检索结果-内蒙古大学图书馆

2024 International Russian Automation Conference, RusAutoCon 2024

作者： Shchegolikhin, Ivan S. Andreev, Sergey M. Nosov Magnitogorsk State Technical University Department of Computer Engineering and Programming Magnitogorsk Russia

An increasing number of steel factories around the world are integrating two processes: continuous casting and hot rolling. The slab warehouse is the link between these two processes. Slabs of certain sizes are cast on the continuous casting machine streams and then transported to the slab warehouse. In the warehouse, overhead cranes move the slabs to storage locations, into stacks. The sequence of slabs arriving at the slab warehouse plays an important role: slabs that arrive earlier should, as a rule, be stacked earlier. If several cranes may be operating in a warehouse in an adjacent space, the scheduling of cranes becomes much more difficult: a safe distance must be maintained between the cranes. This paper proposes a mathematical model of crane scheduling for a defined solution to the storage location assignment problem in a slab warehouse. This mathematical model considers a large number of constraints specific to the mentioned process, such as: orthogonality of crane movement;order of slab processing;minimum distance between cranes;maximum and minimum height of stacks;and many others. The developed mathematical model takes into account the space-time characteristics of the warehouse and crane trajectories, which allows its application to create a digital twin of the slab warehouse, which will allow to check the acceptability of the crane schedule for some solution of the problem of storage location assignment. © 2024 IEEE.

关键词： Continuous casting

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous ensemble classifier in medical decision support systems 5

Heterogeneous ensemble classifier in medical decision suppor...

引用

5th IEEE KhPI Week on Advanced Technology, KhPIWeek 2024

作者： Povoroznyuk, Anatol Y. Povoroznyuk, Oksana Filatova, Anna Department of Computer Engineering and Programming National Technical University "Kharkiv Polytechnic Institute Kharkiv Ukraine

ISBN: (纸本)9798350384499

The work is devoted to solving the current scientific and technical problem of constructing a diagnostic decision support system in medicine based on a heterogeneous ensemble classifier model that implements two approaches to formulating a diagnostic conclusion: a probabilistic one based on the analysis of the training sample, and expert information on the structure of symptom complexes. The choice of prototype matching method as a probabilistic component is justified. Formalization of expert information on the structure of symptom complexes was carried out by representing symptom complexes of diseases with numerical intervals of linguistic variables. Options for taking into account expert assessments about the structure of symptom complexes in an ensemble classifier are considered. Test verification of the developed classifier was done on real medical data and confirmed the effectiveness of its work. ©2024 IEEE.

关键词： Expert systems

来源：评论

学校读者我要写书评

暂无评论

Optimization of neural network calculations using integer arithmetic 5

Optimization of neural network calculations using integer ar...

引用

5th IEEE KhPI Week on Advanced Technology, KhPIWeek 2024

作者： Zakovorotnyi, Oleksandr Khulap, Andrii Department of Computer Engineering Programming National Technical University Kharkiv Polytechnic Institute" Kharkiv Ukraine

ISBN: (纸本)9798350384499

Most of the sensor devices in the Internet of Things systems are based on energy-efficient microcontrollers, the computing resources of which are limited, as well as the amount of available memory. Increasing the security of the use of such devices with the help of neural networks is an important and urgent problem. The article describes the possibility of using artificial neural networks in small microcontrollers with limited resources. The purpose of this work is to check the possibility of calculating neural networks based on integer arithmetic to reduce the time of calculating a neural network and eliminate data normalization operations, as well as to evaluate the feasibility of using such neural networks in the field of security of the Internet of Things in comparison with traditional methods, such as black lists and white lists. The following results were obtained: when switching to integer arithmetic, compared to floating point, the accuracy of the result calculations is within the permissible error of neural network training, that is, it has not changed. Execution time decreased by 30-96%, depending on the architecture of the microcontroller. The program size is reduced by 22-48%, also depending on the microcontroller architecture. Conclusions: the possibility and expediency of using neural networks optimized for microcontrollers with limited resources was proved. This will increase the security of Internet of Things systems, especially against device authentication threats and intrusion detection. Prospects for further research are determined. ©2024 IEEE.

关键词： microcontroller neural network optimization software implementation

来源：评论

学校读者我要写书评

暂无评论

DETECTION computer NETWORK INTRUSION USING DEEP NEURAL NETWORKS 5

DETECTION COMPUTER NETWORK INTRUSION USING DEEP NEURAL NETWO...

引用

5th IEEE KhPI Week on Advanced Technology, KhPIWeek 2024

作者： Gavrylenko, Svitlana Poltoratskyi, Vadym Department of Computer Engineering and Programming National Technical University "Kharkiv Polytechnic Institute" Kharkiv Ukraine

ISBN: (纸本)9798350384499

In this work, the effectiveness of using classical machine learning methods and modern deep neural network models for intrusion detection in computer networks has been investigated. The purpose of this work is to develop a model for detecting intrusions into computer networks based on the Transformer model using tabular input data. In this work, the UNSW-NB15 dataset is used as the source data. This dataset contains information about normal network behaviour as well as during synthetic intrusions. Models for intrusion detection in computer networks based on machine learning methods were investigated: Decision Tree, KNN, Logistic Regression, SVM, Gradient Boosting, Random Forest. A method of converting tabular data into images was developed, which made it possible to build intrusion detection models based on Vision Transformer and Vision Transformer for small-size datasets on modern Transformer architecture. The research results showed that developed model based on Vision Transformer and Vision Transformer for small-size datasets improves the quality of identification, and eliminates the need for a preprocessing step such as dimensionality reduction. ©2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Spam detection with fasttext based features

Spam detection with fasttext based features

引用

2024 Innovations in Intelligent Systems and Applications Conference, ASYU 2024

作者： Karadeniz, Talha Tokdemir, Gül Maraş, H. Hakan Department of Software Engineering Çankaya University Ankara Turkey Department of Computer Engineering Çankaya University Ankara Turkey Department of Computer Programming Çankaya University Ankara Turkey

ISBN: (纸本)9798350379433

Fasttext is a powerful word representation method that creates word representations based on vectors of character n-grams. In this work, we propose a method that utilizes fasttext features for a novel feature engineering model for the spam detection problem. In the feature engineering method, the combination of average, mean of second derivative;mean peak and standard deviation of fasttext features are computed. Finally, tf-idf features are also considered for the modeling process. The success of each feature engineering technique is measured and reported. The combination of the five feature extraction methods, tested on two spam detection datasets, yielded promising results with an accuracy of 0.978 on e-mail spam detection and an accuracy of 0.986 on sms spam classification. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Study of methods for improving the meta-algorithm of the bagging classifier 4

Study of methods for improving the meta-algorithm of the bag...

引用

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

作者： Gavrylenko, Svitlana Hornostal, Oleksii Department of Computer Engineering and Programming National Technical University "Kharkiv Polytechnic Institute" Kharkiv Ukraine

ISBN: (纸本)9798350395532

In this paper, we explored approaches that improve the performance of ensemble bagging classifiers for identifying the state of a computer system. The following algorithms are considered: Ensemble pruning, Advanced Voting Algorithms, Dynamic Voting Strategies, Confidence Calibration, Adaptation through Meta-Features and Meta-Learning, which allow improving the voting procedure of the bagging meta-algorithm. Artificial data was generated as initial data, which complicates the classification task and contains an increased amount of noise. In the Google Collab environment, software models of algorithms have been developed, and their quality has been assessed. It was found that the use of the Ensemble pruning and Adaptation through Meta-Features algorithm is the most qualitative. In addition, the Ensemble pruning algorithm reduces the number of basic ensemble classifiers, and, as a result, increases the efficiency of computer system identification. Based on the results of the study, a method for identifying a computer system was proposed through the integrated use of a bagging classifier and an optimization procedure based on the Ensemble pruning algorithm. © 2023 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

A fault-tolerant scheduling strategy through proactive and clustering techniques for scientific workflows in cloud computing

引用

Soft Computing 2025年第2期29卷 755-781页

作者： Farhood, Suha Mubdir Khorsand, Reihaneh Hussein, Nashwan Jasim Ramezanpour, Mohammadreza Branch Islamic Azad University Isfahan Iran Department of Programming Collage of Information Technology University of Babylon Hillah Iraq Department of Computer Engineering Mobarakeh Branch Islamic Azad University Mobarakeh Isfahan Iran

Cloud computing offers solutions for various scientific and business applications. Large-scale scientific applications, which are organized as scientific workflows, are carried out using cloud computing. However, the higher failure rates in cloud computing can be attributed to the numerous servers and components dealing with intense workloads. This study presents a fault-tolerant scheduling approach using proactive and clustering methods for scientific workflows in cloud computing. Initially, the task clustering issue is addressed by consolidating multiple short-duration tasks into a single job to improve the runtime performance of workflow executions. Subsequently, an automated workflow scheduling strategy is outlined with four key stages: monitoring, analysis, planning, and execution. During monitoring, clustered jobs and the capacities of available cloud resources are observed. In the analysis phase, the accuracy of failure prediction is enhanced by employing the Group Method of Data Handling (GMDH) neural network prior to any faults or failures. The planning stage introduces a novel hybrid multi-objective algorithm, MOPSO-aSA, based on MOPSO and adaptive simulated annealing (SA), to streamline workflow scheduling in error-prone execution environments. Moreover, the reliability of application execution is maintained through re-clustering and migration techniques following any faults or failures. Finally, based on the experimental findings, it is evident that the proposed strategy surpasses other methods in terms of makespan, total cost, energy consumption, and failure rate. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

A zero-watermarking algorithm for use in RGB and monochrome images 5

A zero-watermarking algorithm for use in RGB and monochrome ...

引用

5th IEEE KhPI Week on Advanced Technology, KhPIWeek 2024

作者： Poddubnyi, Vadym Gvozdov, Roman Sievierinov, Oleksandr Sukhoteplyi, Vladyslav Bulba, Serhii Lysytsia, Dmytro Department of of information technology security Kharkiv National University of Radio Electronic Kharkiv Ukraine Department of Computer Engineering and Programming Ivan Kozhedub Kharkiv National Air Force University Kharkiv Ukraine Department of Computer Engineering and Programming National Technical University "Kharkiv Polytechnic Institute" Kharkiv Ukraine

ISBN: (纸本)9798350384499

the article proposes a method of zero-watermarking for colored RGB bitmap images. This algorithm can be used to protect property rights to multimedia resources in which it is impossible to use ordinary watermarks due to the impossibility of changing the image (such as medical data where high accuracy is required and the appearance of artifacts is unacceptable) or due to the presence of a higher distortion of the container. This algorithm is based on DWT, SVD and operations in the field by modulo 256. The software implementation of the algorithm was developed (using the Accord and *** libraries to implement DWT, SVD). The software implementation of the algorithm was tested. This algorithm has advantages in the form of normalization of the average error, but it needs further research to improve its performance. ©2024 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A new DEVS-based network simulator for online routing protocol education

引用

Multimedia Tools and Applications 2024年第21期83卷 60903-60919页

作者： Zengin, Ahmet Altunkaya, Cevat Kara, Şahin Sarjoughian, Hessam Computer Engineering Sakarya University Esentepe Campus Sakarya Serdivan54187 Turkey Computer Programming Sakarya Applied Science University Sakarya Kaynarca54650 Turkey School of Computing and Augmented Intelligence Arizona State University 1151 S Forest Ave TempeAZ85281 United States

Simulation continues to be highly attractive and indispensable for studying networked systems. There remains the need for simulators that can support efficient execution in large-scale, complex models and can offer a theoretical underpinning with model abstractions. A qualified and effective simulator is still hard to find in education and research. To obtain a better solution in education and research, a collection of the parallel DEVS-based computer network model components is presented in this article. The Discrete Event System Specification (DEVS) is a mathematical modeling formalism for describing (discrete and continuous) dynamical systems. Among discrete event modeling approaches, it is well suited for formally describing concurrent processing and the event-driven nature of arbitrary configuration of nodes and links forming network systems. The suggested system is developed by emphasizing the Open Shortest Path First (OSPF) protocol. These expressive models are realized in the DEVS-Suite simulator as DEVS-Suite provides a robust environment with rich support for designing experiments and visualization. Visualization representation of a typical routing protocol logic with routing tables and control packet provides better support for active learning, particularly for distance education in COVID-19 disease. The resulting OSPF-DEVS simulation environment offers a model abstraction well-suited to educational environments. An exemplary computer network model is developed and evaluated in both simulators. The simulation models have proved very helpful in understanding the basics of the computer network’s principles, designs, routing protocols, etc. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.

关键词： Abstracting

来源：评论

学校读者我要写书评

暂无评论

Analysis of Trade-Offs Between Accuracy And Speed of Real-Time Object Detectors for the Tasks of Explosive Ordnance Detection 5

Analysis of Trade-Offs Between Accuracy And Speed of Real-Ti...

引用

5th IEEE KhPI Week on Advanced Technology, KhPIWeek 2024

作者： Mishchuk, Vadym Podorozhniak, Andrii 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

ISBN: (纸本)9798350384499

This paper investigates the performance trade-offs between accuracy and inference time in real-time object detection models, particularly for detecting landmines and unexploded ordnance (UXO). Using subsets from the COCO validation dataset, the models' performance is evaluated across various input resolutions. Object detection has seen substantial advancements over the past few decades, propelled by deep learning and enhanced computational resources. However, the balance between accuracy and inference time differs among models and configurations, requiring detailed evaluation to identify the optimal solution for specific applications like landmine and UXO detection. This balance is critical for autonomous robotic systems, where swift and accurate decision-making is imperative. ©2024 IEEE.

关键词： Landmine detection

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：