检索结果-内蒙古大学图书馆

Research on Leather Defect Detection and Recognition algorithm Based on Improved multilayer perceptron

PROCESSES 2025年第5期13卷 1298-1298页

作者： Liu, Lin Li, Xizhao Wang, Ruiyu Li, Xingke Zheng, Liwang Lan, Lihua Zhao, Fangwei Li, Xibing Fujian Agr & Forestry Univ Coll Mech & Elect Engn Fuzhou 350100 Peoples R China Fujian Univ Technol Sch Management Fuzhou 350118 Peoples R China Shangdong Lab Vocat & Tech Coll Dept Intelligent Mfg Jinan 250022 Peoples R China Fujian Chengsen Grp Co Ltd Longyan 364300 Peoples R China Fujian Quanrun Construct Engn Co Ltd Longyan 364200 Peoples R China

To address the issues of manual inspection and low precision in the detection and recognition of defects in existing animal leather, this study first establishes a leather image dataset and applies an improved Gabor filtering algorithm for image preprocessing. Specifically, the weighted average method is adopted to grayscale the image, and the algorithm parameters are designed and improved to ensure that most of the key texture information of the leather images is obtained, meeting the requirements for texture feature information in subsequent feature extraction. Next, it explores statistical feature extraction algorithms based on the gray-level co-occurrence matrix and the statistical feature extraction algorithm based on gray-level distribution, forming a combination of features for the dataset. The leather defects mainly include warble fly holes, neck wrinkles, and scars. In the processing process, there are also defects such as scratches, holes, and stains. Finally, a leather defect image classification model is proposed based on a multilayer perceptron algorithm, using the ReLU activation function and a SoftMax classifier to classify surface defects in 1280 samples. The classification time is 0.0854 s, and the average precision, recall, and accuracy for leather defect image classification are all 99.53%. This solution innovatively integrates the improved Gabor filtering with the adaptive multilayer perceptron architecture to construct a multi-modal leather defect classification model, which significantly improves the detection accuracy of three types of defects, namely holes, scratches, and stains. It provides a theoretical reference for the automation of the leather processing process.

关键词： leather defect detection and recognition improved Gabor filter algorithm multilayer perceptron algorithm

来源：评论

学校读者我要写书评

暂无评论

Real-time mass estimation of connected commercial vehicle using artificial neural network model

引用

INDIAN JOURNAL OF ENGINEERING AND MATERIALS SCIENCES 2024年第3期31卷 358-373页

作者： Chandrasekaran, M. Rajesh, P. K. PSG Coll Technol Dept Automobile Engn Avinashi Rd Coimbatore 641004 Tamil Nadu India

In recent years, the automotive industry has experienced a remarkable transformation with the advent of digital technologies. The internet of things (IoT) revolutionizes the automobile industry by enabling intelligent, connected vehicles. IoT-generated data enhances vehicle safety through real-time diagnostics, predictive maintenance, and remote monitoring, reducing accidents and breakdowns. Very few studies have used IoT data thread inference in product design. Knowing the real-time mass of the vehicle is significant for design engineers during aggregate design selection and optimizing the vehicle design. This study shows a novel approach to predicting the real-time active mass of a connected medium-duty commercial truck using an artificial neural network (ANN) deep learning (DL) multilayer perceptron (MLP) deep learning algorithm. In this process, the raw data collected from the vehicle is cleaned, and the vehicle's mass is estimated by applying the vehicle dynamics system longitudinal forces model. Different load conditions of the vehicle are calculated with an accuracy of 87%. Later, the estimated mass with the five mass-influencing operating parameters from the data is used as an input in the MLP deep learning model to predict the vehicle's mass as output. The model is trained and tested using overload, rated load, and no-load conditions;when testing the model using the real-time operating parameters, the deep learning model predicted the mass with >90% accuracy. This deep learning model, when integrated into the data-driven digital twin framework, will be instrumental in controlling various actuators based on the predicted mass in future work. Moreover, the predicted real-time active mass is not only helpful for the optimum design of many vehicle systems but also for building application-based design configurations, thereby demonstrating the practical relevance and potential applications of this research in vehicle design and control systems.

关键词： Data-driven vehicle design Longitudinal vehicle dynamics model Mass prediction Medium-duty truck multilayer perceptron algorithm

来源：评论

学校读者我要写书评

暂无评论

Radial Basis Function (RBF) and multilayer perceptron (MLP) Comparative Analysis on Building Renovation Cost Estimation: The Case of Greece

引用

algorithmS 2024年第9期17卷 390页

作者： Papadimitriou, Vasso E. Aretoulis, Georgios N. Papathanasiou, Jason Aristotle Univ Thessaloniki Aristotle Univ Thessaloniki Campus Fac Engn Sch Civil Engn Thessaloniki 54124 Greece Univ Macedonia Dept Business Adm Thessaloniki 54124 Greece

Renovation of buildings has become a major area of development for the construction industry. In the building construction sector, generating a precise and trustworthy cost estimate before building begins is the greatest challenge. Emphasizing the value of using ANN models to forecast the total cost of a building renovation project is the ultimate objective. As a result, building firms may be able to avoid financial losses as long as there is as little discrepancy between projected and actual costs for remodeling works in progress. To address the gap in the research, Greek contractors specializing in building renovations provided a sizable dataset of real project cost data. To build cost prediction ANNs, the collected data had to be organized, assessed, and appropriately encoded. The network was developed, trained, and tested using IBM SPSS Statistics software 28.0.0.0. The dependent variable is the final cost. The independent variables are initial cost, estimated completion time, actual completion time, delay time, initial and final demolition-drainage costs, cost of expenses, initial and final plumbing costs, initial and final heating costs, initial and final electrical costs, initial and final masonry costs, initial and final construction costs of plasterboard construction, initial and final cost of bathrooms, initial and final cost of flooring, initial and final cost of frames, initial and final cost of doors, initial and final cost of paint, and initial and final cost of kitchen construction. The first procedure that was employed was the radial basis function (RBF). The efficiency of the RBFNN model was evaluated and analyzed during training and testing, with up to 6% sum of squares error and nearly 0% relative error in the training sample, which accounted for roughly 70% of the total sample. The second procedure implemented was the method called the multi-layer perceptron (MLP). The efficiency of the MLPNN model was assessed and examined during training and te

关键词： building cost estimation models artificial neural network multilayer perceptron algorithm radial basis function algorithm buildings renovation cost estimation

来源：评论

学校读者我要写书评

暂无评论

Design investigation on 100 gm-thickness thin silicon PERC solar cells with assistance of machine learning

引用

MATERIALS SCIENCE IN SEMICONDUCTOR PROCESSING 2022年 137卷

作者： Zhu, Heng Yan, Wensheng Liu, Yiming Hu, Die Tu, Yiteng Huang, Zhengtao Tan, Xinyu China Three Gorges Univ Hubei Prov Engn Technol Res Ctr Microgrid Coll Elect Engn & New Energy 8 Univ Ave Yichang 443002 Peoples R China

Thin crystalline silicon passivated emitter and rear cell (PERC) solar cells are a very prospective technology for next-phase photovoltaic development due to the potential of high cost effectiveness. The reduction of silicon wafer thickness can significantly save the costs, but there is a loss of cell efficiency if cell design is not conducted. For the thinned 100 gm-thickness PERC solar cells without design, the efficiency loss is pronounced from commercial 180 gm-thickness. In this paper, we have designed and optimized SiO2/SiNx/SiNx/SiOx thin films (here two SiNx layers have different refractive index) on the front surface and SiNx/SiOx thin films on the back surface for the standard front single-sided textured PERC cells. Based on this, we further design and investigate the case of double-sided textured PERC solar cells. Compared with the reference cell, the present designs can lead to the short-circuit current density increase by 0.6 mA/cm2 and the open-circuit voltage enhancement by 10 mV for the front textured case, which causes the efficiency gain of 0.7% from 21.6% to 22.3%. For the double-sided textured cells, the efficiency has an extra increase of 0.6% from 22.3% to 22.9%. Finally, we have constructed the efficiency prediction model by using the multilayer perceptron algorithm in machine learning. It is found from the SHAP values that a significant effect of the front SiNx thickness is observed to predict the performance of the PERC cells.

关键词： Solar cells Passivated emitter and rear cell (PERC) Optical and electrical designs Machine learning multilayer perceptron algorithm

来源：评论

学校读者我要写书评

暂无评论

Internet Banking Fraud Detection Using Deep Learning Based on Decision Tree and multilayer perceptron 6

Internet Banking Fraud Detection Using Deep Learning Based o...

引用

6th International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Kataria, Sonal Nafis, Md Tabrez Jamia Hamdard Dept Comp Sci & Engn New Delhi India

ISBN: (纸本)9789380544342

Fraud transactions have become a growing problem in the online banking sphere. As technology progresses, fraudsters also change their methods of committing fraud. There are also emerging technologies that allow fraudsters to mimic the transaction behavior of genuine customers and they also keep changing their methods so that it is difficult to detect fraud. This paper discusses the importance of fraud detection methods and compares Hidden Markov Model, Deep Learning, and Neural Network that are used to detect fraud in online banking transactions.

关键词： fraud detection online banking fraud detection neural network online banking fraud deep learning artificial neural network decision tree multilayer perceptron algorithm three layer perceptron

来源：评论

学校读者我要写书评

暂无评论

Theory, Analyses and Predictions of Multifractal Formalism and Multifractal Modelling for Stroke Subtypes' Classification 20th

Theory, Analyses and Predictions of Multifractal Formalism a...

引用

20th International Conference on Computational Science and Its Applications (ICCSA)

作者： Karaca, Yeliz Baleanu, Dumitru Moonis, Majaz Zhang, Yu-Dong Univ Massachusetts Med Sch Worcester MA 01655 USA Cankaya Univ Dept Math TR-1406530 Ankara Turkey Inst Space Sci Bucharest Romania Univ Leicester Dept Informat Leicester LE1 7RH Leics England

ISBN: (纸本)9783030588021;9783030588014

Fractal and multifractal analysis interplay within complementary methodology is of pivotal importance in ubiquitously natural and man-made systems. Since the brain as a complex system operates on multitude of scales, the characterization of its dynamics through detection of self-similarity and regularity presents certain challenges. One framework to dig into complex dynamics and structure is to use intricate properties of multifractals. Morphological and functional points of view guide the analysis of the central nervous system (CNS). The former focuses on the fractal and self-similar geometry at various levels of analysis ranging from one single cell to complicated networks of cells. The latter point of view is defined by a hierarchical organization where self-similar elements are embedded within one another. Stroke is a CNS disorder that occurs via a complex network of vessels and arteries. Considering this profound complexity, the principal aim of this study is to develop a complementary methodology to enable the detection of subtle details concerning stroke which may easily be overlooked during the regular treatment procedures. In the proposed method of our study, multifractal regularization method has been employed for singularity analysis to extract the hidden patterns in stroke dataset with two different approaches. As the first approach, decision tree, Naive bayes, kNN and MLP algorithms were applied to the stroke dataset. The second approach is made up of two stages: i) multifractal regularization (kulback normalization) method was applied to the stroke dataset and mFr stroke dataset was generated. ii) the four algorithms stated above were applied to the mFr stroke dataset. When we compared the experimental results obtained from the stroke dataset and mFr stroke dataset based on accuracy (specificity, sensitivity, precision, F1-score and Matthews Correlation Coefficient), it was revealed that mFr stroke dataset achieved higher accuracy rates. Our novel prop

关键词： Multifractal Formalism Fractional brownian motion Hurst exponent Fractal pattern Self-similar process Stroke Prediction algorithms Naive Bayes algorithm kNN algorithm multilayer perceptron algorithm Multifractal regularization

来源：评论

学校读者我要写书评

暂无评论

Predicting rank for scientific research papers using supervised learning

引用

Applied Computing and Informatics 2019年第2期15卷 182-190页

作者： El Mohadab, Mohamed Bouikhalene, Belaid Safi, Said Department of Mathematics and Informatics Laboratory of Innovation in Mathematics and Application and Information Technologies (LIMATI) Polydisciplinary Faculty Sultan Moulay Slimane University PB 592 Beni Mellal Morocco

Automatic data processing represents the future for the development of any system, especially in scientific research. In this paper, we describe one of the automatic classification methods applied to scientific research as a supervised learning task. Throughout the process, we identify the main features that are used as keys to play a significant role in terms of predicting the new rank under the supervised learning setup. First, we propose an overview of the work that has been realized in ranking scientific research papers. Second, we evaluate and compare some of state-of-the-art for the classification by supervised learning, semi-supervised learning and non-supervised learning. During the preliminary tests, we have obtained good results for performance on realistic corpus then we have compared performance metrics, such as NDCG, MAP, GMAP, F-Measure, Precision and Recall in order to define the influential features in our work. © 2018 The Authors

关键词： Data mining multilayer perceptron algorithm Ranking scientific research papers Scientific research Supervised learning

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：