检索结果-内蒙古大学图书馆

2023 International Conference on Electrical, computer, Communications and Mechatronics Engineering, ICECCME 2023

作者： Sylla, Khalifa Babou, Birahim Ouya, Samuel Department of Applied Mathematics and Computer Science Dakar Senegal Diop University Lita Laboratory Polytechnic High School Cheikh Anta Dakar Senegal

ISBN: (纸本)9798350322972

Facial recognition is applied in many sectors, including education. In fact, in engineering schools, where one of the major challenges is to train students in different sectors of activity, the presence of students is fundamental during these courses, unlike in faculties where attendance is not mandatory during lectures. In the face of massification in digital universities, the management of attendance and fraud during evaluations becomes fundamental to the credibility of the diplomas issued. This paper presents an artificial intelligence-based facial recognition system for attendance and fraud management in engineering schools and digital universities. Attendance and exam fraud management play a very important role in the training of learners. The use of this system saves a lot of time by eliminating the attendance management step by automating it while detecting fraud during exams. The solution consists of a student, course and schedule management application coupled with a facial recognition system. It detects the presence of learners during scheduled lessons and assessments through facial recognition. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

An Improved Active Machine Learning Query Strategy for Entity Matching Problem 1

引用

1st international conference on Machine Intelligence and computer science Applications, ICMICSA 2022

作者： Jabrane, Mourad Hafidi, Imad Rochd, Yassir Laboratory of Process Engineering Computer Science and Mathematics National School of Applied Sciences Khouribga University Sultan Moulay Slimane Beni Mellal Morocco

ISBN: (数字)9783031293139

ISBN: (纸本)9783031288456

Entity matching (EM) is crucial step in data integration. Supervised machine learning (SML) approaches have attained the SOTA performance in EM. In real - world scenarios SML suffers from absence or lack of large labeled data for training. Active machine learning (AML) for EM minimize the number of training data required and tries to reduce the amount of Hand labeling by picking just the helpful pairs. ALL AML approaches use just one of the two criteria - informativeness or representativeness - for query selection, Which limit their efficacy. In this work, we propose a Combined Score Sampling (CSS) that combines informativeness and representativeness selection criteria. We evaluate the CSS using the benchmark e-commerce data-sets pair Abt-Buy and AML with ensemble learning as SML model and we demonstrate that it effectively addresses the issue. Comparing our strategy to SML, we demonstrate that it lead to overall enhanced F1 score and stability of the learnt models. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Data integration

来源：评论

学校读者我要写书评

暂无评论

An Online Model for Detecting Attacks in Wireless Sensor Networks 1

引用

1st international conference on Machine Intelligence and computer science Applications, ICMICSA 2022

作者： Tabbaa, Hiba Hafidi, Imad Laboratory of Process Engineering Computer Science and Mathematics National School of Applied Sciences Khouribga University Sultan Moulay Slimane Beni Mellal Morocco

ISBN: (数字)9783031293139

ISBN: (纸本)9783031288456

The Internet of Things (IoT) has been employed in a variety of critical fields, including healthcare, geriatric surveillance, self-driving vehicles, and energy management. The most prevalent infrastructure for these applications is Wireless Sensor Networks (WSNs). Although WSNs have intriguing characteristics, the security of such networks is a major concern, especially for applications where confidentiality is extremely crucial. In order to set up WSNs securely, any type of intrusion should be identified before attackers potentially harm the network. However, research findings have demonstrated that existing approaches are ineffective, particularly in detecting attacks in real-time, mostly owing to the accumulation of enormous amounts of data through interconnected devices. Within this interpretation, our intention is to construct a robust Intrusion Detection System (IDS) for analyzing real-time network traffic of WSNs using online learning algorithm while taking into account the network’s resource constraints. To achieve this goal, we investigated the use of an online classifier, namely the Hoeffding Adaptive Tree (HAT), along with the selection of relevant attributes to distinguish four kinds of DoS attacks among normal network traffic: the attacks considered are Blackhole, Grayhole, Flooding, and Scheduling attacks. Among the experimental findings, we determined that utilizing the HAT classifier along with the Chi-squared method of feature selection, detection rate percentages were 86.75%, 80.02%, 94.92%, 99.12% and 99.03% respectively for Flooding, Scheduling, Grayhole, Blackhole and normal case attacks. With an overall accuracy of 99.03%. Based on these findings, it is indeed possible to infer that the HAT classifier is extremely beneficial for categorizing attacks, as it has managed to secure a high detection rate despite the existence of many threats. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent Solution System for Cloud Security Based on Equity Distribution:Model and Algorithms

引用

computers, Materials & Continua 2024年第1期78卷 1461-1479页

作者： Sarah Mustafa Eljack Mahdi Jemmali Mohsen Denden Mutasim Al Sadig Abdullah M.Algashami Sadok Turki Department of Computer Science and Information College of Science at ZulfiMajmaah UniversityAl-Majmaah11952Saudi Arabia Department of Computer Science College of Computing and InformaticsUniversity of SharjahSharjahUnited Arab Emirates Higher Institute of Computer Science and Mathematics University of MonastirMonastir5000Tunisia Mars Laboratory University of SousseSousseTunisia Department of Logistic and Maintenance UFR MIM at MetzUniversity of LorraineMetzFrance Department of Computer and Information Technologies College of Telecommunicationand Information Riyadh CTITechnical and Vocational Training Corporation TVTCRiyadh12464Saudi Arabia Department of Computer Science Higher Institute of Applied Sciences of SousseSousse UniversitySousse4000Tunisia

In the cloud environment,ensuring a high level of data security is in high *** planning storage optimization is part of the whole security process in the cloud *** enables data security by avoiding the risk of data loss and data *** development of data flow scheduling approaches in the cloud environment taking security parameters into account is *** our work,we propose a data scheduling model for the cloud *** is made up of three parts that together help dispatch user data flow to the appropriate *** first component is the Collector Agent whichmust periodically collect information on the state of the network *** second one is the monitoring agent which must then analyze,classify,and make a decision on the state of the link and finally transmit this information to the *** third one is the scheduler who must consider previous information to transfer user data,including fair distribution and reliable *** should be noted that each part of the proposedmodel requires the development of its *** this article,we are interested in the development of data transfer algorithms,including fairness distribution with the consideration of a stable link *** algorithms are based on the grouping of transmitted files and the iterative *** proposed algorithms showthe performances to obtain an approximate solution to the studied problem which is an NP-hard(Non-Polynomial solution)*** experimental results show that the best algorithm is the half-grouped minimum excluding(HME),with a percentage of 91.3%,an average deviation of 0.042,and an execution time of 0.001 s.

关键词： Cyber-security cloud computing cloud security algorithms heuristics

来源：评论

学校读者我要写书评

暂无评论

ILP-Based Heuristics for the Multi-Modal Stable Matching Problem

引用

Tsinghua science and Technology 2025年第2期30卷 479-487页

作者： Yang Yang Rolf H.Möhring Junteng Song Yicheng Xu Yong Zhang Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhen 518055China University of Chinese Academy of Sciences Beijing 101408China School of Applied Mathematics and Computer Science Technische Universität BerlinBerlin 10623Germany School of Mathematics and Information Science Hebei UniversityBaoding 071002China Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic TechnologyGuilin 541004China

In this paper,we investigate the stable matching problem with multiple preferences in bipartite graphs,where each agent has various preference lists for all available partners with respect to different *** problem requires that each matched agent must have exactly one partner and the obtained matching should be stable for all *** our main contribution,we present an integer linear programming(ILP)model for determining whether there exists a globally stable matching in bipartite graphs,which has been proved to be *** the time consumed for solving ILPs might dramatically increase as the size of instances grows,we develop a preprocessing technique that helps to eliminate pairs that will never be a member of any globally stable matching and thus accelerates the computing *** perform experiments on randomly generated preference lists and observe a significant speedup when we preprocess the instance before solving the *** there does not need to exist a perfect matching that is stable for all given criteria,we extend our ILP to the optimized version of the aforementioned problem,which asks to find a matching with maximum cardinality that is stable among all matched agents.

关键词： stable matching multi-modal integer linear programming(ILP)

来源：评论

学校读者我要写书评

暂无评论

Optimization of Quality Process Control and Preventive Maintenance Strategy: A Case Study

引用

Operations Research Forum 2024年第4期5卷 84页

作者： Sadraoui, Youssef Er-ratby, Mohamed Kadiri, Moulay Saddik Kobi, Abdessamad Laboratory of Process Engineering Computer Science and Mathematics LIPIM National School of Applied Sciences of Khouribga Sultan Moulay Slimane University Beni Mellal Morocco Laboratory of Science and Engineering Techniques LaSTI National School of Applied Sciences of Khouribga Sultan Moulay Slimane University Beni Mellal Morocco LARIS Angevin Laboratory for Systems Engineering Research Polytech Angers University of Angers Angers France

The studied process concerns a wet grinding and cycloning unit, set up to ensure that the particle size it processes complies with the requirements in terms of pipe transport mode. Frequent shutdowns, low reliability, the risk of delivering a product with inappropriate particle size, and the lack of operational parameters’ control are all obstacles for the unit, having enormous repercussions on its relevance and performance. To improve this situation, the implementation of an innovative 5-month quality and process control study has proven crucial to establish a culture of quality among operators, aiming to achieve the targeted grain size. However, the innovative aspects of our approach lie in its thoroughness and inclusiveness since it addresses the process both qualitatively and quantitatively, focusing not only on theoretically modeling and simulating the grinding circuit but also providing an integrated method to address every component of the unit. By going through the seven stages of this study, we were able to enhance the overall performance of the unit controlling the particle size at the output. After establishing a set of quality control tools, we observed a remarkable development in mastering various parameters influencing the targeted particle size. The benefits generated by the study are extremely satisfying for the unit at different levels, particularly in terms of quality, process control, and resource optimization. Furthermore, the integration of maintenance management into the process has proven essential to ensure the reliability and sustainability of the installation, thereby contributing significantly to the overall efficiency of the unit. Graphical Abstract: (Figure presented.) © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Optimization Preventive maintenance Process capability Quality Statistical process control SPC Wet grinding

来源：评论

学校读者我要写书评

暂无评论

Quality Process Control and Preventive Maintenance Optimization of a Grinding Unit: A Case Study 10

Quality Process Control and Preventive Maintenance Optimizat...

引用

10th International Conference on Optimization and Applications, ICOA 2024

作者： Sadraoui, Youssef Er-Ratby, Mohamed Kadiri, Moulay Saddik Kobi, Abdessamad National School of Applied Sciences Sultan Moulay Slimane University LIPIM Laboratory of Process Engineering Computer Science and Mathematics Khouribga Morocco National School of Applied Sciences Sultan Moulay Slimane University LASTI Laboratory of Science and Engineering Techniques Khouribga Morocco Polytech Angers University of Angers LARIS Angevin Laboratory for Systems Engineering Research France

ISBN: (纸本)9798350387353

The studied process is a grinding and hydroclassification unit designed to ensure that the grain size it processes is in line with the specifications for the pipe's transport mode. Obstacles to the unit's operational process include frequent stops, plant's low reliability, product delivery with an inappropriate grain size, and a lack of control over operating parameters. These factors have a significant impact on the unit's relevance and, consequently, its performance. We created a quality culture among operators with '0 grain quality loss' through the implementation of the quality and processes control study, which was essential to improve the situation. Thus, by completing the seven project stages, we were able to enhance and optimize the grinding and hydroclassification unit's overall performance and capability to regulate the grain size quality. We noticed a notable improvement in regulating the several parameters that affect the targeted particle size after we established tools for unit quality control, such as control and monitoring charts, reaction matrices, intervention flow charts and operational standards. The unit has seen a great deal of satisfaction from the project in terms of quality, process control and resources optimization. Moreover, the incorporation of preventive maintenance into this process has shown to be crucial in guaranteeing the reliability and durability of the installation, thereby substantially improving the unit's overall efficiency. © 2024 IEEE.

关键词： Preventive maintenance

来源：评论

学校读者我要写书评

暂无评论

Blockchain Sharding based Federated Learning Empowered with NFT-based Privacy-Preserving Model Sharing 6

Blockchain Sharding based Federated Learning Empowered with ...

引用

6th International Conference on Pattern Analysis and Intelligent Systems, PAIS 2024

作者： Khemaissia, Rofaida Derdour, Makhlouf Djeddai, Ala Tebessa12002 Algeria Larbi Ben m'Hidi University Liaoa Laboratory Oum El Bouaghi Algeria Chadli Bendjedid El-Tarf University Laboratory of Computer Science And Applied Mathematics El Tarf36000 Algeria

ISBN: (纸本)9798350350265

Federated learning is a promising approach that omits the central learning of the collected data through allowing the participating nodes to learn locally their model, and eventually the submitted updates are aggregated to obtain a global trained model. The main goal of this process is maintaining the participant data privacy. Blockchain is supported by lots of federated learning applications in order to handle many issues such as the single point of failure, trust, integrity, privacy and security. On top of that, Blockchain scalability issue is one of the main problems that affects the efficiency of the federated leaning. A few works have been proposed to use Blockchain sharding, yet they have some shortcomings such as static sharding. Besides, the BC approaches marginalize the global model sharing or transfer process between the model owner and the task requester. In this work, we propose FLBCShard a new Blockchain sharding approach that uses proxy nodes and a dynamic shard formation in order to improve the system scalability and improving malicious nodes detection. In addition, for a better protection of the model ownership, we use IPFS and NFT based model sharing between and transfer. The proposed work is implemented using permissioned Hyperledger Fabric and evaluated using MNIST dataset. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Security in the Industrial Internet of Drones

引用

IEEE Internet of Things Magazine 2023年第3期6卷 110-116页

作者： Svaigen, Alisson R. Boukerche, Azzedine Ruiz, Linnyer B. Loureiro, Antonio A. F. EECS PARADISE Research Laboratory University of Ottawa Ottawa Canada at Gulf University for Science and Technology The Center for Applied Mathematics Kuwait State University of Maringá Manna Research Team Maringá Brazil Federal University of Minas Gerais Department of Computer Science Belo Horizonte Brazil

The Industrial Internet of Things (IIoT) has played a key role in enabling an efficient and interconnected industry through real-time communication and processing systems, thereby building on the principles of Industry 4.0. Nowadays, industrial systems are in the process of transitioning towards Industry 5.0, where humans will once again take center stage in decision-making, supported by Artificial Intelligence (AI)-based methods. In this context, drones have emerged as a feasible device for enhancing environmental sensing tasks, reducing operational costs, alleviating communication bottlenecks, and cooperating with humans through the use of Virtual Reality (VR) and Augmented Reality (AR) platforms. Therefore, Internet of Drones (IoD) network paradigm has been adopted in the industry, giving rise to the Industrial Internet of Drones (IIoD). Given these aspects, there have been changes in the privacy and security requirements for this network environment, which demands a thorough analysis of these modifications, including the challenges that arise and possible solutions to overcome them. Consequently, this study analyzes the privacy and security issues related to IIoD. Namely, we highlight the elements of IIoD which require protection, the threats and the countermeasures. We also present how these aspects differ from the general IoD environment. Lastly, we discuss the challenges regarding IIoD security and privacy, leveraging the future directions to address Industry 5.0 aspects. © 2018 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Stability of a Delayed Stochastic Epidemic COVID-19 Model with Vaccination and with Differential Susceptibility

引用

Journal of applied mathematics and Physics 2024年第2期12卷 509-532页

作者： Modeste N’zi Boubacar Sidiki Kouyaté Ilimidi Yattara Modibo Diarra Laboratory of Applied Mathematics and Computer Science University Felix Houphouet-Boigny Abidjan C&#244te d’Ivoire Department of Mathematics and Computer Science University of Science Technic and Technologies Bamako Mali

In this paper, we treat the spread of COVID-19 using a delayed stochastic SVIRS (Susceptible, Infected, Recovered, Susceptible) epidemic model with a general incidence rate and differential susceptibility. We start with a deterministic model, then add random perturbations on the contact rate using white noise to obtain a stochastic model. We first show that the delayed stochastic differential equation that describes the model has a unique global positive solution for any positive initial value. Under the condition R₀ ≤ 1, we prove the almost sure asymptotic stability of the disease-free equilibrium of the model.

关键词： SIRS Delayed Epidemic Model Nonlinear Incidence rate Lyapunov Function Asymptotic Stability in Probability

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：