检索结果-内蒙古大学图书馆

15th International Scientific and Technical Conference: Applied Mechanics and systems Dynamics, AMSD 2021

作者： Belim, S.v. Khiryanov, E.v. Kvashnina, P.A. Ostrinskaya, L.I. Omsk State Technical University 11 Mira ave Omsk644050 Russia Siberian State Automobile and Highway University Omsk Russia

Road image analysis is an important task for automatic road inventory. The determination geometric dimensions for the road and the identification road objects are subprocess of constructing a road digital image. In this article, two algorithms for solving different subtasks of automatic road image inventory are proposed. The first algorithm identifies road signs. A convolutional artificial neural network is used in this algorithm. The training set for the neural network is prepared. A computer experiment to determine the recognition effectiveness of road signs has been conducted. The second algorithm defines the edges of the pavement. The algorithm consists five stages. The edges of the road are modeled as straight lines. The result allows you to automatically determine the width of the road. © Published under licence by IOP Publishing Ltd.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

image-Based Analysis of Plate Separation and Clearance Distribution in Wet Clutches

引用

APPLIED SCIENCES-BASEL 2024年第20期14卷 9270页

作者： Pointner-Gabriel, Lukas Flamm, Simon voelkel, Katharina Stahl, Karsten Tech Univ Munich Gear Res Ctr FZG TUM Sch Engn & Design Dept Mech Engn D-85748 Garching Germany

A fundamental understanding of wet clutches' drag loss behavior is essential for designing efficient clutch systems. It has been widely recognized that the separation behavior immediately after disengaging the clutch and the resulting clearance distribution influence the drag loss behavior. However, these influencing factors have yet to be systematically investigated. Therefore, this study aimed to experimentally investigate the effects of plate separation and clearance distribution on drag loss behavior under different operating conditions and modes. For this purpose, image series of an operating clutch system were recorded and subsequently analyzed using image processing algorithms to evaluate the movements of the plates. Based on this, the effects on drag loss behavior were analyzed. The investigations were carried out on a clutch system used in an industrial application. The measurements show that the axial movements of the plates comprise main and superimposed non-periodic movements of much a smaller amplitude. The separation of the plates is primarily driven by the applied differential speed so that the set total clearance is only utilized mainly in the higher differential speed range. The separation behavior, therefore, decisively influences the drag loss behavior. The plates can even remain in contact in the low differential speed range. The investigations also showed that the separation behavior and, thus, the drag loss behavior can be improved by using waved plates, especially in the low differential speed range. It was also found that a high plate number and a large set total clearance support a non-uniform clearance distribution. Based on the investigations conducted, it is possible to expand our fundamental knowledge of separation behavior and clearance distribution, allowing for a reduction in the drag losses of wet clutches. The findings can thus contribute to the development of low-loss and compact clutch systems.

关键词： applied image processing wet clutches drag losses plate separation

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Detection Mammogram imagesusing Convolution Neural Network

Breast Cancer Detection Mammogram Imagesusing Convolution Ne...

引用

2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering, ICECONF 2023

作者： Swetha, v. vadivu, G. SRM Institute of Science and Technology Srm Nagar Kattankulathur India

ISBN: (纸本)9798350334357

One in eight women globally develop breast cancer. By identifying the cancer of the breast tissue cells, it is *** various algorithms and methodologies, modern medical image processing systems examine histopathology images that have been recorded by a *** imaging and pathology tools are being processed using machine learning ***-aided methods are used to achieve better outcomes than manual pathological detection systems since manually identifying a cancer cell is a laborious operation and entails human mistake. Transfer learning and fine-tuning can also be used to get the most out of a CNN that has already been trained. The first is to develop simple models or adapt existing ones to reduce the time investment and the number of training *** deep learning, this is typically accomplished by first extracting features with the assistance of a convolutional neural network (CNN), and then categorizing data with the assistance of a fully connected network. The field of medical imaging makes extensive use of the technique of deep learning because it does not necessitate prior knowledge in a field that is related to it. Within the scope of this investigation, we trained a convolutional neural network to generate forecasts that had an accuracy of up to 88.86%. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Detecting Counterfeit Indian Currency A Comparative Analysis of Machine Learning algorithms and image processing

Detecting Counterfeit Indian Currency A Comparative Analysis...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： M R v vyshnavi N.L. varshitha Konda v. S. Harshith Kumar Tripty Singh Mansi Sharma Suman Chatterjee Department of Computer Science Engineering Amrita School of Computing Bengaluru India Graphics Era (Deemed to be university) Dehradun India Department of Mechanical Engineering Kongju National University Cheonan India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

The degree of secured currency is one of the key areas that makes its contribution in solving the problem of economic insecurity, highlights the most important. Even as it can be quite strained to actually identify which precise time frame this fake process was prepared in, complex fakes render the use of validation techniques quite challenging. This paper has aimed at displaying and evaluating the overall outcome of the different strategies of image, and the acquired classifiers in the identification of the fake FI currency. The following are the subsequent of the other operation that was applied in order to achieve the objectives of the intended work; image capture This is whereby the images to be used are taken by the appropriate camera or scanner. Others used include the Naïve Bayes, Support vector Classifier and Gradient Descent and Artificial Neural Network in this paper. As in the conclusion, with the help of the mathematical formulation, it can be confirmed that in fact, within an experiment, Neural Networks do have a higher level of optimization, much more than an average image processing if it is provoked to identify fake notes. In other words if used and implemented with the best of the machine learning approach and best of the image processing method then solitaire for detection of the counterfeit currency can be made more dependable than all the combined methods stated above. The objective of this study is to build and compare the performance of different machine learning algorithms and image processing methodologies for the identification of fake Indian currency notes.

关键词： Economics Training Machine learning algorithms Machine learning Artificial neural networks vectors Real-time systems Bayes methods Reliability Currencies

来源：评论

学校读者我要写书评

暂无评论

Star Sensor Simulation with Application of the k-NN Method in Star Identification Problem 12

Star Sensor Simulation with Application of the k-NN Method i...

引用

12th Asia Conference on Mechanical and Aerospace Engineering, ACMAE 2021

作者： Chen, Danhe Kudlak, vitaliya v. Maslennikov, Andrey L. 2-nd Baumanskaya Street Russian Federation 5 Moscow105005 Russia

Simulation of the navigation systems is required to develop efficient, reliable, and accurate algorithms for orientation problems. In this paper the astronavigation system is considered, and the star sensor simulation based on algorithmic mathematical model is discussed. The algorithms include the starry sky image obtaining, data processing, and stars identification. Two modifications of the known stars identification algorithm are proposed and related to the use of k-NN method in identification and stars selection criteria for increasing computational efficiency. Simulation of the described approach for star sensor is performed in MathWorks MATLAB. The simulation results show adequate results. © Published under licence by IOP Publishing Ltd.

关键词： Navigation systems

来源：评论

学校读者我要写书评

暂无评论

Intelligent machining methods for Ti6Al4v: A review

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART E-JOURNAL OF PROCESS MECHANICAL ENGINEERING 2021年第4期235卷 1188-1210页

作者： Ribeiro-Carvalho, Silvia Pereira, R. B. D. Horovistiz, Ana Davim, J. Paulo Univ Aveiro Dept Mech Engn Campus Santiago P-3810193 Aveiro Portugal Univ Fed Sao Joao del Rei Dept Mech Engn Ctr Innovat Sustainable Mfg Sao Joao Del Rei Brazil

Digital manufacturing is a necessity to establishing a roadmap for the future manufacturing systems projected for the fourth industrial revolution. Intelligent features such as behavior prediction, decision-making abilities, and failure detection can be integrated into machining systems with computational methods and intelligent algorithms. This review reports on techniques for Ti6Al4v machining process modeling, among them numerical modeling with finite element method (FEM) and artificial intelligence-based models using artificial neural networks (ANN) and fuzzy logic (FL). These methods are intrinsically intelligent due to their ability to predict machining response variables. In the context of this review, digital image processing (DIP) emerges as a technique to analyze and quantify the machining response (digitization) in the real machining process, often used to validate and (or) introduce data in the modeling techniques enumerated above. The widespread use of these techniques in the future will be crucial for the development of the forthcoming machining systems as they provide data about the machining process, allow its interpretation and quantification in terms of useful information for process modelling and optimization, which will create machining systems less dependent on direct human intervention.

关键词： Intelligent machining methods Ti6Al4v finite element method digital image processing artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

DOWNFALL SEED SPREAD. A STACK-BASED ALGORITHM FOR THE AUTONOMOUS GENERATION OF 2D MAPS IN vIDEOGAMES 18

DOWNFALL SEED SPREAD. A STACK-BASED ALGORITHM FOR THE AUTONO...

引用

18th International Conference on Interfaces and Human Computer Interaction 2024, IHCI 2024, the 17th International Conference on Game and Entertainment Technologies 2024, GET 2024 and the 18th International Conference on Computer Graphics, visualization, Computer vision and image processing 2024, CGvCvIP 2024, Part of the 18th Multi Conference on Computer Science and Information systems 2024, MCCSIS 2024

作者： Acosta-Guevara, Lenin Fernández-Peña, Félix Urrutia-Urrutia, Pilar Coello-Fiallos, Diana Universidad Técnica de Ambato Av. De los Chasquis Ambato Ecuador Universidad Espíritu Santo Km. 2 5 vía Samborondón Ecuador Escuela Superior Politécnica de Chimborazo Panamericana Sur km 1 ½ Riobamba Ecuador

ISBN: (纸本)9789898704580

The autonomous generation of 2D maps is commonly achieved by using algorithms that produce useful noise interpreted as a height map. By normalizing height maps as matrices of correlated values, it is easy to generate a 2D map. Each value in the matrix is used to choose an asset from an asset library. The problem is thus defined as the need of an algorithm for creating those matrices of correlated values. Ideally, generated matrices must be different each time while maintaining a common specific geometry among them. Procedural algorithms found in the literature can be particularly useful but also complex and time consuming. In contrast to the use of graphs and other complex data structures, we have proposed to use a stack to achieve desired characteristics in automatically generated matrices of correlated values. In this paper, we present the results of the evaluation of this proposal. Specifically, we show how changing hyper-parameters in our approach, we are up to controlling the resulting geometry of 2D maps. The results show that it was possible to successfully generate fractal geometry resembling the box fractal, tree-like geometry in the style of L-System, and caves like those obtained with cellular automata. The obtained results were compared with the findings of other authors. In all cases, results were similar, but the computational complexity of our solution was always lower. Finally, our approach has been successfully used in the generation of three 2D maps deployed in the Godot Engine. © 2024 Interfaces and Human Computer Interaction. All Rights Reserved.

关键词： Cellular automata

来源：评论

学校读者我要写书评

暂无评论

Analysis of Digital images in Order to Control the Manufacturing of Integrated Circuits

引用

PATTERN RECOGNITION AND image ANALYSIS 2021年第1期31卷 119-131页

作者： Doudkin, A. A. Inyutin, A., v Natl Acad Sci Belarus United Inst Informat Problems Minsk 220012 BELARUS

This paper offers a brief overview of the main theoretical and practical results in digital image processing in the manufacturing of integrated circuits (ICs), obtained by the authors and staff of the Laboratory for systems Identification of the United Institute for Informatics Problems of the National Academy of Sciences of Belarus. The developed methods, algorithms, and computer analysis technology combine conventional digital processing methods and neural networks. This ensures robust recognition and optical inspection of the objects of layouts of ICs with the desired accuracy. The obtained results are used at the leading enterprises of electronic engineering of the Republic of Belarus in vLSI designing and manufacturing, as well as in the fabrication of optical inspection units for vLSI semiconductor wafers.

关键词： integrated circuit photomask topological layer design computer vision system digital image processing optical layout inspection

来源：评论

学校读者我要写书评

暂无评论

Non-intrusive Internal Corrosion Characterization using the Potential Drop Technique for Electrical Mapping and Machine Learning

引用

JOURNAL OF CONTROL AUTOMATION AND ELECTRICAL systems 2022年第1期33卷 183-197页

作者： Pinto, George Amaral, Jorge Pinheiro, Gil R., v Silva, victor G. Gomes, Jose A. C. P. State Univ Rio de Janeiro UERJ Grad Program Elect Engn Sao Francisco Xavier St 524 BR-20550900 Rio De Janeiro RJ Brazil Univ Estado Rio De Janeiro Dept Elect & Telecomm Engn Rio De Janeiro RJ Brazil Brazilian Petr Corp Petrobras Res & Dev Ctr Horacio Macedo Ave 950Cidade Univ BR-21941915 Rio De Janeiro RJ Brazil Fed Univ Rio de Janeiro UFRJ Dept Met & Mat Engn PB 68505 BR-21941599 Rio De Janeiro RJ Brazil

This paper describes a non-intrusive method for collecting data about internal corrosion damages in AISI-304 stainless steel plates and classifying them according to severity. The mapping of the electric potential gradient is derived using the potential drop technique, which is then analyzed using image processing techniques including edge enhancement and segmentation. Simulations were run using finite element modeling to produce examples of damaged plates, with four types of defects that can be considered part of pitting corrosion. The image processing stage plays the role of an extractor of features that, when employed as inputs of machine learning algorithms, make it possible to determine the damage severity. With the Gradient Boosting regressor, the maximum absolute error of 0.879 mm was obtained in the estimate of the depth of the defects. Additionally, with the application of a Convolutional Neural Network, an accuracy of 94.84% was achieved to classify of the severity of the damages.

关键词： Damage classification Damage depth Convolutional neural network Electrical mapping Segmentation Non-intrusive Potential drop technique Internal corrosion

来源：评论

学校读者我要写书评

暂无评论

ADAPTATION OF DEEPLAB v3+FOR DAMAGE DETECTION ON PORT INFRASTRUCTURE imageRY 39

ADAPTATION OF DEEPLAB V3+FOR DAMAGE DETECTION ON PORT INFRAS...

引用

39th International Symposium on Remote Sensing of Environment (ISRSE) - From Human needs to SDGs

作者： Scherff, M. Hake, F. Alkhatib, H. Leibniz Univ Hannover Geodet Inst Hannover Germany

Regular inspection and maintenance of infrastructure facilities are crucial to ensure their functionality and safety for users. However, current inspection methods are labor-intensive and can vary depending on the inspector. To improve this process, modern sensor systems and machine learning algorithms can be deployed to detect defects based on rapidly acquired data, resulting in lower downtime. A quality-controlled processing chain allows to provide hence informed uncertainty assessments to inspection operators. In this study, we present several Deeplab v3+ models optimized to predict corroded segments of the quay wall at JadeWeserPort, Germany, which is a dataset from the 3D HydroMapper research project. Our models achieve generally high accuracy in detecting this damage type. Therefore, we examine the use of a Region Growing-based weakly supervised approach to efficiently extend our model to other common types in the future. This approach achieves about 90 % of the results compared to corresponding fully supervised networks, of which a ResNet-50 variant peaks at 55.6 % Intersection-over-Union regarding the test set's corrosion class.

关键词： image segmentation Damage Detection Deep Learning Optimization Supervised Weakly Supervised

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：