2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)最新文献

筛选
英文 中文
Industrial IoT (IIOT) Architecture for Remote Solar Plant Monitoring 用于太阳能电站远程监控的工业物联网(IIOT)架构
2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet) Pub Date : 2022-09-15 DOI: 10.1109/RoEduNet57163.2022.9921045
Vladimir Voicu, D. Petreus, E. Cebuc, R. Etz
{"title":"Industrial IoT (IIOT) Architecture for Remote Solar Plant Monitoring","authors":"Vladimir Voicu, D. Petreus, E. Cebuc, R. Etz","doi":"10.1109/RoEduNet57163.2022.9921045","DOIUrl":"https://doi.org/10.1109/RoEduNet57163.2022.9921045","url":null,"abstract":"This paper proposes a redundant IIoT network architecture design for SCADA systems in photovoltaic (PV) / solar power plants. IIOT is found at the crossroads of SCADA and IOT, and therefore it encompasses the monitoring and control part of the former, and the data analysis of the latter. Using two industrial carrier boards from Waveshare based on Raspberry Pi Compute module 4 (CM4), a redundant gateway protocol translator is achieved. Data sent from various sensors - used for site monitoring, connected to the peripherals can be encapsulated for transport to the central management system for analysis and decision making. This ensemble is used in solar panel monitoring in our experimental setup alongside various environmental sensors for weather analysis and forecasting. To ensure security over the Internet, a VPN tunnel is established between the egress location and the central system. Being connected via VPN to the central control location ensures a degree of security in communications. Having an always ready data link to the central system guarantees that any modifications an operator makes on the remote solar power plant are to be executed without delay.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124566657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Classification algorithm of an automated sorting system for Construction and Demolition Waste materials 建筑及拆建废物自动分类系统的分类算法
2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet) Pub Date : 2022-09-15 DOI: 10.1109/RoEduNet57163.2022.9921053
G. Suciu, Ioana Petre, G. Iordache, Tapurica Ionel, S. Simionescu
{"title":"Classification algorithm of an automated sorting system for Construction and Demolition Waste materials","authors":"G. Suciu, Ioana Petre, G. Iordache, Tapurica Ionel, S. Simionescu","doi":"10.1109/RoEduNet57163.2022.9921053","DOIUrl":"https://doi.org/10.1109/RoEduNet57163.2022.9921053","url":null,"abstract":"Construction and Demolition Waste (CDW) management market size has reached in 2021 USD 212.8 Billion and its constantly increasing and expected to reach USD 287.4 Billion by 2027. The demolition of existing infrastructures generates more than twenty types of materials. CDW management aims at the disposing and reusing the materials to reduce the negative impact on the environment and the consumption of raw materials which have higher costs at present after the COVID-19 pandemic. In the last years, the integration of AI and robots for efficient recycling activities in CDW has been increasing. The development of a system for CDW material handling and processing composed of a robotic arm and classification algorithm will have important benefits such as increasing the total amount of recycled material, maximize the economic value of recycled materials and products, reducing the environmental degradation, greenhouse gas emissions, pollution, contamination. This paper aims to present a classification algorithm for fast identification and selection of CDW materials based on information obtained from several hyperspectral cameras and sensors. The main goal is the division of the materials from the conveyor belt into specific groups and their placement into dedicated bins.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134219643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Video Streaming Evaluation Using Priority Queuing in P4 Programmable Networks P4可编程网络中基于优先队列的视频流评估
2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet) Pub Date : 2022-09-15 DOI: 10.1109/RoEduNet57163.2022.9921096
Calin-Marian Iurian, Robert Botez, I. Ivanciu, V. Dobrota
{"title":"Video Streaming Evaluation Using Priority Queuing in P4 Programmable Networks","authors":"Calin-Marian Iurian, Robert Botez, I. Ivanciu, V. Dobrota","doi":"10.1109/RoEduNet57163.2022.9921096","DOIUrl":"https://doi.org/10.1109/RoEduNet57163.2022.9921096","url":null,"abstract":"There is an increasing popularity of domain-specific languages such as P4 and of the capability to write code for improving the device performance. Therefore, the time-critical traffic becomes decisive to avoid network and service disruption due to a poor implementation. To handle real-time traffic and latency-sensitive applications (e.g., video streaming) in a Software-Defined Network (SDN) environment, the trustworthy and secure mechanisms are needed to guarantee a minimum end-to-end delay and to manage response time. This paper presents a P4-based switch solution to improve the data-control performance and to provide efficient queuing in SDN. Additionally, we studied how priority queuing mechanisms can help in achieving a solid video quality. In contradiction, a poor network implementation can lead to a longer network delay, which can make the video unplayable. The network was developed using the Behavioral Model v2 of the P4 language.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115427693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
RoEduNet 2022 Cover Page RoEduNet 2022封面页
2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet) Pub Date : 2022-09-15 DOI: 10.1109/roedunet57163.2022.9921080
{"title":"RoEduNet 2022 Cover Page","authors":"","doi":"10.1109/roedunet57163.2022.9921080","DOIUrl":"https://doi.org/10.1109/roedunet57163.2022.9921080","url":null,"abstract":"","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124404514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Network Congestion Solution for FTP Services Based on Distributed Firewall and Snort 基于分布式防火墙和Snort的FTP服务网络拥塞解决方案
2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet) Pub Date : 2022-09-15 DOI: 10.1109/RoEduNet57163.2022.9921099
Andrei-Daniel Tudosi, A. Graur, D. Balan, A. Potorac
{"title":"Network Congestion Solution for FTP Services Based on Distributed Firewall and Snort","authors":"Andrei-Daniel Tudosi, A. Graur, D. Balan, A. Potorac","doi":"10.1109/RoEduNet57163.2022.9921099","DOIUrl":"https://doi.org/10.1109/RoEduNet57163.2022.9921099","url":null,"abstract":"The exploit of network traffic has become common due to the increased flow of web traffic from services like Hypertext Transfer Protocol (HTTP), File Transfer Protocol (FTP), Simple Mail Transfer Protocol (SMTP), and others. The number of cyberattacks has grown therefore they require different information about a target with the purpose of intimidating, blackmailing or harassing a person or a company. Servers of different industries, including medical and dental organizations, have become a good source of information for cyber criminals, due to the huge information stored across years. Besides compromised health data, another problem with huge impact is congestion of a network. If a network of database servers is overcrowded, the result is high delays in obtaining the information of a patient that needs urgent medical care. In this paper, an overview of traffic generated by a network simulator during a User Datagram Protocol (UDP) flood is presented, also a solution to this type of network attack, consisting in a custom firewall rule, that obtains significant improvements in the network resources usage. The solution is implemented to prove the necessity of improving the security of FTP.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125674201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Convolutional Neural Networks for Environmental Sound Recognition 环境声音识别的卷积神经网络
2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet) Pub Date : 2022-09-15 DOI: 10.1109/RoEduNet57163.2022.9920993
Svetlana Segarceanu, G. Suciu
{"title":"Convolutional Neural Networks for Environmental Sound Recognition","authors":"Svetlana Segarceanu, G. Suciu","doi":"10.1109/RoEduNet57163.2022.9920993","DOIUrl":"https://doi.org/10.1109/RoEduNet57163.2022.9920993","url":null,"abstract":"Environmental sound recognition is now an important field of computer science, with applications in manifold domains like security, environment protection, wildlife monitoring. The current methodology evolved from methods used in speech-based applications to more specific approaches, and with the rapid growth of the deep learning technologies many attempts using these methods came about. The paper extends our former research using Deep Feed Forward Neural Networks, by exploring the Convolutional Neural Networks for the recognition of environmental sounds susceptible to indicate a logging activity in forest environment. Unlike other Convolutional Neural Networks solutions to AESR, where the input data ix based either on Log-MelSpectrograms or raw data, we will use as input data linear frequency Log Spectrograms. We will compare these results with the ones obtained with Deep Deed forward Neural Networks applied on Fourier power spectrum.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128013740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Solar Power Prediction Based on Weather Forecast 基于天气预报的太阳能发电预测
2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet) Pub Date : 2022-09-15 DOI: 10.1109/RoEduNet57163.2022.9921070
F. B. Manolache, O. Rusu
{"title":"Solar Power Prediction Based on Weather Forecast","authors":"F. B. Manolache, O. Rusu","doi":"10.1109/RoEduNet57163.2022.9921070","DOIUrl":"https://doi.org/10.1109/RoEduNet57163.2022.9921070","url":null,"abstract":"Prediction of an evolving system behavior based on a sparse historic data set is hardly achievable with current artificial intelligence concepts, even if using massive computing power. This paper presents a novel prediction technique for such difficult cases. The technique is based on local regression and dimensional splitting of the parameter space. As an application, the power generated by a generic solar cell is predicted, based on the weather forecast obtained from public sources. The algorithm maintains a good balance between generating reasonably good predictions and keeping the computation needs very low. Several common prediction strategies are compared, proving the superiority of an adaptive approach. Measurements on an experimental device are used to validate the prediction technique.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125409478","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Scalable Deployments for Real-Time AI Video Stream Processing 实时AI视频流处理的可扩展部署
2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet) Pub Date : 2022-09-15 DOI: 10.1109/RoEduNet57163.2022.9921091
Catalin Patrascu, Adrian Cosma, I. Radoi
{"title":"Scalable Deployments for Real-Time AI Video Stream Processing","authors":"Catalin Patrascu, Adrian Cosma, I. Radoi","doi":"10.1109/RoEduNet57163.2022.9921091","DOIUrl":"https://doi.org/10.1109/RoEduNet57163.2022.9921091","url":null,"abstract":"Real-time stream processing is becoming more prevalent today due to huge chunks of data needing to be processed upon arrival. In video streaming the need for real-time management is both important and challenging because video frames come at high frequency. AI advances have made it possible to understand video feeds at a high level in real-time, making them a valuable source of information in regards to human behavior, trends, surveillance and much more. As a consequence of these reasons, there is a need for a highly performant and deployable system in terms of latency, scalability, accuracy of results and computing power, which leverages the cloud as a service. A design for a low-latency and highly scalable system is much needed as video stream processing or video analytics has uses in areas such as surveillance, real-time video analytics, criminality and autonomous vehicles, which require fast and accurate analysis of data. Such a system should be able to employ not only streaming but also different processing actions including machine learning models which can be applied to frames resulting in data analysis or further data pipelines. We developed a scalable real-time video processing system which consumes video frames, processes them using deep learning models, renders them and stores the resulting semantic information in a database for further downstream processing. We show that our proposed processing architectures are a suitable solution for modern video analytics systems, which can be scaled both vertically and horizontally, and achieves real-time latency within maximum of 1 second for frame rates ranging from 10 to 60 fps.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124143429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Symmetric Multiprocessor Support for bhyve on arm64 在arm64上支持bhyve的对称多处理器
2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet) Pub Date : 2022-09-15 DOI: 10.1109/RoEduNet57163.2022.9921081
Andrei-Costin Martin, Darius Mihai, Marian Mihailescu, M. Cărăbaş, N. Tapus
{"title":"Symmetric Multiprocessor Support for bhyve on arm64","authors":"Andrei-Costin Martin, Darius Mihai, Marian Mihailescu, M. Cărăbaş, N. Tapus","doi":"10.1109/RoEduNet57163.2022.9921081","DOIUrl":"https://doi.org/10.1109/RoEduNet57163.2022.9921081","url":null,"abstract":"In the years, ARM started to take its share of the personal computers and server markets. Their CPUs are known for their low power consumption and mobile market supremacy. In these new areas, virtualization is used to provide working machines in the cloud and create secure environments. The FreeBSD community started developing an ARM-based hypervisor, but it was not tested on real hardware and without some features that AMD64 has. Furthermore, nowadays, computers usually have more CPUs, to perform the task in parallel and increase the speed of the overall system. This paper presents the SMP (Symmetric Multiprocessor Support) added to bhyve on arm64. This feature allows the user to start a virtual machine when the host operating system has more than one cores and the ability to start a virtual machine with more virtual CPUs.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130995844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Hiding cloud network access patterns for enhanced privacy 隐藏云网络访问模式以增强隐私
2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet) Pub Date : 2022-09-15 DOI: 10.1109/RoEduNet57163.2022.9920974
Gabriel-Cosmin Apostol, Bogdan-Costel Mocanu, Dragos-Mihai Radulescu, Ionut Petre, Florin Pop
{"title":"Hiding cloud network access patterns for enhanced privacy","authors":"Gabriel-Cosmin Apostol, Bogdan-Costel Mocanu, Dragos-Mihai Radulescu, Ionut Petre, Florin Pop","doi":"10.1109/RoEduNet57163.2022.9920974","DOIUrl":"https://doi.org/10.1109/RoEduNet57163.2022.9920974","url":null,"abstract":"The cybersecurity landscape in the last years has evolved significantly. Considering the fact that more than 281 million people were affected by cyber-threads in 2021 with an estimated financial impact of more than $15.680 million, the research for security mechanisms for better services has risen significantly. One of the most active trends in cybersecurity offensive procedures is perimeter breaching. This represents the incipient step that attackers take when they target external networks. On average the penetration of the internal networks takes no more than two days, therefore, the defense mechanisms should comply with this hard deadline. Therefore, in this paper, we propose a real-time approach that solves the privacy issues posed by network protocol profiling and surveillance. This can be done by disguising the generated traffic using different transport protocols like chat or gaming services. In order to choose the right channels which can be used, we identified the most prominent ones like Extensible Messaging and Presence Protocol (XMPP) or Internet Relay Chat (IRC) chat and the AllJoyn network, a service used mainly for multiplayer communication in gaming environments on mobile terminals. We evaluate the proposed solution considering metrics such as time frame, speed, and rate limiting delay.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126790737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信