检索结果-内蒙古大学图书馆

Drying process modelling based on improved backpropagation algorithm

IFAC Proceedings Volumes 1999年第2期32卷 5082-5086页

作者： Tao Wu Xiaoming Xu Zhe Zhang Dengying Liu Department of Automation Shanghai Jiaotong University Shanghai 200030 P. R. China Institute of Engineering Thermophysics Chinese Academy of Sciences Beijing 100080 P. R. China

An improved backpropagation algorithm to simultaneously determine the optimal learning rate and momentum coefficient is applied to model the impingement stream drying process. Simulation results show that for those new-style high-efficient dryers which can not be modelled based on the motion as well as heat and mass transfer of products during drying, the neural network model given in this paper is capable of predicting the behavior of the dryers exactly and rapidly.

关键词： Neural networks Modelling Optimal backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Positive and Negative Recognition of Watch Shell Blank Using backpropagation algorithm Based on Matlab

Positive and Negative Recognition of Watch Shell Blank Using...

引用

International Conference on Intelligent Human-Machine Systems and Cybernetics

作者： Ying Xi Shuyuan Leng Mengru Li Xuanquan Wu School of Mechanical Engineering Tongji University Shanghai China

In this paper, a machine vision recognition method for identifying the two sides of a watch shell used for mechanical arm loading and unloading is present, aiming at many problems such as the production efficiency, failure rate and labor injury caused by manual loading and unloading in the process of watch shell processing. Because the traditional method of image feature extraction is difficult to recognize two sides, the backpropagation algorithm of neural network is used to identify the positive and negative of the watch shell. The algorithm is realized by programming in Matlab, used on the collected picture of the watch shell, and good experimental results have been obtained.

关键词： Watch shell loading and unloading Machine vision Neural network backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

A highly efficient implementation of a backpropagation learning algorithm using matrix ISA

引用

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING 2008年第7期68卷 949-961页

作者： Soliman, Mostafa I. Mohamed, Samir A. S Valley Univ Comp & Control Sect Dept Elect Engn Fac Engn Aswan Egypt

backpropagation (BP) is the most famous learning algorithm for Artificial Neural Networks (ANN). BP has received intensive research efforts to exploit its parallelism in order to reduce the training time for complex problems. A modified version of BP based on matrix-matrix multiplication was proposed for parallel processing. In this paper, we present the implementation of Matrix backpropagation (MBP) using scalar, vector, and matrix Instruction Set Architectures (ISAs). Besides this, we show that the performance of the MBP is improved by switching from scalar ISA to vector ISA. It is further improved by switching from vector ISA to matrix ISA. On a practical application, speech recognition, the speedup of training a neural network using unrolling scalar ISA over scalar ISA is 1.83. On eight parallel lanes, the speedups of using vector, unrolling vector, and matrix ISAs are respectively 10.33, 11.88, and 15.36, where the maximum theoretical speedup is 16. The results obtained show that the use of matrix ISA gives a performance close to optimal, because of reusing the loaded data, decreasing the loop overhead, and overlapping the memory operations with arithmetic operations. (c) 2008 Elsevier Inc. All rights reserved.

关键词： neural networks parallel architecture vector/matrix processing parallel algorithms backpropagation algorithm reusing data loop unrolling

来源：评论

学校读者我要写书评

暂无评论

Design of layered‐neural nonlinear filters using backpropagation algorithm

引用

Electronics and Communications in Japan (Part III: Fundamental Electronic Science) 1992年第1期75卷 9-19页

作者： Arakawa, Kaoru Harashima, Hiroshi School of Science and Technology Meiji University Kawasaki 214 Japan Faculty of Engineering The University of Tokyo Tokyo 113 Japan

The signal such as an image signal is a non‐Gaussian signal with an abrupt change. When a random noise is superposed on such a signal, it is impossible to eliminate the noise effectively by using the traditional linear filter. Then it is desired to develop a nonlinear filter. From such a viewpoint, this paper proposes a nonlinear digital filter using a layered neural network, aiming at the elimination of such a noise. By thus introducing the nonlinearity and the learning ability of the layered neural network, the noise can effectively be eliminated. In this paper, the noise elimination is shown for the case of a one‐dimensional test signal and a two‐dimensional image signal indicating the usefulness. Copyright © 1992 Wiley Periodicals, Inc., A Wiley Company

关键词： backpropagation algorithm digital signal processing image restoration neural network Nonlinear digital filter signal estimation

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Parallel backpropagation Learning algorithm for Multilayer Perceptrons

An Enhanced Parallel Backpropagation Learning Algorithm for ...

引用

7th World Congress on Intelligent Control and Automation

作者： Ting, Li Min, Wu Cent S Univ Sch Informat Sci & Engn Changsha Hunan Peoples R China

ISBN: (纸本)9781424421138

backpropagation learning algorithm for multilayer perceptrons (MLPs) has disadvantages of slow convergence and easily being trapped into local optimum. Inspired by efficient global searching ability of particle swarm optimization (PSO), a novel PSO based backpropagation learning algorithm (PSO-BP) is proposed. At first, training procedure for MLPs is formulated as nonlinear optimization problem that can be processed by PSO. Then, combination of PSO learning and BP learning is used to train architecture and weights of MLPs. By using particle update equations, PSO learning provides optimal architecture and weights under the condition of input and desired output that are known. BP learning provides optimal weights of MLPs under the condition of given architecture and initial weights that have been set by PSO learning. The proposed learning algorithm is applied to load forecasting in electric power system. Test results show that the proposed algorithm can effectively avoid to be trapped into local optimum and has faster convergence speed than BP algorithm.

关键词： Neural network Multilayer perceptrons Particle swarm optimization backpropagation algorithm Genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Genetic algorithm (GA)-backpropagation (BP) network approach for hardness prediction of austempered ductile iron (ADI)

引用

MATERIALS SCIENCE AND TECHNOLOGY 2025年第3期41卷 210-220页

作者： Li, Pengchun Du, Yuzhou Zhang, Min Yang, Qian Liu, Chen Wang, Xin Zhang, Ruochen Jiang, Bailing Xian Univ Technol Sch Mat Sci & Engn Xian 710048 Peoples R China

Hardness serves as a crucial indicator for assessing the success of quenching treatment in the steel and iron industry, impacting the processability and wear properties of materials. In the present study, a dataset comprising 125 hardness values of the QT500-7 sample subjected to various austempering heat treatment parameters was utilised to train a neural network model for predicting the hardness of austempered ductile iron (ADI). The established model based on a genetic algorithm and error backpropagation algorithm demonstrates high accuracy in predicting the hardness of ADI if given heat treatment parameters. The mean square error of the model was about 1.019, indicating the reliability and precision of the model in predicting the hardness of ADI based on the specified heat treatment parameters.

关键词： Austempered ductile iron hardness backpropagation algorithm genetic algorithm prediction

来源：评论

学校读者我要写书评

暂无评论

A machine learning approach for clustered data

引用

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION 2025年第2期54卷 406-416页

作者： Wang, Jing Univ Utah Dept Family & Prevent Med Salt Lake City UT 84112 USA

Artificial neural networks (NNs) are a machine learning algorithm that have been used as a convenient alternative of conventional statistical models, such as regression in prediction and classification because of their capability of modeling complex relationships between dependent and independent variables without a priori assumptions about the model form and variable distributions. However, traditional NNs cannot incorporate dependencies of data with a clustering or nesting structure involved in longitudinal studies and cluster sampling. This research is intended to fill this literature gap by integrating the random-effects structure into NNs to account for within-cluster correlations. The proposed NN method incorporating random effects (NNRE) is trained by minimizing the cost function using the backpropagation algorithm combined with the quasi-Newton and gradient descent algorithms. Model overfitting is controlled by using the L2 regularization method. The trained NNRE model is evaluated for prediction accuracy by using the leaving-one-out cross-validation for both simulated and real data. Prediction accuracy is compared between NNRE and two existing models, the conventional generalized linear mixed model (GLIMMIX) and the generalized neural network mixed model (GNMM), using simulations and real data. Results show that the proposed NNRE results in higher accuracy than both the GLIMMIX and GNMM.

关键词： Artificial neural networks backpropagation algorithm Clustered data Generalized linear mixed model Leaving-one-out-cross-validation Overfitting regularization

来源：评论

学校读者我要写书评

暂无评论

Optical modeling, solver, and design of macroscopic single-enantiomer carbon nanotube film and reconfigurable chiral photonic device

引用

CARBON 2025年 235卷

作者： Fan, Jichao Hillam, Benjamin Guo, Cheng Fujinami, Hiroyuki Shiba, Koki Xie, Haoyu Chen, Ruiyang Yanagi, Kazuhiro Gao, Weilu Univ Utah Dept Elect & Comp Engn 50 S Cent Campus Dr Salt Lake City UT 84112 USA Stanford Univ Dept Appl Phys 348 Via Pueblo Stanford CA 94305 USA Tokyo Metropolitan Univ Dept Phys 1-1 Minami Osawa Hachioji Tokyo 1920397 Japan

The interaction of circularly polarized light with chiral matter and functional devices enables novel phenomena and applications. Recently, macroscopic solid-state single-enantiomer carbon nanotube (CNT) films have become feasible and are emerging as a chiral photonic material platform thanks to their quantum-confinement- induced optical properties and facile scalable assembly. However, optical modeling, solver, and device design tools for such materials are non-existent. Here, we prepare macroscopic single-enantiomer (6,5) and (11,-5) randomly oriented CNT films and create an optical material model based on measured experimental optical spectra. We also implement a highly-parallel graphic-processing-unit accelerated transfer matrix solver for general bi-anisotropic materials and layered structures. Further, we demonstrate reconfigurable chiral photonic devices in a heterostructure with phase change materials through machine learning-enabled efficient gradient- based inverse design and optimization. Our developed full stack of a chiral photonic material and device hardware platform and a corresponding high-performance differential-programming-enabled solver opens the door for future chiral photonic devices and applications based on single-enantiomer CNT films.

关键词： Single-enantiomer carbon nanotube Transfer matrix GPU acceleration backpropagation algorithm Phase change material Reconfigurable chiral photonic devices

来源：评论

学校读者我要写书评

暂无评论

Numerical Simulation and ANN Prediction of Nano-Encapsulated PCM Slurry in a Microchannel: A Thermodynamic Analysis

引用

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2025年 1-21页

作者： Ghasemi, Hamidreza Sheikhzadeh, Ghanbar Ali Fattahi, Abolfazl Univ Kashan Fac Mech Engn Kashan Iran

The growing demand for precise and efficient thermal management in microfluidic heat exchange systems has led to increasing interest in nano-encapsulated phase change materials (NEPCMs) for enhanced heat transfer and thermal energy storage. This study performs a comprehensive numerical simulation and machine learning-based prediction of the thermo-hydrodynamic behavior of NEPCM slurries in microchannels with secondary flow passages. The research aims to quantify the influence of microchannel geometry, flow conditions (Reynolds number: 100-200), and NEPCM concentration (0-10%) on heat transfer and pressure drop characteristics. Energy and entropy analyses are conducted by applying the first and second laws of thermodynamics to assess system efficiency. Furthermore, an artificial neural network (ANN) model is trained to predict the Nusselt number and performance evaluation criterion (PEC) based on input parameters with high accuracy. The simulation results indicate that incorporating NEPCMs enhances heat transfer performance, increasing the average Nusselt number by up to 50% compared to a simple microchannel. However, this improvement comes at the cost of higher pressure drop, with the friction factor showing a variation of up to 100% across different configurations. Entropy generation analysis reveals that thermal entropy generation dominates at lower Reynolds numbers, whereas frictional entropy generation becomes significant at higher Reynolds numbers. The ANN model achieves an R2 value of 0.98, with a prediction error of less than 1.5%, demonstrating its effectiveness. These findings provide quantitative insights for optimizing microchannel-based thermal management systems, balancing heat transfer enhancement, pressure drop, and entropy generation for improved performance in microfluidic applications.

关键词： CFD NEPCM PEC Frictional and thermal entropy generation backpropagation algorithm Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis for Advancements and Challenges in Deep Learning Models for Image Processing 5th

A Comprehensive Analysis for Advancements and Challenges in ...

引用

5th International Conference on Data Science, Machine Learning and Applications

作者： Ch, Ravikumar Chary, Kalvog Prakasha Srinivas, S. Bhavani, Tedla Veeranna Chaitanya Bharathi Inst Technol Dept Artificial Intelligence & Data Sci Hyderabad Telangana India CVR Coll Engn Dept CSE Cyber Secur Hyderabad Telangana India CVR Coll Engn Dept Comp Sci & Engn Hyderabad Telangana India Vardhaman Coll Engn Dept Comp Sci & Engn Hyderabad Telangana India Sri Indu Coll Engn & Technol Dept Informat Technol Hyderabad Telangana India

ISBN: (纸本)9789819780334;9789819780310;9789819780303

Deep learning, a profound advancement in artificial intelligence, has demonstrated remarkable achievements, particularly in image processing. The rapid evolution of deep learning in architecture, training methods, and specifications has driven the expansion of image processing techniques. However, the increasing complexity of model structures challenges the effectiveness of the back propagation algorithm, and issues like the accumulation of unlabeled training data and class imbalances hinder deep learning performance. To address these challenges, there's a growing need for innovative deep models and cutting-edge computing paradigms to enable more sophisticated image content analysis. In this study, we conduct a comprehensive examination of four deep learning models utilizing Convolutional Neural Networks (CNNs), clarifying their theoretical foundations within the image processing context, opening the door for further research. CNNs are notably essential for image processing due to their ability to handle complex images effectively.

关键词： Deep learning Image processing backpropagation algorithm Convolutional Neural Networks (CNNs) Model structures

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：