurrence of flashover. Hence, it is imperative to predict the LC future value. The objective of this paper is to use bayesian regularized neural network to predict both the fundamental and third harmonic components of LC under salt fog condition. Three different models of neural network are proposed and each is trained to predict the time series of both the fundamental and third harmonic of LC. The results have shown that there is a high correlation between the fundamental and third harmonic of LC when the nonlinearity of the leakage current increases. Moreover the future value of the LC has been successfully predicted.

关键词： Artificial Neural Network bayesian regularization Leakage Current Harmonics outdoor insulators

来源：评论

学校读者我要写书评

暂无评论

bayesian regularization: application to calibration in NIR spectroscopy

引用

JOURNAL OF CHEMOMETRICS 2009年第11-12期23卷 562-568页

作者： Alciaturi, C. E. Quevedo, G. INZIT Maracaibo Venezuela Univ Zulia LUZ Maracaibo 4011 Venezuela

The use of a bayesian regularization algorithm is proposed for calibration in near-infrared spectroscopy (NIR) with linear models. The algorithm used in this work is based upon the concepts developed by MacKay for inference and model comparison in artificial neural networks. it is demonstrated that this algorithm is fast, easy to use, and shows good generalization properties without previous dimensionality reduction. Examples are shown for NIR spectroscopy calibration and synthetic data. Copyright (C) 2009 John Wiley & Sons, Ltd.

关键词： bayesian regularization linear models calibration near-infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

bayesian regularization and nonnegative deconvolution for room impulse response estimation

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2006年第3期54卷 839-847页

作者： Lin, YQ Lee, DD Univ Penn Grasp Lab Dept Elect & Syst Engn Philadelphia PA 19104 USA

This paper proposes bayesian regularization And Nonnegative Deconvolution (BRAND) for accurately and robustly estimating acoustic room impulse responses for applications such as time-delay estimation and echo cancellation. Similar to conventional deconvolution methods, BRAND estimates the coefficients of convolutive finite-impulse-response (FIR) filters using least-square optimization. However, BRAND exploits the nonnegative, sparse structure of acoustic room impulse responses with nonnegativity constraints and L-1-norm sparsity regularization on the filter coefficients. The optimization problem is modeled within the context of a probabilistic bayesian framework, and expectation-maximization (EM) is used to derive efficient update rules for estimating the optimal regularization parameters. BRAND is demonstrated on two representative examples, subsample time-delay estimation in reverberant environments and acoustic echo cancellation. The results presented in this paper show the advantages of BRAND in high temporal resolution and robustness to ambient noise compared with other conventional techniques.

关键词： bayesian regularization echo cancellation non-negative deconvolution time-delay estimation

来源：评论

学校读者我要写书评

暂无评论

bayesian regularization neural networks for optimizing fluid flow processes

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2006年第7-8期195卷 481-500页

作者： Hirschen, K Schäfer, M TH Darmstadt Dept Numer Methods Mech Engn D-64287 Darmstadt Germany

This paper details the application of neural networks and evolutionary strategies for shape optimization problems. These, commonly grouped under the name soft computing methods, are quite recent methods and in demand for application to engineering optimization tasks. For complex problems, like in non-convex optimization, such heuristic techniques are able to outperform conventional optimization methods. We show that the use of progressive network models can yield satisfactory results when optimizing engineering relevant applications. Numerical examples are given. (c) 2005 Elsevier B.V. All rights reserved.

关键词： shape optimization neural networks bayesian regularization evolutionary algorithm

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：