An underwater glider is a special type of remotely operated underwater vehicle employed for research and monitoring the underwater environment. This article presents the design and fabrication of an underwater glider ...
详细信息
Microservice architecture is a key component of modern distributed softwaresystems, providing scalability and independent deployment of individual components. However, many different factors, such as the dynamic vari...
详细信息
ISBN:
(数字)9798331531836
ISBN:
(纸本)9798331531843
Microservice architecture is a key component of modern distributed softwaresystems, providing scalability and independent deployment of individual components. However, many different factors, such as the dynamic variability of modern Internet services and the evolution of user requests, can offset the advantages of microservices. Machine learning algorithms, in particular deep reinforcement learning, are an effective way to optimize distributed softwaresystems, allowing adaptive management of system resources in non-stationary environments. This paper discusses the integration of multi-agent reinforcement learning into a micro service architecture. The paper demonstrates the results of training intelligent agents in the road selection service based on the current weather condition. Three methods of integrating deep Q-Iearning into the microservice architecture were developed, and three classical algorithms of deep reinforcement learning were used to evaluate the effectiveness of the methods.
Despite technological advancements, ensuring aircraft safety remains a challenge, however, Machine learning (ML)-based approaches for predicting future incidents play a crucial role in addressing flight safety. As ML ...
详细信息
Starting with software Defined Networking (SDN) and Network Functions Virtualization (NFV) technologies, network slicing is emerging as a critical technology in 5G-Advanced and 6G mobile communications to allocate log...
详细信息
In the context of the growing use of software, code security is of particular importance for preventing data leakages, financial losses and threats to national security. This paper proposes a hybrid approach to decisi...
详细信息
ISBN:
(数字)9798331531836
ISBN:
(纸本)9798331531843
In the context of the growing use of software, code security is of particular importance for preventing data leakages, financial losses and threats to national security. This paper proposes a hybrid approach to decision support for ensuring code security based on a combination of the results of static and dynamic code analysis. Static and dynamic analysis together allow identifying and eliminating vulnerabilities at various stages of the software development life cycle. The proposed approach is implemented as a decision support system for ensuring the software code security. During the experiment conducted on the implemented system, it was found that the use of the decision support module allows more efficient analysis of data on identified vulnerabilities. The system visualizes the results in graphical form, which facilitates the decision-making process for the user. In the presence of large data volumes and complex calculations, the human factor can lead to errors, which makes automation of the analysis process especially important. The results of the experiment confirm that the proposed approach not only improves the analysis quality, but also contributes to a more reliable software development process, given the constantly changing threat landscape.
Undetected anomalous incidents on the freeway, such as crashes, can cause increased congestion and secondary crashes. To address this problem, we recently released a real freeway traffic anomalous event detection data...
详细信息
ISBN:
(纸本)9798400714986
Undetected anomalous incidents on the freeway, such as crashes, can cause increased congestion and secondary crashes. To address this problem, we recently released a real freeway traffic anomalous event detection dataset. However, our evaluation was limited to a static week of traffic data. This demo presents a live anomaly detection dashboard, processing sensor data with a 1-minute delay. It has interactive components to adjust the anomaly detection performance, providing a realistic evaluation of graph anomaly detection methods for long-term analysis and method improvements.
Address Resolution Protocol (ARP) spoofing is a severe threat in software-Defined Networking (SDN) systems, allowing attackers to modify network traffic via Man-in-the-Middle (MITM) attacks. This study presents an eff...
详细信息
ISBN:
(数字)9798331543891
ISBN:
(纸本)9798331543907
Address Resolution Protocol (ARP) spoofing is a severe threat in software-Defined Networking (SDN) systems, allowing attackers to modify network traffic via Man-in-the-Middle (MITM) attacks. This study presents an effective proactive ARP spoofing defense that uses SDN's centralized control and programmability features. The system continually analyzes ARP packets, keeps an accurate logical and physical address mapping, and dynamically adds flow restrictions to prevent malicious hosts from imitating legitimate devices. The proposed system identifies and prevents single and multiple source ARP spoofing attacks in real-time at O(1) processing cost, resulting in low network overhead. The experiment conducted on an SDN-simulated environment proved that the Ryu controller can mitigate ARP spoofing attempts while preserving legitimate network activities. Furthermore, the proposed technique can scale in terms of network capacity and traffic volume. The proposed automated and scalable ARP spoofing approach enhances SDN cybersecurity.
This paper introduces a novel personalized book recommendation system that integrates emotional understanding and contextual relevance to enhance the accuracy and personalization of suggestions. The system employs a h...
详细信息
ISBN:
(数字)9798331522216
ISBN:
(纸本)9798331522223
This paper introduces a novel personalized book recommendation system that integrates emotional understanding and contextual relevance to enhance the accuracy and personalization of suggestions. The system employs a hybrid filtering method, combining content-based and collaborative filtering, to address the limitations of traditional recommendation systems. By incorporating Explainable AI (XAI), the system provides transparent justifications for each recommendation, enhancing user trust and engagement. Additionally, sentiment analysis and contextual factors, such as weather, time of day, and the user's emotional state, are considered to ensure that the recommended books align with the user's current circumstances. Our findings show that the integration of Explainable AI significantly improved user satisfaction and engagement. Testing with 100 participants resulted in a high level of satisfaction, with 55% reporting that they found the recommendations more trustworthy due to explanations. The system makes a significant contribution to improving emotional well-being by providing personalized recommendations.
With the rapid advancement of blockchain technology, a significant trend is the adoption of Directed Acyclic Graphs (DAGs) as an alternative to traditional chain-based architectures for organizing ledger records. Syst...
详细信息
ISBN:
(数字)9798331523114
ISBN:
(纸本)9798331523121
With the rapid advancement of blockchain technology, a significant trend is the adoption of Directed Acyclic Graphs (DAGs) as an alternative to traditional chain-based architectures for organizing ledger records. systems like IOTA, which are specially designed for the Internet of Things (Io'T), leverage DAG-based architectures to achieve greater scalability by enabling multiple attachment points in the ledger for new transactions while allowing these transactions to be added to the network without incurring any fees. To determine these attachment points, many tip selection algorithms commonly employ specific strategies on the DAG ledger. Transaction prioritization is not considered in the IOTA network, which becomes especially important when network bandwidth is limited. In this paper, we propose an optimization framework designed to integrate a priority level for critical or high-priority IoT transactions within the IOTA network. We evaluate our system using fully based on the official IOTA GitHub repository, which employs the currently operational IOTA node software (Hornet version), as part of the Chrysalis update (1.5). The experimental results show that higher-priority transactions in the proposed algorithm reach final confirmation in less time compared to the original IOTA system.
暂无评论