检索结果-内蒙古大学图书馆

IEEE Advanced Information Management,Communicates,Electronic and Automation control conference (IMCEC)

作者： Weiye Han Yuyang Zhang Wenxuan Qiao Ping Dong School of Electronic and Information Engineering Beijing Jiaotong University Beijing China

ISBN: (数字)9798350316537

ISBN: (纸本)9798350316544

With the rapid popularization of mobile internet, the requirements for the internet in various application scenarios have gradually increased. Under the mobile network, mobile internet devices will generate a large amount of important information in the network, which can be used to analyze the link status and operational performance of the entire network. Safe and effective management and control of these remote devices will help the entire network and technology optimization and upgrade. However, most current network architectures have problems such as poor scalability and single points of failure. Therefore, in order to carry out hierarchical on-demand management and control of large-scale network devices with complex scenarios, we propose a domain-based network management and control system for mobile devices. This system divides remote mobile devices into domain networks according to scenarios. At the same time, it can connect the remote ends of different domain networks through tunnel routing technology to facilitate management and control. In order to improve transmission efficiency, a method based on mobile vehicles is proposed. At the end of the system, a transmission strategy for data adaptive adjustment is carried out; at the same time, detailed planning and analysis of the system's security protection and fault prevention are carried out. The final test results show that the system can make full use of network resources to achieve domain-based management and control of remote mobile devices.

关键词： Scalability control systems Market research Mobile handsets internet Planning Topology

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based video quality enhancement for the new versatile video coding

引用

NEURAL COMPUTING & APPLICATIONS 2022年第17期34卷 14135-14149页

作者： Bouaafia, Soulef Khemiri, Randa Messaoud, Seifeddine Ben Ahmed, Olfa Sayadi, Fatma Ezahra Univ Monastir Fac Sci Monastir Lab Elect & Microelect Monastir Tunisia Univ Gabes Higher Inst Comp Sci & Multimedia Gabes Gabes Tunisia Univ Poitiers CNRS XLIM Bat SP2MI11 Bd Marie & Pierre Curie F-86962 Chasseneuil France Univ Sousse Natl Engn Sch Sousse Lab Networked Objects Control & Commun Syst Sousse Tunisia

Multimedia IoT (M-IoT) is an emerging type of internet of things (IoT) relaying multimedia data (images, videos, audio and speech, etc.). The rapid growth of M-IoT devices enables the creation of a massive volume of multimedia data with different characteristics and requirements. With the development of artificial intelligence (AI), AI-based multimedia IoT systems have been recently designed and deployed for various video-based services for contemporary daily life, like video surveillance with high definition (HD) and ultra-high definition (UHD) and mobile multimedia streaming. These new services need higher video quality in order to meet the quality of experience (QoE) required by the users. Versatile video coding (VVC) is the new video coding standard that achieves significant coding efficiency over its predecessor high-efficiency video coding (HEVC). Moreover, VVC can achieve up to 30% BD rate savings compared to HEVC. Inspired by the rapid advancements in deep learning, we propose in this paper a wide-activated squeeze-and-excitation deep convolutional neural network (WSE-DCNN) technique-based video quality enhancement for VVC. Therefore, we replace the conventional in-loop filtering in VVC by the proposed WSE-DCNN model that eliminates the compression artifacts in order to improve visual quality and hence increase the end user QoE. The obtained results prove that the proposed in-loop filtering technique achieves similar to 2.85%, similar to 8.89%, and similar to 10.05% BD rate reduction for luma and both chroma components under random access configuration. Compared to the traditional CNN-based filtering approaches, the proposed WSE-DCNN-based in-loop filtering framework achieves efficient performance in terms of RD cost.

关键词： Video coding Artificial intelligence Multimedia IoT VVC

来源：评论

学校读者我要写书评

暂无评论

network Based control systems for Six Axis Robot System

Network Based Control Systems for Six Axis Robot System

引用

International conference on Computing Communication control and Automation (ICCUBEA)

作者： Ajit Nikam Sachin Argade Dipak Kole Prajwal Nimbokar Electrical Engineer JSPM Rajarshi Shahu College Of Engineering Pune India

ISBN: (数字)9798350391770

ISBN: (纸本)9798350391787

Principal network traffic in network-based control systems (NBCS) is driven by plant Sensor–controller–Actuator nodes operating in closed-loop. The performance provided by an NBCS's quality-of-control (QoC), and Every closed-loop operation is dependent on both the message scheduling method and the controller *** this paper, We discuss the problem of NBCS afterwards we describe the token ring scheduling algorithm solution ,sampling algorithm calculation and the simulation results.

关键词： Automation Scheduling algorithms Simulation Telecommunication traffic control systems Robot sensing systems Stability analysis Scheduling Delays

来源：评论

学校读者我要写书评

暂无评论

A Marine Benthic Detection Algoritm Based On Improved Lightweight network 34

A Marine Benthic Detection Algoritm Based On Improved Lightw...

引用

34th Chinese control and Decision conference (CCDC)

作者： Le, Bai Ying, Hu Kun, Chang Hai Dalian Maritime Univ Dalian Peoples R China

ISBN: (纸本)9781665478960

Recently, using underwater robots to capture marine organisms have become a development trend. However, the blurred underwater images and colour distortion caused by the complex and variable underwater environment have seriously affected the accuracy and speed of underwater target detection. A marine benthic detection algorithm based on a lightweight network model is proposed in this paper, which can detect the number and distribution of marine organisms and enable the underwater robot to obtain reliable data quickly. Firstly, UGAN is added as an image enhancement network in the front end of the detection network to improve the quality of underwater images. Then a Ghost-SKYOLOv5-based target detection model is proposed, introducing GhostNet, a lightweight network composed of Ghost modules, instead of the backbone feature extraction network, significantly reducing the number of parameters and computation of the network model. In addition, an improved SK convolution is introduced in the feature extraction structure instead of the traditional convolution to improve the detection accuracy. Furthermore, the Focal loss optimization loss function is introduced to solve the positive and negative sample imbalance problem and improve detection accuracy to ensure detection speed. Finally, the algorithms performance is tested, and the algorithm can obtain an average accuracy of 86.12%, which is 3.96% better than the YOLOv5 algorithm;the detection speed is 60.50% better than the UGAN -YOLOv5 network.

关键词： UGAN Lightweight YOLOv5 SKNet network Target detection

来源：评论

学校读者我要写书评

暂无评论

Open Set Domain Adaptation with Zero-shot Learning on Graph 23

Open Set Domain Adaptation with Zero-shot Learning on Graph

引用

4th International conference on Computing, networks and internet of Things, CNIOT 2023

作者： Zhang, Xinyue Yang, Xu Liu, Zhiyong School of Artificial Intelligence University of Chinese Academy of Sciences China and State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798400700705

Open set domain adaptation focuses on transferring the information from a richly labeled domain called source domain to a scarcely labeled domain called target domain, while classifying the unseen target samples as one unknown class in an unsupervised way. Compared with the close set domain adaptation, where the source domain and the target domain share the same class space, the classification of the unknown class makes it easy to adapt to the real environment. Particularly, after the recognition of the unknown samples, the model can either ask for manually labeling or further develop the classification ability of the unknown classes based on pre-stored knowledge. Inspired by this idea, we propose a model for open set domain adaptation with zero-shot learning on the unknown classes in this paper. We utilize adversarial learning to align the two domains while rejecting the unknown classes. Then the knowledge graph is introduced to generate the classifiers for the unknown classes with the employment of the graph convolution network (GCN). Thus the classification ability of the source domain is transferred to the target domain, and the model can distinguish the unknown classes in detail with prior knowledge. We evaluate our model on digits datasets and the result shows superior performance. © 2023 Owner/Author.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Novel Tuning Strategies to Enhance State Estimator performance and quality in the All India Power System network

Novel Tuning Strategies to Enhance State Estimator Performan...

引用

National Power systems conference (NPSC)

作者： Bhavneet Singh Neha Madhukar Rohit Shukla Pramod Singh B S Roy Grid Controller of India Limited New Delhi India

ISBN: (数字)9798331519568

ISBN: (纸本)9798331519575

The accuracy and reliability of state estimation are crucial for the effective operation and control of power systems, particularly in large-scale networks. Operators often face challenges such as measurement noise, data redundancy, and computational inefficiencies while striving for optimal solutions. This paper introduces novel tuning strategies to enhance state estimator performance and quality. The paper begins by underscoring the importance of state estimation in power systems. It then examines the integration of SCADA (Supervisory control and Data Acquisition) and EMS (Energy Management System) applications, highlighting their interlinking and significance in data collection and system monitoring. Key features of state estimator(SE) are detailed, including real-time sequencing, data filtration, handling various types of measurements, and consistency checks. A comprehensive discussion of the processes involved in achieving an optimal state estimator solution follows, covering SCADA data import, network topology processing, and observability analysis. The paper then delves into specific tuning strategies designed to improve state estimator performance. These strategies include network truncation, verification of network parameters, incorporation of pseudo measurements, correction of ICCP (Inter control Centre Communication Protocol) mismatches, and network topology corrections, etc. Finally, the paper evaluates the quality of the state estimator solution and the associated objective function values, demonstrating significant improvements through the proposed strategies. This study provides practical and innovative solutions to enhance state estimation in large and complex power networks, contributing to more reliable and efficient power system operations.

关键词： Sequential analysis Accuracy network topology SCADA systems Power system stability Real-time systems Stability analysis Power system reliability State estimation Tuning

来源：评论

学校读者我要写书评

暂无评论

Joint Caching and Computing Service Placement for Edge-Enabled IoT Based on Deep Reinforcement Learning

引用

IEEE internet OF THINGS JOURNAL 2022年第19期9卷 19501-19514页

作者： Chen, Yan Sun, Yanjing Yang, Bin Taleb, Tarik China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Jiangsu Peoples R China Chuzhou Univ Sch Comp & Informat Engn Chuzhou 239000 Anhui Peoples R China Univ Oulu Ctr Wireless Commun Oulu 90570 Finland Sejong Univ Dept Comp & Informat Secur Seoul 05006 South Korea

By placing edge service functions in proximity to IoT facilities, edge computing can satisfy various IoT applications' resource and latency requirements. Sensing-data-driven IoT applications are prevalent in IoT systems, and their task processing relies on sensing data from sensors. Therefore, to ensure the quality of Service (QoS) of such applications in an edge-enabled IoT system, dedicated caching functions (CFs) are required to cache necessary sensing data. This article considers an edge-enabled IoT system and investigates the joint caching and computing service placement (JCCSP) problem for sensing-data-driven IoT applications. Then, deep reinforcement learning (DRL) is exploited to address the problem since it can adapt to a heterogeneous system with limited prior knowledge. In the proposed DRL-based approaches, a policy network based on the encoder-decoder model is constructed to address the issue of varying sizes of JCCSP states and actions caused by different numbers of CFs related to applications. Then, an on-policy REINFORCE-based method is adopted to train the policy network. After that an off-policy training method based on the twin-delayed (TD) deep deterministic policy gradient (DDPG) is proposed to enhance the training efficiency and experience utilization. In the proposed DDPG-based method, a weight-averaged twin-Q-delayed (WATQD) algorithm is introduced to reduce the bias of Q-value estimation. Simulation results show that our proposed DRL-based JCCSP approaches can achieve converged performance that is significantly superior to benchmarks. Moreover, compared with the original TD method, the proposed WATQD method can significantly improve the training stability.

关键词： Deep reinforcement learning (DRL) edge computing IoT joint service placement sensing-data-driven applications

来源：评论

学校读者我要写书评

暂无评论

Toyota Financial Services Data Portal

Toyota Financial Services Data Portal

引用

IEEE International conference on Imaging systems and Techniques (IST) / IEEE International School on Imaging

作者： Chaudhary, Kundan D'Spain, Keenan Khanal, Sabina Nguyen, Khiem Pham, Loc Lall, Gaurav Trieu, Tai Kadiyala, Krishna Wei, Bingyang Texas Christian Univ Dept Comp Sci Ft Worth TX 76109 USA Toyota Financial Serv 6565 Headquarters Dr Plano TX 75024 USA

ISBN: (纸本)9781665481021

Toyota Financial Services (TFS), being part of a highly regulated industry needs to ensure that all risk management, governance process, and controls are in place to ensure compliance. This entails documenting all the business processes, definitions of their data elements, and connecting the defined data elements to the physical attributes in their various applications and databases. Furthermore, they need to document the lineage of the data to ensure that it is flowing correctly through their ecosystem. We, the members of the TFS Data Portal Project, built a portal where we can visualize data duly categorized that end users can use for visualization and solving their business problems. The portal would basically organize data by business areas such as Loan Origination, Insurance, Servicing, etc., and give the user ability to do a google like search for any data element which would bring up business definitions, physical attributes, data quality rules & profile and any related data associated with it.

关键词： Industries Data visualization Process control Insurance Software internet Portals

来源：评论

学校读者我要写书评

暂无评论

ATL: A Link Failure Recovery Method with Fast Recovery Speed, Low Interruption Rate, and Small TCAM Consumption in SDN 29

ATL: A Link Failure Recovery Method with Fast Recovery Speed...

引用

29th IEEE International conference on Parallel and Distributed systems, ICPADS 2023

作者： Zhang, Xinyu Chen, Jue Shanghai University of Engineering Science School of Electronic and Electric Engineering Shanghai China

ISBN: (纸本)9798350330717

Based on the architecture of the Software Defined network (SDN), we argue that SDN together with internet of Things (IoT) applications can enhance the control and management of IoT in terms of flexibility and intelligence. However, with the rapid development of SDN, link fault tolerance has become a crucial challenge in ensuring network reliability and stability. In this field, the current solutions mainly consist of proactive and reactive schemes, but there are still limitations and challenges. The proactive solutions often waste significant TCAM resources, while the reactive solutions face longer fault recovery time. In order to solve the shortcoming of both solutions, and to address the issues of traffic interruption caused by insufficient link bandwidth after link failures, this paper proposes a method called Adapt To Link (ATL) which combines the greedy algorithm with Pro-VLAN technology (a proactive method which calculates a backup path and assigns a VLAN ID for each link before link failures), aiming to achieve efficient fault-tolerant recovery for link failures in the SDN data plane. In this algorithm, we utilize the Pro-VLAN method and pre-compute multiple backup paths for each link before a failure occurs. When a link failure occurs, we can swiftly switch the affected traffic to the backup paths automatically without the controller, ensuring continuous flow of network traffic. Additionally, we introduce a greedy algorithm to satisfy the requirement of elephant flows, thereby improving network resource utilization and performance. By combining these techniques and methods, our algorithm exhibits the characteristics of low interruption rate, minimal resource consumption, and high efficiency. The experimental results demonstrate that under high load conditions, the ATL scheme reduces the interruption rate by 72.4% compared to the proactive approach and by 54.9% compared to the reactive approach, respectively. The number of additional flow rules in ATL is only

关键词： Fault Tolerance Heuristic Algorithm Proactive Approach Reactive Approach Software Defined network

来源：评论

学校读者我要写书评

暂无评论

Joint User Cooperation and Scheduling for Federated Learning in CFmMIMO networks 2

Joint User Cooperation and Scheduling for Federated Learning...

引用

2nd International conference on Smart Technologies and systems for Next Generation Computing, ICSTSN 2023

作者： Bao, Han Gao, Bo Xiong, Ke Fan, Pingyi Beijing Jiaotong University School of Computer and Information Technology Beijing China Beijing Jiaotong University Engineering Research Center of Network Management Technology for High Speed Railway Ministry of Education School of Computer and Information Technology Beijing China Tsinghua University Department of Electronic Engineering Beijing China

ISBN: (纸本)9798350348002

This paper proposes a joint user cooperation and scheduling (JUCS) method to minimize the maximum transmission time among users in the synchronous federated learning (FL) architecture, since the user with the worst quality link limits the training performance of FL. To this end, an optimization problem is formulated to find the optimal user cooperation pairing and the power control coefficients. Meanwhile, as the links among users operate on the same frequency bands, the interface between them is taken into account in this paper. As the problem is non-convex, we decouple it into two sub-problems. For the first sub-problem, we propose a fair scheduling (FS)-based algorithm to schedule the helping users to pair with the ones who are required to be assisted. For the second sub-problem, an algorithm based on deterministic policy gradient (DDPG) is proposed to find the optimized power control coefficients. Experiments show that the proposed JUCS method shortens about 34.48% transmission time of the worst user in FL compared to the traditional one without JUCS. © 2023 IEEE.

关键词： Scheduling algorithms

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：