检索结果-内蒙古大学图书馆

An algorithm for outlier detection in a time series model using backpropagation neural network

JOURNAL OF KING SAUD UNIVERSITY SCIENCE 2020年第8期32卷 3328-3336页

作者： Vishwakarma, Gajendra K. Paul, Chinmoy Elsawah, A. M. Indian Inst Technol Dhanbad Dept Math & Comp Dhanbad 826004 Bihar India Pandit Deendayal Upadhyaya Adarsha Mahavidyalaya Dept Stat Eraligool 788723 Karimganj India Beijing Normal Univ United Int Coll Hong Kong Baptist Univ Div Sci & Technol Zhuhai 519085 Peoples R China Zagazig Univ Fac Sci Dept Math Zagazig 44519 Egypt

Outliers are commonplace in many real-life experiments. The presence of even a few anomalous data can lead to model misspecification, biased parameter estimation, and poor forecasts. Outliers in a time series are usually generated by dynamic intervention models at unknown points of time. Therefore, detecting outliers is the cornerstone before implementing any statistical analysis. In this paper, a multivariate out-lier detection algorithm is given to detect outliers in time series models. A univariate time series is transformed to bivariate data based on the estimate of robust lag. The proposed algorithm is designed by using robust measures of location and dispersion matrix. Feed forward neural network is used for designing time series models. Number of hidden units in the network is determined based on the standard error of the forecasting error. A comparison study between the proposed algorithm and the widely used algorithms is given based on three real-data sets. The results demonstrated that the proposed algorithm out-performed the existing algorithms due to its non-requirement of a priori knowledge of the time series and its control of both masking and swamping effects. We also discussed an efficient method to deal with unexpected jumps or drops on share prices due to stock split and commodity prices near contract expiry dates. (C) 2020 Published by Elsevier B.V.

关键词： Multivariate outliers Detection Neural network Robust estimate Time series backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of MLP Networks Using backpropagation algorithms in Electrical Equipment Thermography

引用

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2014年第5期39卷 3873-3885页

作者： Huda, A. S. Nazmul Taib, Soib Univ Sains Malaysia Sch Elect & Elect Engn Nibong Tebal 14300 Pulau Pinang Malaysia

Nowadays, infrared thermographic inspection has increasingly been utilized for fault diagnosis tools of electrical equipment, because it maintains non-interrupting operation of power system and ensures early diagnosis of faults. The article discusses the performance comparison of multilayer perceptron (MLP) networks using various backpropagation algorithms for thermal imaging-based condition monitoring of electrical hotspots. The training algorithms are Levenberg-Marquardt, Broyden-Fletcher-Goldfarb-Shanno quasi-Newton, resilient backpropagation, gradient descent with momentum and adaptive learning rate and standard gradient descent training algorithms. The performance of the training algorithms are evaluated in terms of percentage of accuracy, sensitivity, specificity, false-positive and false-negative results. In the beginning, thermal images of electrical equipment are captured using infrared camera. Six statistical intensity features, namely mean, maximum, minimum, median, standard deviation and variance extracted from each hotspot of equipment thermal image are used as the inputs of multilayered perceptron networks to classify the thermal conditions of hotspots into two classes, namely normal and defective. The comparison of MLP networks using training algorithms proves that the MLP network trained with resilient backpropagation algorithm gives the best performance in thermal condition recognition.

关键词： Electrical hotspots Thermography backpropagation algorithm MLP network

来源：评论

学校读者我要写书评

暂无评论

Modified Mean Square Error algorithm with Reduced Cost of Training and Simulation Time for Character Recognition in backpropagation Neural Network

Modified Mean Square Error Algorithm with Reduced Cost of Tr...

引用

2nd International Conference on Frontiers in Intelligent Computing - Theory and Applications (FICTA)

作者： Singh, Sapna Singh, Daya Shankar Kumar, Shobhit Madan Mohan Malaviya Engn Coll Comp Sci & Engn Dept Gorakhpur Uttar Pradesh India Manyawar Kanshiram Inst Engn Informat Technol Dept Informat Technol Akbarpur India

ISBN: (纸本)9783319029313;9783319029306

Neural Network concept is based on "Learn by example". Mean square error function is the basic performance function which affects the network directly. Reducing of such error will result in an efficient system. The paper proposes a modified mean squared error value while training backpropagation (BP) neural networks. The new cost function is referred as Arctan mean square error (AMSE). The formula computed prove that the modification of MSE is optimal in the sense of reducing the value of error for an asymptotically large number of statistically independent training data patterns. The results shows improved network with reduced error value along with increment in performance consequently.

关键词： backpropagation algorithm Mean square error algorithm neural network

来源：评论

学校读者我要写书评

暂无评论

Selection of Network Parameters in Direct ANN Modeling of Roughness Obtained in FFF Processes

引用

POLYMERS 2025年第1期17卷 120-120页

作者： Buj-Corral, Irene Sivatte-Adroer, Maurici Rodero-de-Lamo, Lourdes Marco-Almagro, Lluis Univ Politecn Cataluna Barcelona Sch Ind Engn ETSEIB Dept Mech Engn Ave Diagonal 647 Barcelona 08028 Spain Univ Politecn Cataluna Polytech Sch Engn Vilanova & Geltru EPSEVG Dept Mech Engn Ave Victor Balaguer 1 Vilanova I La Geltru 08880 Spain Univ Politecn Catalunya UPC Barcelona Sch Ind Engn ETSEIB Dept Stat & Operat Res Av Diagonal 647 Barcelona 08028 Spain

Artificial neural network (ANN) models have been used in the past to model surface roughness in manufacturing processes. Specifically, different parameters influence surface roughness in fused filament fabrication (FFF) processes. In addition, the characteristics of the networks have a direct impact on the performance of the models. In this work, a study about the use of ANN to model surface roughness in FFF processes is presented. The main objective of the paper is discovering how key ANN parameters (specifically, the number of neurons, the training algorithm, and the percentage of training and validation datasets) affect the accuracy of surface roughness predictions. To address this question, 125 3D printing experiments were conducted changing orientation angle, layer height and printing temperature, and measuring average roughness Ra as response. A multilayer perceptron neural network model with backpropagation algorithm was used. The study evaluates the effect of three ANN parameters: (1) number of neurons in the hidden layer (4, 5, 6 or 7), (2) training algorithm (Levenberg-Marquardt, Resilient backpropagation or Scaled Conjugate Gradient), and (3) data splitting ratios (70%-15%-15% vs. 55%-15%-30%). Mean Absolute Error (MAE) was used as the performance metric. The Resilient backpropagation algorithm, 7 neurons, and using 55% of training data yielded the best predictive performance, minimizing the MAE. Additionally, the impact of the dataset size on prediction accuracy was analysed. It was observed that the performance of the ANN gets worse as the number of datasets is reduced, emphasizing the importance of having sufficient data. This study will help to select appropriate values for the printing parameters in FFF processes, as well as to define the characteristics of the ANN to be used to model surface roughness.

关键词： FFF FDM Polylactic acid artificial neural networks surface roughness training algorithm number of neurons datasets distribution multilayer perceptron backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

backpropagation and Levenberg-Marquardt algorithm for Training Finite Element Neural Network

Backpropagation and Levenberg-Marquardt Algorithm for Traini...

引用

6th UKSim/AMSS European Symposium on Computer Modeling and Simulation (EMS)

作者： Reynaldi, Arnold Lukas, Samuel Margaretha, Helena Pelita Harapan Univ Fac Sci & Math Tangerang Banten Indonesia Pelita Harapan Univ Fac Comp Sci Tangerang Banten Indonesia

ISBN: (纸本)9780769549262

In this paper, finite element based neural network is developed. The purpose is to solve differential equation and inverse problem of differential equation. Inverse problem of differential equation is a problem to solve for parameters of differential equation, assuming that the solution of the differential equation is already known beforehand. Inverse problem mainly used to approximate physical parameters of material. Finite element method will be combined with artificial neural network using backpropagation algorithm to solve differential equation and Levenberg-Marquardt training algorithm to solve inverse differential problem. By using proposed method, invers matrix calculation will not be needed for solving both differential equation and inverse differential problem. From any given differential equation, the solution will be solved first. And the solution is used to validate the parameter in differential equation, namely to solve inverse problem of that differential equation.

关键词： finite element method artificial neural network backpropagation algorithm Levenberg-Marquardt algorithm inverse differential problem

来源：评论

学校读者我要写书评

暂无评论

Pattern Recognition Using backpropagation And Template Matching algorithm

Pattern Recognition Using Backpropagation And Template Match...

引用

2nd International conferences on Information Technology, Information Systems and Electrical Engineering (ICITISEE)

作者： Letsoin, Hendrykus S. Slarmanat, Chaken C. Z. Mirino, Antonio E. Suyoto Univ Atma Jaya Magister Informat Engn Yogyakarta Yogyakarta Indonesia

ISBN: (纸本)9781538606582

Based on the constitution no 28 In 2009 about tax areas and regional retribution on article 4, that the subject is a personal vehicle Tax or entity owns and or controlled vehicle. Every owner of a vehicle is required to be obedient to pay taxes vehicles. Intelligent systems on these applications use the collaboration of two algorithms, namely the backpropagation algorithm and template matching. The process of working application this is to start with system first taken imagery digital (scan) license plate then do segmentation to detect character which is found in the license plate the next system will match with a character is in the database and the system showing the data in accordance with the character of the license plate. The intelligent system of the work process in the application is divided into two processes namely image processing and pattern recognition. The process of image processing using the backpropagation algorithm and will continue with the process of pattern recognition using template matching method. The process of image processing using the backpropagation algorithm and will continue with the process of pattern recognition using template matching method. Images processing are consisted of binary, media filtering, slicing, and resizing. Due to the process of image processing consists of binary, the media filtering, slicing, and resizing. After that character obtained the segmentation process will be conducted to find out each character in the license plate number of the vehicle. The character which is stored at the base of data consists of 38 namely character letters A-Z, character figures 0-9, character spacing (" "), character point ("."). The application was built for the purpose of ease checking of vehicle tax online through the cell phone and can be used by various parties those who need information accurate about vehicle tax.

关键词： Pattern Recognition backpropagation algorithm Template Matching algorithms

来源：评论

学校读者我要写书评

暂无评论

Herbal Leaf Recognization Using backpropagation Artificial Neural Network algorithm 5

Herbal Leaf Recognization Using Backpropagation Artificial N...

引用

5th International Conference on Innovative Trends in Information Technology (ICITIIT)

作者： Apsara, S. Anitha, P. Aswini, R. Maheswari, N. J. Sakthi Ayya Nadar Janaki Ammal Coll Dept Comp Sci Sivakasi India

ISBN: (纸本)9798350386813;9798350386820

This study presents an approach for herbal leaf recognization using backpropagation Artificial Neural Network algorithm. The main purpose is to enhance the accuracy and efficiency of herbal leaf identification by leveraging the capabilities of BPANN. The proposed system will extract relevant features from herbal leaf images,which are then used as input data for training and testing the BPANN model. The algorithm's learning process is simplified through backpropagation which allows the network to change and optimize its parameters to improve the classification performance. The experimental results demonstrate the effectiveness of the proposed method in achieving robust herbal leaf recognization, showing its potential for application in fields such as medicine, plant sciences, agriculture management, environmental monitoring and conservation.

关键词： Preprocessing Feature extraction backpropagation algorithm Accuracy Network design

来源：评论

学校读者我要写书评

暂无评论

The Cascaded Forward algorithm for neural network training

引用

PATTERN RECOGNITION 2025年 161卷

作者： Zhao, Gongpei Wang, Tao Jin, Yi Lang, Congyan Li, Yidong Ling, Haibin Beijing Jiaotong Univ Key Lab Big Data & Artificial Intelligence Transpo Minist Educ Beijing Peoples R China Beijing Jiaotong Univ Sch Comp Sci & Technol Beijing 100044 Peoples R China SUNY Stony Brook Dept Comp Sci Stony Brook NY 11794 USA

backpropagation (BP) algorithm has played a significant role in the development of deep learning. However, there exist some limitations associated with this algorithm, such as getting stuck in local minima and experiencing vanishing/exploding gradients, which have led to questions about its biological plausibility. To address these limitations, alternative algorithms to backpropagation have been preliminarily explored, with the Forward-Forward (FF) algorithm being one of the most well-known. In this paper we propose a new learning framework for neural networks, namely Ca scaded Fo rward ( CaFo ) algorithm, which does not rely on BP optimization as that in FF. Unlike FF, CaFo directly outputs label distributions at each cascaded block and waives the requirement of generating additional negative samples. Consequently, CaFo leads to a more efficient process at both training and testing stages. Moreover, in our CaFo framework each block can be trained in parallel, allowing easy deployment to parallel acceleration systems. The proposed method is evaluated on four public image classification benchmarks, and the experimental results illustrate significant improvement in prediction accuracy in comparison with recently proposed baselines. The code is available at: https://***/Graph-ZKY/CaFo.

关键词： Deep neural network backpropagation algorithm Forward-Forward algorithm Image classification

来源：评论

学校读者我要写书评

暂无评论

Enhancing Agricultural Disease Detection: A Multi-Model Deep Learning Novel Approach

ENGINEERING REPORTS

引用

ENGINEERING REPORTS 2025年第1期7卷

作者： Hamid, Muhammad Khalid Shah, Said Khalid Husnain, Ghassan Ghadi, Yazeed Yasin Al Maaytah, Shahab Ahmad Qahmash, Ayman Bannu Univ Sci & Technol Dept Comp Sci Bannu Khyber Pakhtunk Pakistan CECOS Univ IT & Emerging Sci Dept Comp Sci Peshawar Pakistan Al Ain Univ Dept Comp Sci & Software Engn Al Ain U Arab Emirates King Faisal Univ Appl Coll Dept Languages & Humanities Alhafof Eastern Provinc Saudi Arabia King Khalid Univ Dept Informat & Comp Syst Abha Saudi Arabia

Artificial intelligence, especially deep learning, has attracted significant interest in bioinformatics, with prominent applications in precision agriculture. A significant threat to the agricultural sector is the rapid propagation of diseases from affected to healthy plants, which, if undetected, may culminate in significant crop losses. This research focusses on employing multi-model deep-learning techniques to identify diseases in the leaves of economically significant crops that are potatoes, tomatoes, grapes, apples, and peaches. These crops are widely grown and crucial for food security, with disease outbreaks threatening yield and quality. This study evaluates the performance of deep learning models, including VGG16, MobileNetV2, Xception, and ResNet, using four metrics, that is, Accuracy, Precision, Recall, and F1-Score. Furthermore, consumer research was undertaken to evaluate user trust in AI-driven multi-model systems, collecting feedback from farmers to inform future research directions. The results demonstrate that the VGG16 model outperformed all others in every evaluation criterion. Experimental simulations were performed in Jupyter Notebook utilizing Anaconda and Python. The findings indicate that the proposed multi-model approach allows a scalable, non-invasive, and contactless machine vision solution for the early detection of diseases in plant leaves, achieving an efficiency of 99% via multimodal classification techniques that incorporate statistical variables including mean, median, mode, skewness, and kurtosis.

关键词： agronomist artificial intelligence backpropagation algorithm convolutional neural network deep learning precision agriculture

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Sizing Model for Tapered Electrical Submersible Pumps Under Multiple Operating Conditions

引用

PROCESSES 2025年第4期13卷 1056-1056页

作者： Yao, Jinsong Han, Guoqing Liang, Xingyuan Wang, Mengyu China Univ Petr Coll Petr Engn Beijing 102249 Peoples R China

Dewatering gas wells typically exhibit a high gas-liquid ratio, making tapered electrical submersible pump (ESP) systems a common choice. However, the flow rate within the pump varies significantly along its length, and production parameters fluctuate considerably across different stages of operation for a gas reservoir. Traditional ESP sizing methods typically consider one single operating case and one single pump model. In contrast, tapered ESP systems require the designer to manually select and combine pump models, stage numbers, and operating frequencies based largely on experience. This process can be cumbersome and time-consuming. To address the limitations of existing ESP sizing methods, this study develops a computational program for ESP operation parameters stage by stage and generates extensive training data. A fully connected neural network (FCNN) based on the backpropagation (BP) algorithm is then trained on these data. The model can predict key parameters such as gas volume fraction (GVF) and flow rate along the pump, operating frequency, and total pump efficiency, using input data such as fluid parameters at the pump's intake and discharge, as well as pump stage numbers and performance curve data. The model demonstrates high accuracy, with a mean absolute error (MAE) of 0.3431, a mean squared error (MSE) of 0.3231, and a coefficient of determination (R2) of 0.9991. By integrating a wellbore two-phase flow model and leveraging industry experience in pump sizing, a hybrid model for automatic ESP sizing under multiple working conditions is proposed, with the objective of maximizing pump efficiency. This model enables optimal pump sizing, calculates the operating frequency corresponding to given working cases, significantly reduces the workload of designers, and enhances the overall design outcomes.

关键词： tapered ESP system backpropagation algorithm fully connected neural network hybrid model pump efficiency ESP sizing multiple working conditions

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：