检索结果-内蒙古大学图书馆

12th IEEE International conference on Identification, Information and Knowledge in the internet of Things, IIKI 2024

作者： Mei, Liyao Zhang, Junyu Long, Teng School of information Engineering Beijing China

ISBN: (纸本)9798331510633

Deep learning plays a growing and crucial role on the internet of Things (IoT), especially in intelligent data analysis, decision support, and automation control. YOLOv5, as an efficient model for target detection in deep learning, inherits the high-efficiency features of the YOLO series, and significantly improves the performance of real-time detection applications by enhancing the structure of the network and the optimization of the loss function. The article introduces the network structure of YOLOv5 and emphasizes an analysis of its advantages in target detection tasks. Then, the article details the optimization of the network structure based on YOLOv5, including the attention mechanism(CA) and the bidirectional feature pyramid network (BiFPN) structure. In addition, extensions of the evaluation metrics are explored, especially the improved IoU loss functions (e.g., CIoU, EIoU, and SIoU), which address the limitations of the standard IoU loss functions in dealing with targets of different shapes and sizes by introducing new penalty terms. YOLOv5 has been widely used in the IoT domain, and has demonstrated usefulness in the areas of smart city, agricultural monitoring, industrial automation, and environmental monitoring, etc., showing utility and effectiveness, while it has a promising application in the IoT field. By further optimizing the network structure of YOLOv5 and combining it with other AI techniques, it can drive IoT systems towards greater intelligence and automation. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Deep-Reinforcement-Learning-Based Drone Base Station Deployment for Wireless Communication Services

引用

IEEE internet OF THINGS JOURNAL 2022年第21期9卷 21899-21915页

作者： Tarekegn, Getaneh Berie Juang, Rong-Terng Lin, Hsin-Piao Munaye, Yirga Yayeh Wang, Li-Chun Bitew, Mekuanint Agegnehu Natl Taipei Univ Technol Dept Elect Engn & Comp Sci Taipei 10608 Taiwan Feng Chia Univ Dept Elect Engn Taichung 40724 Taiwan Natl Taipei Univ Technol Dept Elect Engn Taipei 10608 Taiwan Bahir Dar Univ Fac Comp Bahir Dar Inst Technol Bahir Dar 26 Ethiopia Natl Chiao Tung Univ Dept Elect & Comp Engn Hsinchu 30010 Taiwan

Over the last few years, drone base station (DBS) technology has been recognized as a promising solution to the problem of network design for wireless communication systems, due to its highly flexible deployment and dynamic mobility features. This article focuses on the 3-D mobility control of the DBS to boost transmission coverage and network connectivity. We propose a dynamic and scalable control strategy for drone mobility using deep reinforcement learning (DRL). The design goal is to maximize communication coverage and network connectivity for multiple real-time users over a time horizon. The proposed method functions according to the received signals of mobile users, without the information of user locations. It is divided into two hierarchical stages. First, a time-series convolutional neural network (CNN)-based link quality estimation model is used to determine the link quality at each timeslot. Second, a deep Q-learning algorithm is applied to control the movement of the DBS in hotspot areas to meet user requirements. Simulation results show that the proposed method achieves significant network performance in terms of both communication coverage and network throughput in a dynamic environment, compared with the Q-learning algorithm.

关键词： Channel estimation communication coverage convolutional neural network (CNN) deep reinforcement learning (DRL) drone base station (DBS) mobility control network connectivity

来源：评论

学校读者我要写书评

暂无评论

Measurement of Cloud-based Game Streaming System Response to Competing TCP Cubic or TCP BBR Flows 22

Measurement of Cloud-based Game Streaming System Response to...

引用

22nd ACM internet Measurement conference (IMC)

作者： Xu, Xiaokun Claypool, Mark Worcester Polytech Inst Worcester MA 01609 USA

ISBN: (纸本)9781450392594

Cloud-based game streaming is emerging as a convenient way to play games when clients have a good network connection. However, high-quality game streams need high bitrates and low latencies, a challenge when competing for network capacity with other flows. While some network aspects of cloud-based game streaming have been studied, missing are comparative performance and congestion responses to competing TCP flows. This paper presents results from experiments that measure how three popular commercial cloud-based game streaming systems - Google Stadia, NVidia GeForce Now, and Amazon Luna - respond and then recover to TCP Cubic and TCP BBR flows on a congested network link. Analysis of bitrates, loss rates and round-trip times show the three systems have markedly different responses to the arrival and departure of competing network traffic.

关键词： Transmission control protocol

来源：评论

学校读者我要写书评

暂无评论

Unified View of IoT and CPS Security and Privacy

Unified View of IoT and CPS Security and Privacy

引用

International conference on Computing, networking and Communications (ICNC)

作者： Luo, Lan Morales-Gonzalez, Christopher Wang, Shan Ling, Zhen Fu, Xinwen Anhui Univ Technol Maanshan Anhui Peoples R China Univ Massachusetts Lowell Lowell MA USA Hong Kong Polytech Univ Hong Kong Peoples R China Southeast Univ Email Zhenling Seueducn Nanjing Peoples R China

ISBN: (纸本)9798350371000;9798350370997

The concepts of internet of Things (IoT) and Cyber Physical systems (CPS) are closely related to each other. IoT is often used to refer to small interconnected devices like those in smart home while CPS often refers to large interconnected devices like industry machines and smart cars. In this paper, we present a unified view of IoT and CPS: from the perspective of network architecture, IoT and CPS are similar given that they are based on either the OSI model or TCP/IP model. In both IoT and CPS, networking/communication modules are attached to original things so that isolated things can be integrated into cyber space. If needed, actuators can also be integrated with a thing so as to control the thing. With this unified view, we can perform risk assessment of an IoT/CPS system from six factors, hardware, networking, operating system (OS), software, data and human. To illustrate the use of such risk analysis framework, we analyze an air quality monitoring network, smart home using smart plugs and building automation system (BAS). We also discuss challenges such as cost and secure OS in IoT security.

关键词： internet of things

来源：评论

学校读者我要写书评

暂无评论

GAT-based Deep Reinforcement Learning Algorithm for Real-time Task Scheduling on Multicore Platform 36

GAT-based Deep Reinforcement Learning Algorithm for Real-tim...

引用

36th Chinese control and Decision conference (CCDC)

作者： Zhao, Mingjun Mo, Lei Liu, Ji Han, Jie Niu, Dan Southeast Univ Sch Automat Nanjing 210096 Peoples R China Hithink RoyalFlush Informat Network Co Ltd Hangzhou 310023 Peoples R China

ISBN: (纸本)9798350387780;9798350387797

The scheduling of real-time and dependent tasks on multicore systems plays an important role in influencing system performance. During the scheduling process, multiple constraints should be taken into account, e.g., task dependency, real-time response, and energy efficiency. The complex task scheduling problem makes it difficult to balance solution quality and computation time. Existing works either use time-consuming methods to find optimal solutions or get feasible solutions through heuristic methods. In this paper, we propose a GAT (graph attention network)-based deep reinforcement learning (DRL) algorithm to solve task scheduling problems. This method combines the benefits of deep learning (DL) networks and reinforcement learning (RL) algorithms. It can achieve adaptive learning and adjust information features by constructing the GAT to model the dependencies between tasks. At the same time, we use the soft actor-critic (SAC) algorithm to optimize the task scheduling policy to minimize the makespan of scheduling results. The experimental results show that our method outperforms other scheduling methods regarding scheduling efficiency (the quality of task scheduling problem) and algorithm running time.

关键词： Deep reinforcement learning graph attention network multicore system dependent real-time task task scheduling

来源：评论

学校读者我要写书评

暂无评论

A Spatiotemporal Model for Hard-Deadline Multistream Traffic in Uplink IoT networks

引用

IEEE internet OF THINGS JOURNAL 2022年第1期9卷 601-615页

作者： Tang, Weijun Zhang, Rongbin Feng, Suili South China Univ Technol Sch Elect & Informat Engn Guangzhou 510641 Peoples R China Shantou Univ Dept Elect & Informat Engn Shantou 515063 Peoples R China

Ultrareliable and delay-intolerant message delivery is one of the key components for internet of Things (IoT) and cyber-physical systems to support real-time control and real-time interaction. In this article, we provide a spatiotemporal framework that captures the packet loss rate (PLR) for large-scale grant-free uplink IoT networks with multiple types of hard-deadline traffic. An independent and a prioritized packet scheduling schemes are proposed and investigated for efficiently realizing frequency diversity. Tools from stochastic geometry and queuing theory are utilized to account for the macroscopic coverage probability and microscopic PLR. The expressions of devices' coverage, steady state distribution, and PLR of services are derived for both scheduling schemes. Detailed system-level simulations are used to identify network design guidelines. The results show that the independent scheme provides better network scalability and consumes lower average transmit power at the devices, while the prioritized scheme enhances the PLR performance of high priority service and requires lower peak transmit power of devices.

关键词： internet of Things Uplink Spatiotemporal phenomena performance evaluation Ultra reliable low latency communication Scalability quality of service Grant-free access hard deadlines internet of Things (IoT) priority queuing stochastic geometry

来源：评论

学校读者我要写书评

暂无评论

TCP CUBIC with HyStart: Congestion control for Satellite Communication in OMNeT++ INET 29

TCP CUBIC with HyStart: Congestion Control for Satellite Com...

引用

29th IEEE Asia Pacific conference on Communications, APCC 2024

作者： Martino, Luigi Deutschmann, Jorg Hielscher, Kai-Steffen German, Reinhard Friedrich-Alexander-Universität Erlangen-Nürnberg Computer Networks and Communication Systems Germany

ISBN: (纸本)9798331517816

In the context of satellite communication, unique challenges arise, such as long delay links that can impact the network performance also at the Transport Layer. With regard to the Transmission control Protocol (TCP), congestion control plays a crucial role in managing network traffic and ensuring efficient data transmission over the internet. This paper wants to give an overview of how TCP congestion control mechanisms adapt to mitigate the effects of long link delays, highlighting the importance of optimizing protocols for these specific environments. Within this context, where signals travel extended distances, traditional TCP algorithms designed for terrestrial networks with relatively low latency, may struggle to maintain optimal performance. As a result, specialized congestion control algorithms, like TCP CUBIC, can be employed to address these challenges. Through the integration of TCP CUBIC with HyStart within a simulation framework based on OMNeT++ and INET, this study sheds light on the importance of tailoring congestion control strategies to suit specific network environments including satellite communication. © 2024 IEEE.

关键词： Transmission control protocol

来源：评论

学校读者我要写书评

暂无评论

Optimized Handoff in IoT

Optimized Handoff in IoT

引用

2024 International conference on Futuristic Technologies in control systems and Renewable Energy, ICFCR 2024

作者： Meenakshi Kumar, Satyam Chandigarh University Ece Department Mohali India Chandighar University It Department Mohali India

ISBN: (纸本)9798331504601

As wireless technologies and mobile are continuously expanding, it become necessary for future wireless communication to incorporate multiple networks with unique features. Mobile devices must seamlessly switch between networks with varying access interfaces and technologies to meet user demands for connectivity anytime and anywhere for all type of service. Although next-generation wireless networks offer improved data offerings, maintaining quality of service but maintain a seamless connection is still a big issue. To ensure optimal network connections, numerous vertical handoff protocols have been developed, and this paper provides an overview and categorization of these schemes and their characteristics. Additionally, we compare quality of Service (QoS) aware vertical handoff algorithm with some of the existing techniques. The QoS aware handoff procedures reduce the handoff delay, handoff failure probability, and energy consumption which result the better handoff. The whole research is performed on NS2 software where it's demonstrated that proposed research approach may result better result than existing approach. © 2024 IEEE.

关键词： internet of things

来源：评论

学校读者我要写书评

暂无评论

A study on Anomaly-based Intrusion Detection systems Employing Supervised Deep Learning Techniques 8

A study on Anomaly-based Intrusion Detection Systems Employi...

引用

8th International conference on Inventive systems and control, ICISC 202

作者： Shaffi, Abubucker.S. Chacko, John Velloreuzhathil Eliyan, Greeshma Balaji, S. Gulf College Department of Computing Sciences Oman Al Zahra College for Women Department of Information Technology Ghala Muscat Oman

ISBN: (纸本)9798350386578

The rise of smart cities, driverless automobiles, smart watches, and mobile banking has led to increased reliance on the internet. Although technology has enormous advantages for people and society, it also introduces threats. Cyber attacks are more common in this digital world and the intruders are working hard to enter into the business websites or an organization data server. Hence, integrating an intrusion detection system (IDS) is essential in the security environment because it enables IT infrastructure to resist threats. Conventional IDS are limited to detect only sophisticated attacks and fails to detect the hidden and other anomalies that occur in the network systems. An accurate and strong approach for IDS must be created to solve this difficulty for the successful functioning of businesses. The present study explores the use of supervised Deep Learning (DL) techniques and recommends an effective model for anomaly detection. The performance evaluation of the model is performed using NSL-KDD dataset and KDDcup99 and the explored DL models in this study are compared in terms of accuracy and precision. © 2024 IEEE.

关键词： network intrusion

来源：评论

学校读者我要写书评

暂无评论

Real-Time Communication Model for IoT systems 18

Real-Time Communication Model for IoT Systems

引用

18th conference on Computer Science and Intelligence systems, FedCSIS 2023

作者： Deniziak, Stanislaw Plaza, Miroslaw Arcab, Lukasz Kielce University of Technology Faculty of Electrical Engineering Automatic Control and Computer Science Kielce Poland

ISBN: (纸本)9788396744784

internet of Things solutions typically involve interaction between sensors, actuators, the cloud, embedded systems and user applications. Often in such cases, there are time constraints specifying the maximum response time to a request. This time depends on the calculation time and transmission time. Existing internet communication solutions do not ensure the implementation of transmissions in a way that guarantees meeting the set time constraints. This paper proposes a new model of internet communication dedicated to real-time internet of Things systems, which includes a communication protocol, as well as a transmission scheduling and routing method. The protocol takes into account information about transmission time constraints, which is used for packet scheduling by routers, allowing to increase quality of service. In addition, the proposed static routing mechanism makes it possible to parallelize transmissions if time constraints are still exceeded. Also presented are preliminary results of experiments showing to what extent the proposed methods allow improving the quality of service in real-time internet of Things systems. © 2023 Polish Information Processing Society.

关键词： internet of things

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：