检索结果-内蒙古大学图书馆

2023 International Conference on Industrial Engineering, Applications and Manufacturing, ICIEAM 2023

作者： Chernikov, Alexander Smirnova, Elena Zhavoronkov, Oleg Peter the Great St. Petersburg Polytechnic University Higher School of Automation and Robotics St. Petersburg Russia Saint Petersburg State University Department of System Programming St. Petersburg Russia Computer Vision Systems Llc St. Petersburg Russia

ISBN: (纸本)9781665475952

The production of metal pipes is an important component of metallurgy and the entire industry as a whole. Traditional surface quality control is carried out by human inspectors, which is unsatisfactory due to low productivity, reliability and economy. Therefore, the introduction of an automatic visual inspection system into this production allows you to quickly find defects in products and reduce economic losses. To solve this problem, an algorithm based on the neural networks of the YOLOv5 and Unet architectures has been created, which allows finding the bounding frames of defects and their segmentation mask from the image. The created algorithm was applied to two control sites: mandrel defectoscopy and pipe defectoscopy. For mandrel defectoscopy, the accuracy for mAP 0.5 detection is 0.785, for iou_score segmentation - 0.562. For pipe defectoscopy, the accuracy for mAP 0.5 detection is 0.693, for iou_score segmentation - 0.526. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Method of Detection of Intrusions Based on Stacking Meta-Algorithm

Method of Detection of Intrusions Based on Stacking Meta-Alg...

引用

Advanced Technology (KhPIWeek), IEEE KhPI Week on

作者： Svitlana Gavrylenko Vladislav Zozulia Nataliia Khatsko Department of Computer Engineering and Programming National Technical University “Kharkiv Polytechnic Institute” Kharkiv Ukraine Department Information Systems and Technologies National Technical University «Kharkiv Polytechnic Institute» Kharkiv Ukraine

ISBN: (数字)9798350384499

ISBN: (纸本)9798350384505

An analysis of modern computer network intrusion detection systems was carried out. The application of machine and deep learning methods for classification problems has been investigated. The UNSW-NB15 dataset, developed at the Australian Cyber Security Center's (ACCS) Cyber Range Laboratory, contains data on normal network operations and synthetic intrusions. Data pre-processing was performed, including class balancing using the SMOTEENN method and selection of informative features using the Recursive Feature Elimination method. The possibility of using the stacking meta-algorithm to detect intrusions into computer networks has been investigated. A new algorithm for generating packets of raw data is proposed, which generates two sets of training data: one for training basic models, the other for a meta-model. A study of the effectiveness of using Random Forest, ANN, K Nearest Neighbor methods and Support Vector Machine and Random Forest as a decision-making meta-model was conducted. The use of the stacking meta-algorithm with the proposed algorithm for forming packets of output data, as well as basic models and a meta-model, led to a significant improvement in the quality of the model. It was found that, on average, recall and f1 score increased by 55.6% and 37.4%, respectively, compared to raw data and other models.

关键词： Training Support vector machines Computational modeling Stacking Training data Intrusion detection Predictive models Nearest neighbor methods Data models Random forests

来源：评论

学校读者我要写书评

暂无评论

Personalize Web Searching Strategies Classification and Comparison

arXiv

引用

arXiv 2022年

作者： Evtimova, Mariya Savova Momtchev, Ivan Momtchilov Faculty of Computer Systems and Control Programming Computer Technologies Department Technical University of Sofia Sofia1000 Bulgaria

Personalization is becoming very important direction in semantic web search for the users that needs to find appropriate information. In this paper, a classification of web personalization is proposed and semantic web search tools are investigated. Building user interest profile is essential for personalizing. Nowadays, semantic web tools use ontologies for personalization because of their advantages. It is important to mention that most of the semantic web search tools use agent technologies for implementation. © 2022, CC BY.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Advantages of Applying a Multi-agent Approach in Simulation Modeling: a Data-to-Action Case Study Applied to Electricity Production

Advantages of Applying a Multi-agent Approach in Simulation ...

引用

National Conference with International Participation (TELECOM)

作者： Krassimir Stoyanov Varbinka Stefanova-Stoyanova Petko Danov Department of Computer Systems Faculty of Computer Systems and Technologies Technical University of Sofia Sofia Bulgaria Department of Programming and Computer Technologies Faculty of Computer Systems and Technologies Technical University of Sofia Sofia Bulgaria

ISBN: (纸本)9781665482134

This article examines modern methods for analysis and dynamic process modeling with the context of the capabilities, characteristics and advantages of types of multiagent systems. A practical implementation of the “Data to Action” model is proposed through the research simulation modeling system “Photovoltaic (PV) to Smart Energy Storage (SES) Grid”, developed by the authors using a Multi-Agent System for simulating the process of generating electricity produced by a PV park, its storage with the possibility of Time-Shifting and sale of energy.

关键词： Photovoltaic systems Process modeling Production Data models Telecommunications Multi-agent systems Energy storage

来源：评论

学校读者我要写书评

暂无评论

Traffic Modeling for the Industrial Internet of NanoThings 4

Traffic Modeling for the Industrial Internet of NanoThings

引用

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

作者： Kuchuk, Nina Kovalenko, Andriy Ruban, Igor Shyshatskyi, Andrii Zakovorotnyi, Oleksandr Sheviakov, Iurii Department of Computer Engineering and Programming National Technical University "Kharkiv Polytechnic Institute" Kharkiv Ukraine Department of Electronic Computers Kharkiv National University of Radio Electronics Kharkiv Ukraine Department of Computerized Management Systems National Aviation University Kyiv Ukraine Civil AviationI nstitute Ivan Kozhedub Kharkiv National Air Force University Kharkiv Ukraine

ISBN: (纸本)9798350395532

Industrial Internet of NanoThings (IIoNT) traffic model proposed. The model is based on the developed algorithm for Dynamic Data Composition Control. The application of the algorithm made it possible to reduce the total amount of transmitted information from the end nodes of IIoNT. The model made it possible to determine the parameters of aggregation traffic of IIoNT cluster gateway. With the calculated parameters, the value of the aggregated package is maximized. The main limitation is not exceeding the value of the boundary delay for the transmission of sensor readings. The model also allows you to dynamically determine the required amount of the gateway buffer memory. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

An Experiment to Evaluate IoT Application Security Scheme (IoTGazePass)

An Experiment to Evaluate IoT Application Security Scheme (I...

引用

2022 International Conference on Engineering and MIS, ICEMIS 2022

作者： Keshlaf, Ayad A. Alfard, Faheemah M. Bouzid, Omar M. Sabratha University Faculty of Engineering Computer Eng. and It Department Sabratha Libya Libyan Center for Electronic Systems Programming and Aviation Research University of Zawia Computer Department Faculty of Engineering Zawia Libya University of Gharyan Faculty of Engineering Elec. and Electronic Eng. Dept Gharyan Libya

ISBN: (数字)9781665454360

ISBN: (纸本)9781665454360

IoTGazePass is a new password scheme that has been designed to tackle the weaknesses of existing types of passwords. It is intended to be suitable for IoT applications. An experiment was conducted to evaluate the strengths and weaknesses of the IoTGazePass scheme (e.g., security, usability and memorability). The evaluation aspects include a comparison with traditional textual and graphical based passwords in terms of memorability and security of the passwords. The results of the evaluation indicate that the IoTGazePass scheme is easy to use, memorable and flexible, as it can generate strong, secure and scalable passwords. The experiment results have also showed that the IoTGazePass scheme have good ability to deal with shoulder surfing attacks. In fact, the experiment results lead to some recommendations and suggestions to improve the planned performance. © 2022 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Classified emotion as implicit recommendation system feedback

Classified emotion as implicit recommendation system feedbac...

引用

Advanced Technology (KhPIWeek), IEEE KhPI Week on

作者： Andrii Kuliahin Heorhii Kuchuk Department of Computer Systems Networks and Cybersecurity National Aerospace University “Kharkiv Aviation Institute” Kharkiv Ukraine Department of Computer Engineering and Programming National Technical University “Kharkiv Polytechnic Institute” Kharkiv Ukraine

the paper proposes the use of 3D convolutional neural network for recognizing user emotions on videos in a recommender system. The data approach aims to use the recognized emotion as important implicit feedback and improve the recommendation result. This is expected to significantly improve the performance of the recommender system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hassenstein-Reichardt Detector Using Controllable Single Pulse Time-Delay Circuit for Neuromorphic Hardware

Hassenstein-Reichardt Detector Using Controllable Single Pul...

引用

computer Science (COMSCI), International Scientific Conference on

作者： Ianislav Trendafilov Veska Gancheva Neuromorphica Ltd. Sofia Bulgaria Department of Programming and Computer Technologies Faculty of Computer Systems and Technologies Technical University of Sofia 8 Kliment Ohridski blvd. Sofia Bulgaria

Inspired by the visual system of the fruit fly, we had created a generic building block for neuromorphic hardware that is vital for third generation neural networks. This enables time delay to be parametrized in a cheap and inexpensive way. The advantage of our proposal is the possibility of building and testing new networks using dynamicist approach in artificial intelligence.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model-based Generation of Attack-Fault Trees

arXiv

引用

arXiv 2023年

作者： Groner, Raffaela Witte, Thomas Raschke, Alexander Hirn, Sophie Pekaric, Irdin Frick, Markus Tichy, Matthias Felderer, Michael Institute of Software Engineering and Programming Languages Ulm University Germany Department of Computer Science University of Innsbruck Austria Department of Information Systems and Computer Science University of Liechtenstein Liechtenstein Germany Department of Mathematics and Computer Science University of Cologne Germany

Joint safety and security analysis of cyber-physical systems is a necessary step to correctly capture inter-dependencies between these properties. Attack-Fault Trees represent a combination of dynamic Fault Trees and Attack Trees and can be used to model and model-check a holistic view on both safety and security. Manually creating a complete AFT for the whole system is, however, a daunting task. It needs to span multiple abstraction layers, e.g., abstract application architecture and data flow as well as system and library dependencies that are affected by various vulnerabilities. We present an AFT generation tool-chain that facilitates this task using partial Fault and Attack Trees that are either manually created or mined from vulnerability databases. We semi-automatically create two system models that provide the necessary information to automatically combine these partial Fault and Attack Trees into complete AFTs using graph transformation rules. © 2023, CC BY-NC-ND.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Advanced computer-Aided Optimization of Quartz Resonator-Based Sensors

Advanced Computer-Aided Optimization of Quartz Resonator-Bas...

引用

International Conference on Perspective Technologies and Methods in MEMS Design (MEMSTECH)

作者： Volodymyr Savchenko Oksana Mnushka Oleg Sokulskyi Computer Engineering and Programming Department National Technical University “Kharkiv Polytechnic Institute” Kharkiv Ukraine Information Systems and Technologies Department National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute” Kyiv Ukraine

ISBN: (数字)9798350378627

ISBN: (纸本)9798350378634

In this study, we present an improved approach to optimizing the parameters of sensor sensing elements using quartz resonators with an interelectrode gap. We combine graphical and analytical methods to solve the multi-criteria optimization problem. The work focuses on the modes of operation of a quartz resonator equipped with an interelectrode gap in sensors with a frequency output, determining a set of optimal parameters and representing them as surfaces in a particular optimization parameter space. The presented results reveal specific areas on the surface of the objective function where optimization of design and technological parameters is possible, taking into account technological influences and features of the sensor design, including the initial value of the interelectrode gap. By using an improved mathematical model for the oscillations of a quartz resonator with an electrode gap, this study achieves results with an accuracy of ($8 . . .11$)% higher than previous studies, demonstrating the effectiveness of the proposed method in improving the design and functionality of piezoelectric sensors for advanced applications.

关键词： Micromechanical devices Electrodes Accuracy Resonant frequency Linear programming Mathematical models Sensors

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：