检索结果-内蒙古大学图书馆

International Computer Sciences and Information Technologies (CSIT)

作者： Lesia Dubchak Anatoliy Sachenko Carsten Wolff Nadiia Vasylkiv Zenovii Bernas Department of Computer Engineering West Ukrainian National University Ternopil Ukraine Research Institute for Intelligent Computer Systems West Ukrainian National University Ternopil Ukraine Department of Tele-Informatics Kazimierz Pulaski University of Technology and Humanities in Radom Radom Poland Dortmund University of Applied Science and Arts Dortmund Germany Department of Information Computer Systems and Control West Ukrainian National University Ternopil Ukraine

ISBN: (数字)9798331542634

ISBN: (纸本)9798331542641

The article presents a study on classifying wind turbine defects using the SqueezeNet neural network. Wind turbines are critical for renewable energy, but defects such as corrosion, erosion, and cracks can significantly reduce their efficiency. The study proposes using image classification techniques with neural networks, particularly SqueezeNet, to automate defect detection. The compact nature of SqueezeNet makes it suitable for real-time applications with limited computing resources. Through training and testing, the network achieved an accuracy of 89%, demonstrating its potential to improve wind turbine maintenance and reduce operational costs.

关键词： Training Accuracy Costs Neural networks Real-time systems Wind turbines Maintenance Defect detection Testing Image classification

来源：评论

学校读者我要写书评

暂无评论

Intelligent model for assessing the suitability of water based on its chemical and biological parameters 24

Intelligent model for assessing the suitability of water bas...

引用

24th International Symposium INFOTEH-JAHORINA, INFOTEH 2025

作者： Tynchenko, Yadviga Tynchenko, Vadim Degtyareva, Ksenia Kuznetsov, Georgy Kukartseva, Svetlana Artificial Intelligence Technology Scientific and Education Center Bauman Moscow State Technical University Moscow Russia Department of Technological Machines and Equipment of Oil and Gas Complex School of Petroleum and Natural Gas Engineering Siberian Federal University Krasnoyarsk Russia Department of Systems Analysis and Operations Research Reshetnev Siberian State University of Science and Technology Krasnoyarsk Russia Department of Applied Informatics Moscow Timiryazev Agricultural Academy Moscow Russia Center for Continuing Education Bauman Moscow State Technical University Moscow Russia Information-Control Systems Department Reshetnev Siberian State University of Science and Technology Krasnoyarsk Russia

ISBN: (纸本)9798331515799

This paper presents a study on the development and testing of a machine learning model for classifying water according to its purpose, based on chemical and microbiological indicators. The aim of the study is to create an accurate and stable model that can effectively determine the categories of water - drinking, industrial, agricultural and technical - based on the analysis of its qualitative characteristics. The gradient boosting method was chosen as the algorithm for classification, which demonstrated high accuracy and reliability when working with multidimensional data. The study included the processing of a synthetic dataset containing information on water parameters such as calcium concentration, total bacterial content, phosphate levels, alkalinity, sulfates and oxidizability. The analysis of the correlation matrix made it possible to identify the relationships between the features, which made it possible to optimize the operation of the model and improve its accuracy. The quality of the model was tested using accuracy, completeness and F1-score metrics, which demonstrated almost perfect results for all categories. In conclusion, it is concluded that the proposed model can be successfully used to automate the analysis of water quality in ecology, industry and agriculture. The use of intelligent technologies opens up new opportunities for monitoring water resources, increasing the efficiency and reliability of quality control. © 2025 IEEE.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Departure Counting Process in a Finite-Buffer Queue with Batch Arrivals and Multiple Vacation Policy

SSRN

引用

SSRN 2024年

作者： Marjasz, Rafal Kempa, Wojciech M. Kovtun, Viacheslav Institute of Theoretical and Applied Informatics Polish Academy of Sciences 5 Baltycka Str. Gliwice44-100 Poland Silesian University of Technology Faculty of Applied Mathematics 23 Kaszubska Str. Gliwice44-100 Poland Vinnytsia National Technical University Faculty of Intelligent Information Technologies and Automation Department of Computer Control Systems 95 Khmelnitske Shose Str. Vinnytsia21000 Ukraine

The study investigates the departure counting process in a finite-buffer queueing system with batch arrivals and multiple vacation policy. A representation for the mixed double transform of the number of departures up to the fixed time moment is obtained in the explicit form applying analytic approach based on integral equations and linear algebra. Numerical study is attached that focuses on understanding the impact of various system parameters on the behaviour of the mean number of packets processed within a fixed time frame. Utilizing numerical experiments, the study examines the influence of vacation duration, initial buffer state, arrival intensity, and processing rate on the departure process. Results reveal significant dependencies between these parameters and the transient behaviour of the queueing system. Notably, the service speed parameter demonstrates the most substantial influence on the mean number of processed packets, followed by the arrival rate. Conversely, variations in vacation duration and initial packet count exhibit comparatively minor effects on system behaviour. Overall, the findings provide valuable insights into the dynamics of departure processes in finite-buffer queue systems with batch arrivals and multiple vacation policies, offering implications for system optimization and performance enhancement strategies. © 2024, The Authors. All rights reserved.

关键词： Integral equations

来源：评论

学校读者我要写书评

暂无评论

Assessment of the mineral potential of rocks using intelligent data analysis technologies 24

Assessment of the mineral potential of rocks using intellige...

引用

24th International Symposium INFOTEH-JAHORINA, INFOTEH 2025

作者： Tynchenko, Yadviga Tynchenko, Vadim Degtyareva, Ksenia Kalmykova, Ekaterina Kukartseva, Svetlana Bauman Moscow State Technical University Artificial Intelligence Technology Scientific and Education Center Moscow Russia Siberian Federal University School of Petroleum and Natural Gas Engineering Department of Technological Machines and Equipment of Oil and Gas Complex Krasnoyarsk Russia Reshetnev Siberian State University of Science and Technology Information-Control Systems Department Krasnoyarsk Russia Reshetnev Siberian State University of Science and Technology Department of Systems Analysis and Operations Research Krasnoyarsk Russia Bauman Moscow State Technical University Center for Continuing Education Moscow Russia Moscow Timiryazev Agricultural Academy Department of Applied Informatics Moscow Russia

ISBN: (纸本)9798331515799

This paper presents a study aimed at developing and evaluating a classification model for the mineral potential of geological layers using machine learning methods. The main goal was to create an algorithm capable of predicting the categories of mineral potential - low, medium and high - based on key geological characteristics such as ore content, density, depth, permeability and rock type. The results obtained demonstrated the overall accuracy of the model at 98%, with an almost ideal classification for the categories of medium and high mineral potential. The analysis of the significance of the features showed that the ore content and density have the greatest impact on the classification. The work also revealed certain difficulties in classifying low mineral potential, which is due to limited data or the intersection of characteristics between classes. These results highlight the importance of further research in feature selection and improving data balance. The findings demonstrate the effectiveness of using machine learning methods in geological research and their potential for automating mineral resource assessment processes. The developed methodology can be adapted to solve other problems in the field of geology, such as forecasting deposits and optimizing mining. © 2025 IEEE.

关键词： Radioactive prospecting

来源：评论

学校读者我要写书评

暂无评论

Continual Learning of a Time Series Model Using a Mixture of HMMs with Application to the IoT Fuel Sensor Verification

Continual Learning of a Time Series Model Using a Mixture of...

引用

Federated Conference on Computer Science and Information systems (FedCSIS)

作者： Przemysław Głomb Michał Cholewa Paweł Foszner Jakub Bularz Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice Poland Department of Computer Graphics Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland AIUT Sp. z o.o. ul Gliwice Poland

This paper presents an application of a mixture of Hidden Markov Models (HMMs) as a tool for verification of IoT fuel sensors. The IoT fuel sensors report the level of fuel in tanks of a petrol station, and are a key component for monitoring system reliability (billing), safety (fuel/oil leak detection) and security (theft prevention). We propose an algorithm for learning a mixture of HMMs based on a continual learning principle, i.e. it adapts the model while monitoring a sensor over time, signalling unexpected or anomalous sensor reports. We have tested the proposed approach on a real-life data of 15 fuel tanks being monitored with the FuelPrime system, where it has shown a very good performance (average area under ROC curve of 0.94) of detecting anomalies in the sensor data. Additionally we show that the proposed method can be used for trend monitoring and present qualitative analysis of the short and long term learning performance. The proposed method has promising performance score, the resulting model has a high degree of explainability, limited memory and computation requirements and can be easily generalized to other domains of sensor verification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved method of segmentation of images from space-based optoelectronic observation systems based on Otsu's algorithm with global and adaptive thresholds 4

Improved method of segmentation of images from space-based o...

引用

4th IEEE KhPI Week on Advanced Technology, KhPI Week 2023

作者： Khudov, Hennadii Kalimulin, Temir Khudov, Rostyslav Butko, Ihor Burtseva, Viktoriia Burtsev, Valeriy Department of Radar Troops Tactic Ivan Kozhedub Kharkiv National Air Force University Kharkiv Ukraine Department of Theoretical and Applied Informatics V.N.Karazin Kharkiv National University Kharkiv Ukraine Department of Computer Sciences and Software Engineering Academician Y. Bugay International Scientific and Technical University Kyiv Ukraine Scientific Research Department of Military Standards Metrology Center of Military Standards Kharkiv Ukraine Department of Control Systems of Antiaircraft Missile Troops Ivan Kozhedub Kharkiv National Air Force University Kharkiv Ukraine

ISBN: (纸本)9798350395532

An analysis of optoelectronic image, received from space-based observation system has been carried out. It has been found out, that this image has a complex structure and a unimodal intensity histogram. Otsu method is chosen as to segment the image. This method is easy and relatively quick, when talking of its realization. Methods of global and adaptive thresholding have been researched to perform image segmentation. Results of experimental research of segmentation of optoelectronic image from space-based observation system with use of Otsu method are developed. Ways for future research in this area are defined. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Threshold Wavelet Filtering of Images Based on Weight Model

Threshold Wavelet Filtering of Images Based on Weight Model

引用

applied Mathematics, Computational Science and Mechanics: Current Problems (AMCSM)

作者： Maya Lyasheva Stella Lyasheva Mikhail Shleymovich Department for Automated Systems for Information Processing and Control Kazan National Research Technical University named after A.N. Tupolev-KAI Kazan Russian Federation Department for Applied Mathematics and Informatics Kazan National Research Technical University named after A.N. Tupolev-KAI Kazan Russian Federation

ISBN: (数字)9798350348576

ISBN: (纸本)9798350348583

Many modern information processing and control systems are based on computer vision technologies. In such systems, a number of tasks are solved, including the task of primary image processing. The primary processing is designed to transform the geometric, brightness and color characteristics of images, ensuring that they are brought to the best possible appearance for further analysis. Brightness conversion must be performed to implement image enhancement and restoration procedures. Threshold wavelet filtering is the basis of one of the frequently used approaches for solving these problems. To build the appropriate procedures in this article, it is proposed to use a weight model of the image. This model allows us to obtain estimates of the significance of the contribution of pixels to the total energy of the analyzed image.

关键词： Wavelet transforms Computer vision Analytical models Filtering Noise Brightness Information processing

来源：评论

学校读者我要写书评

暂无评论

Application of the Weight Model to Detect the State Registration Number of the Vehicle in the Image

Application of the Weight Model to Detect the State Registra...

引用

2021 International Russian Automation Conference, RusAutoCon 2021

作者： Lyasheva, Maya M. Lyasheva, Stella A. Shleymovich, Mikhail P. Kazan National Research Technical University Named after A. N. Tupolev-KAI Department for Automated Systems for Information Processing and Control Kazan Russia Kazan National Research Technical University Named after A. N. Tupolev-KAI Department for Applied Mathematics and Informatics Kazan Russia

ISBN: (纸本)9780738131566

The article deals with the issues of detecting state registration numbers of vehicles in images when solving the problem of their identification in intelligent transport systems. The main approaches for solving this problem are described, which belong to two classes-based on image processing and based on machine learning. It is shown that, despite the effectiveness of methods based on machine learning, it is advisable to use methods based on image processing for certain specific conditions. Among the image processing methods for detecting vehicle license plates, edge analysis methods are the fastest. At the same time, you can use the properties of the wavelet transform to analyze the edges. This is the basis of the approach proposed by the authors, which provides for the use of a weight model based on the coefficients of the multiple-scale orthogonal Haar wavelet transform. As a result of building such a model, weights are calculated that reflect the significance of the pixels of the original image for the analysis of the edges when searching for the area of the vehicle number. The weight model allows you to emphasize the characteristics of the vehicle number area in the image and use additional processing to find its location. The advantages of the proposed approach include simplicity in implementation, the detection of vehicle numbers in images obtained under various conditions, and the possibility of supplementing it with operations that ensure increased efficiency at all stages. © 2021 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Object Detection Using Color Segmentation, Radial Symmetry Detector, and Hough Method

Object Detection Using Color Segmentation, Radial Symmetry D...

引用

2021 International Russian Automation Conference, RusAutoCon 2021

作者： Shakirzyanov, Rinat M. Shakirzyanova, Alina A. Kazan National Research Technical University Named after A. N. Tupolev-KAI Department for Applied Mathematics and Informatics Kazan Russia 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)9780738131566

Currently, unmanned control systems for various vehicles, including cars, are widely used. Driving an unmanned vehicle involves solving tasks related to recognizing road objects. An improved algorithm for solving the problem of detection and recognition of round traffic light signals is proposed. To solve this problem, we use: fast radial symmetry transformation, Hough transform, and color segmentation. A special feature of the algorithm is that the areas where the light signals are located they are preliminarily determined based on the color attribute, followed by specifying the shape and position of objects. At the final stage, the solution is refined using the Hough method. The proposed algorithm has shown operability, it can be expanded in terms of the types of recognized signals and applied as part of unmanned vehicle control systems, as well as part of driver assistance systems for solving problems related to the prevention of dangerous and emergency situations. © 2021 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Image compression method based on analysis of energy features

Image compression method based on analysis of energy feature...

引用

2021 International Conference on Industrial Engineering, Applications and Manufacturing, ICIEAM 2021

作者： Lyasheva, M. Lyasheva, S. Shleymovich, M. Department for Automated Systems for Information Processing and Control Kazan National Research Technical University named after A. N. Tupolev-KAI Kazan Russia Department for Applied Mathematics and Informatics Kazan National Research Technical University named after A. N. Tupolev-KAI Kazan Russia

ISBN: (纸本)9781728145877

Currently, many information processing and control systems are based on computer vision technologies. Among the many problems that need to be solved in such systems, it is important to reduce the redundancy of information in the image. To solve this problem, various methods of image compression are used, including those based on the wavelet transform. This paper is devoted to one of these methods. The proposed method is based on the calculation and analysis of energy features, which allow us to assess the significance of the detailing coefficients for the representation of the image in a compressed form. As a result of its application, a matrix of approximating coefficients of the initial level, significance maps and sets of significant detailing coefficients of various levels of the wavelet transform are formed. To improve the compression quality, significant detailing coefficients are normalized. In addition, you can apply entropy coding for each level of data. The described method is simple to implement and provides flexible parameter settings to obtain the required image compression quality indicators. © 2021 IEEE.

关键词： Wavelet transforms

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：