检索结果-内蒙古大学图书馆

26th International Conference on Digital Signal processing and its Applications, DSPA 2024

作者： Tsygankov, Y.A. Kovriznich, Y.A. Sergeychik, M.S. Korenev, A.V. Nust 'MISIS' Stary Automated and Information Control Systems Department Oskol Russia

ISBN: (纸本)9798350361728

The paper considers the problem of early recognition of slag of steel casting ladle of continuous casting machine during steel pouring. In this paper, the vibration method of slag recognition was investigated, as it is the most informative. In order to cut off slag in time and prevent it from getting into the intermediate ladle, a hybrid method of analyzing the vibration acceleration signal of the protective tube manipulator was tested. It is based on sequential application of singular spectral analysis of the initial signal and calculation of power spectral density of the carrier component of singular decomposition, on the basis of which the moment of slag ingress into the intermediate ladle was determined. Analysis of the test results of this method showed that it allowed to exclude the influence of interference created by the gate movement on the quality of slag cutoff criteria operation. © 2024 IEEE.

关键词： Slags

来源：评论

学校读者我要写书评

暂无评论

Analysis of Methods of Augmentation of Images of the Branding of Cast Billet at A. A. Ugarov Oskol Electrometallurgical Plant 5

Analysis of Methods of Augmentation of Images of the Brandin...

引用

5th International Conference on control systems, Mathematical Modeling, Automation and Energy Efficiency, SUMMA 2023

作者： Poleshchenko, Dmitriy Zorin, Ivan Automated and Information Control Systems Department Stary Oskol Russia

ISBN: (纸本)9798350309126

The paper deals with the procedure of increasing the training sample size using augmentation methods. The paper considers the main methods of image augmentation, selects the most suitable ones for solving the presented class of problems, and approbation of these methods with testing on the deep learning neural network Faster R-CNN. It is shown that the use of augmentation methods to increase the image base allows to raise the quality of training of the neural network by 1%. It is also found that the type of augmentation should correlate with the prevailing type of disturbance affecting the image quality. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Analysis of Signal Integrity and Distortion in Twisted Pair in a Multilayer Printed Circuit Board

Analysis of Signal Integrity and Distortion in Twisted Pair ...

引用

2024 International Russian Smart Industry Conference, SmartIndustryCon 2024

作者： Gizatullin, Zinnur Gizatullin, Rifnur Nuriev, Marat Kazan National Research Technical University Named after A.N. Tupolev-KAI Department for Automated Systems for Information Processing and Control Kazan Russia

ISBN: (纸本)9798350395044

One of the areas of information security of electronic systems is the physical protection of information. Includes techniques for maintaining the integrity of electrical information signals in electronic systems at the physical level and reducing electromagnetic emissions. Differential transmission of electrical signals is one of the most promising areas for building high-speed electronic systems from the point of view of physical information protection. To transmit such signals on printed circuit boards, a differential pair are used - two transmission lines with a strong coupling between them. In practice today, each line is a conventional coplanar, stripline, or microstrip transmission line. This article discusses a new type of communication lines on printed circuit boards in the form of twisted pairs. Structurally, the twisted pair is implemented in two layers of a multilayer printed circuit board using vias. The article analyzes distortions of information signals in connections of multilayer printed circuit boards in the form of twisted pairs. The results are compared with the distortion of information signals in coplanar interconnects. © 2024 IEEE.

关键词： Printed circuit boards

来源：评论

学校读者我要写书评

暂无评论

Real-time tracking of fast-moving object in occlusion scene

引用

Journal of systems Engineering and Electronics 2024年第3期35卷 741-752页

作者： LI Yuran LI Yichen ZHANG Monan YU Wenbin GUAN Xinping Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of Systems Control and Information Processing Ministry of Education of ChinaShanghai 200240China

Tracking the fast-moving object in occlusion situations is an important research topic in computer vision. Despite numerous notable contributions have been made in this field,few of them simultaneously incorporate both object's extrinsic features and intrinsic motion patterns into their methodologies,thereby restricting the potential for tracking accuracy improvement. In this paper, on the basis of efficient convolution operators(ECO) model, a speed-accuracy-balanced model is put forward. This model uses the simple correlation filter to track the object in real-time, and adopts the sophisticated deep-learning neural network to extract high-level features to train a more complex filter correcting the tracking mistakes, when the tracking state is judged to be poor. Furthermore, in the context of scenarios involving regular fast-moving, a motion model based on Kalman filter is designed which greatly promotes the tracking stability, because this motion model could predict the object's future location from its previous movement pattern. Additionally,instead of periodically updating our tracking model and training samples, a constrained condition for updating is proposed,which effectively mitigates contamination to the tracker from the background and undesirable samples avoiding model degradation when occlusion happens. From comprehensive experiments, our tracking model obtains better performance than ECO on object tracking benchmark 2015(OTB100), and improves the area under curve(AUC) by about 8% and 32% compared with ECO, in the scenarios of fast-moving and occlusion on our own collected dataset.

关键词： speed-accuracy balanced motion modeling constrained updater

来源：评论

学校读者我要写书评

暂无评论

Identification of a Person Based on Block processing of a Signature Image

Identification of a Person Based on Block Processing of a Si...

引用

2024 International Russian Smart Industry Conference, SmartIndustryCon 2024

作者： Rizaev, Ildus Takhavova, Elza Shleimovich, Mikhail Kazan National Research Technical University Named after A.N. Tupolev-KAI Automated Systems for Information Processing and Control Department Kazan Russia

ISBN: (纸本)9798350395044

The development of computer vision systems stimulates the development of various applications in the field of image recognition. Methods and algorithms for image recognition in document processing systems play a crucial role. There is a lot of research in this direction, and one of the most difficult problems is handwritten text recognition. This includes the tasks of signature identification, which the authors of the paper consider. The article considers the main stages of signature analysis to establish authorship. They are the preprocessing of the signature, representation in a form convenient for applying author identification. A dataset containing sample signatures of various people is used. The described tools became means to develop software for preprocessing images of signatures, extracting characteristics and identifying the author of the signature. © 2024 IEEE.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Development of Hardware Module for Collecting Parameters of Microhydroelectric Power Plant Operation in Mountainous Conditions

Development of Hardware Module for Collecting Parameters of ...

引用

2024 International Conference on Industrial Engineering, Applications and Manufacturing, ICIEAM 2024

作者： Onishchenko, Stefan V. Mamiy, Aliy R. Yurkaev, Konstantin A. Adyghe State University Laboratory Of Renewable Energy Sources Maykop Russia Adyghe State University Department Of Automated Systems Of Processing Information And Control Maykop Russia

ISBN: (纸本)9798350395013

Hydropower plants play a major role in the global energy sector, generating up to 17% of all energy generated. Despite this, the spread of small hydropower is not as extensive, although it has an extremely large potential and is a competitive renewable energy source, as small hydropower plants have high efficiencies of up to 80%. The implementation of such energy complexes requires a preliminary assessment of their efficiency, for which atlases and data from existing GIS systems are most often used, but they may not have information on the potential of small rivers and streams, and do not allow for seasonal changes in the water landscape, which is particularly pronounced in mountainous terrain. Therefore, this paper proposes to examine the process of developing a small generating station suitable for use on small streams in mountainous terrain, which can be used as a means to collect data on the energy production profile of small mountain streams, which will help to establish seasonal dependencies and balance the energy system, achieving sustainable energy production through the involvement of other generation sources. © 2024 IEEE.

关键词： Rivers

来源：评论

学校读者我要写书评

暂无评论

Testing automated Complex for Assessing Agrotechnical Parameters of Agricultural Crops Based on Photographs Taken by an Unmanned Aerial Vehicle (UAV) in a Mock-Up of a Real Field 26

Testing Automated Complex for Assessing Agrotechnical Parame...

引用

26th International Conference on Digital Signal processing and its Applications, DSPA 2024

作者： Poleshchenko, Dmitriy Mikhailov, Ilia Petrov, Vladislav Stankevich, Vladislav National University of Science and Technology Misis Automated and Information Control Systems Department Stary Oskol Russia

ISBN: (纸本)9798350361728

The work is devoted to approbation of methods for assessing agrotechnical parameters of agricultural crops from UAV photos using neural networks on the developed laboratory bench with a real field layout. The laboratory bench is used to determine the number of corn mock-ups, weeds and the degree of weediness of a field plot based on YOLOv5 and YOLOv8 architectures. This laboratory bench allows to conduct research under controlled conditions and improve the efficiency of the complex. © 2024 IEEE.

关键词： Laboratories

来源：评论

学校读者我要写书评

暂无评论

Development of a Neural Network Method for Identification of the Method to Detect Slag Flow in a Metallurgical Unit "Steel Ladle-Intermediate Ladle" 5

Development of a Neural Network Method for Identification of...

引用

5th International Conference on control systems, Mathematical Modeling, Automation and Energy Efficiency, SUMMA 2023

作者： Tsygankov, Y.A. Kovriznich, Y.A. Sergeychik, M.S. Korenev, A.V. NUST MISIS Automated and Information Control Systems Department Stary Oskol Russia

ISBN: (纸本)9798350309126

The paper presents the results of research on the development of an algorithm for identifying the moment of the beginning of slag lapse during the functioning of the metallurgical unit "steel ladle-intermediate ladle". In the paper were performed works on the formation of datasets of the vibration acceleration signal at the functioning technological object. After that, experiments on amplitude and frequency analysis of the signal were performed in order to form a criterion for determining the moment of the beginning of slag flow. Then the possibility of application of autoencoder artificial neural network for identification of metallurgical unit state was tested. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

On the Possibility of Developing a System for Predicting Students Academic Performance Using Machine Learning Methods 5

On the Possibility of Developing a System for Predicting Stu...

引用

5th International Conference on control systems, Mathematical Modeling, Automation and Energy Efficiency, SUMMA 2023

作者： Tsygankov, Y.A. Solovev, A.Iu. Sergeychik, M.S. NUST MISIS Automated and Information Control Systems Department Stary Oskol Russia

ISBN: (纸本)9798350309126

This article considers the possibility of developing data mining techniques and applying machine learning models to identify hidden dependencies that uniquely characterize different categories of students in order to predict their academic performance. The application of machine learning in this subject area is conditioned by their ability to analyze large amounts of data, obtaining, as a result, generalizing models capable of classifying the objects of study and predicting the required indicators. The development of such a system will allow, based on the analysis of a priori data and current indicators, to predict the expected performance of students in disciplines of different orientation, providing information on the categories of performance in a visual form. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Model of Dependence of Zone Gain from Technological Parameters of Multizone Heating Furnace Using Regression and Neural networks 5

Model of Dependence of Zone Gain from Technological Paramete...

引用

5th International Conference on control systems, Mathematical Modeling, Automation and Energy Efficiency, SUMMA 2023

作者： Fomin, Andrey Savostin, Nikita Zhukov, Petr NUST MISIS Automated and Information Control Systems Department Stary Oskol Russia

ISBN: (纸本)9798350309126

The general purpose of this study is to investigate the technological data collected during the operation of a multizone heating furnace by an automated control system (ACS). The certain aim is to develop a mathematical model that reflects the dependence of the gain of a multizone furnace zone on a number of other technological parameters collected during the operation of the plant. Among such parameters we consider: the position of the fume exhauster damper, underpressure in the breeching pipe of the fume exhauster, the average time that the billets spend in the furnace zones and others. It is found that the data taken from the operating process facilities have a shifted asymmetric unimodal distribution with a "heavy"tail. This distribution is characterized by a large number of values, which are considered as outlier values by parametric methods of analysis. This fact does not allow applying parametric regression models and estimating their accuracy. Then we studied the applicability of neural networks to design the required model. A promising result is obtained using classical neural networks. © 2023 IEEE.

关键词： Regression analysis

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：