检索结果-内蒙古大学图书馆

Prioritized recovery Strategy For robust UAV Swarm Communication via Graph reinforcement Learning

IEEE Internet of Things Journal 2025年

作者： Peng, Yabin Wu, Jiangxing duan, Tong Liu, Yuchen Zhang, Zhen Zhang, Jinfeng Southeast University School of Cyber Science and Engineering Nanjing211189 China Purple Mountain Laboratories Nanjing211111 China National Digital Switching System Engineering and Technological R and D Center Zhengzhou450002 China PLA Information Engineering University Zhengzhou450002 China

Network failures, whether due to random disruptions or malicious attacks, pose significant challenges for unmanned aerial vehicle (UAV) swarm networks. One critical concern is determining which failed UAVs to recover or replace under limited resource conditions to enhance the robustness of their communication networks. Current research primarily considers static structural characteristics of the network and struggles to uncover deep features that influence network robustness, and the efficiency cannot meet the real-time needs in UAV swarm scenarios. To address these issues, we introduce a Prioritized recovery strategy for failed nodes based on Graph reinforcement Learning (PrGrL). This approach integrates a random SAmpling neighbor method with a multi-head attention mechanism to create a novel Graph Convolutional Kernel (SAGCK). This kernel is designed to extract global structural information and relative positional information of nodes within the graph. Additionally, we develop a deep Policy Network (dPN) that explores the intricate relationships between graph-level and node embedding features, enabling the assessment of nodes’ impact on overall robustness. PrGrL’s network parameters are automatically updated and optimized using scalable deep reinforcement learning. Importantly, PrGrL prioritizes the recovery of boundary nodes within connected components to enhance network robustness further. Our experiments, conducted on both simulated and real-world networks, demonstrate that PrGrL outperforms existing methods of robustness enhancement across various recovery ratios, attack strategies, and network sizes while delivering superior real-time performance. © 2014 IEEE.

关键词： deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Measuring^(222)rn in aquatic environment via Pulsed Ionization Chamber radon detector

引用

Acta Oceanologica Sinica 2023年第8期42卷 185-189,I0001-I0006页

作者： Lijun Song Wen Liu Shibin Zhao Chunqian Li Jinjia Guo Natasha dimova Bochao Xu Frontiers Science Center for Deep Ocean Multispheres and Earth System/Key Laboratory of Marine Chemistry Theory and Technology of Ministry of Education Ocean University of ChinaQingdao 266100China Laboratory for Marine Ecology and Environmental Science Qingdao National Laboratory for Marine Science and TechnologyQingdao 266071China College of Chemistry and Chemical Engineering Ocean University of ChinaQingdao 266100China College of Information Science and Engineering Ocean University of ChinaQingdao 266100China R&D Center for Marine Instruments and Apparatuses Qingdao Marine Science and Technology CenterQingdao 266200China Department of Geological Sciences College of Arts and SciencesUniversity of AlabamaTuscaloosa 35487USA

radon(rn)is a naturally occurring radioactive inert gas in nature,and^(222)rn has been routinely used as a powerful tracer in various aquatic environmental research on timescales of hours to days,such as submarine groundwater *** we developed a new approach to measure^(222)rn in discrete water samples with a wide range of^(222)rn concentrations using a Pulsed Ionization Chamber(PIC)radon *** sensitivity of the new PIC system is evaluated at 6.06 counts per minute for 1 Bq/L when a 500 mL water sample volume is used.A robust logarithmic correlation between sample volumes,ranging from 250 mL to 5000 mL,and system sensitivity obtained in this study strongly suggests that this approach is suitable for measuring radon concentration levels in various natural *** to the currently available methods for measuring radon in grab samples,the PIC system is cheaper,easier to operate and does not require extra accessories(e.g.,drying tubes etc.)to maintain stable measurements throughout the counting procedure.

关键词： ^(222)rn radon measurement Pulsed Ionization Chamber radon detector radon in discrete water samples submarine groundwater discharge

来源：评论

学校读者我要写书评

暂无评论

CLMSI: A Novel Image-Text Named Entity recognition Method Based on Contrast Learning and Multimodal Semantic Interaction

CLMSI: A Novel Image-Text Named Entity Recognition Method Ba...

引用

International Conference on Behavior, Economic and Social Computing (BESC)

作者： Jiangtao Ma Wenduo Jin Yonggang Chen Fan Zhang Shenyi Qian Yaqiong Qiao College of Computer and Information Engineering Tianjin Normal University Tianjin China School of Computer Science and Technology Zhengzhou University of Light Industry Zhengzhou China The State Information Center China National Digital Switching System Engineering and Technology R&D Center Zhengzhou China College of Cyber Science Nankai University Tianjin China

ISBN: (数字)9798331531904

ISBN: (纸本)9798331531911

Most existing multimodal named entity recognition (MNEr) methods cannot align image and text well, and fail to effectively fuse image-text semantic information, leading to suboptimal MNEr accuracy. To this end, this paper proposes a novel named entity recognition model based on Contrastive Learning and Multimodal Semantic Interaction (named CLMSI). Specifically, to narrow the semantic gap between image-text modalities, making semantically similar image-text representations closer and pushing dissimilar ones further apart, we propose a contrastive learning-based cross-modal alignment method. Moreover, to integrate multimodal information effectively and filter out the noise introduced by image features as thoroughly as possible, we propose to incorporate image descriptions as additional features to enrich the multimodal representation and to reduce the semantic bias of the image information. Extensive experiments conducted on two MNEr benchmark datasets, Twitter-2015 and Twitter-2017, demonstrate the superiority of the proposed method. Further ablation studies and case analyses also affirm the efficacy of CLMSI.

关键词： Visualization Social computing Accuracy Social networking (online) Computational modeling Semantics Noise Named entity recognition Feature extraction data mining

来源：评论

学校读者我要写书评

暂无评论

6G Polymorphic Smart Network Architecture and Key Technologies

6G Polymorphic Smart Network Architecture and Key Technologi...

引用

Frontiers technology of Information and Computer (ICFTIC), IEEE International Conference on

作者： Xingxing Liao Wei You Jingwen Lv Min Wang Ying Zhao Gang He Purple Mountain Laboratories Nanjing China National Digital Switching Engineering & Technological R&D Center Zhengzhou China Southeast University Nanjing China

In response to the problems of high architecture complexity, only support the IP, difficult against unknown threats, deficient intelligent in 5G network, a new polymorphic smart network architecture is proposed, including network system architecture and network deployment architecture. New network functions, such as polymorphic routing and addressing, endogenous security, and endogenous intelligent, are designed into the architecture. the polymorphic smart network selects corresponding network models for each terminal. SdN plans a network path for the network model that is associated with security and AI services. Finally, this article provides a simple validation of key technologies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

5G-PPdE: A Novel Adaptive Scaling Framework for Enhancing the resilience of the 5G Cloud Core Network

5G-PPDE: A Novel Adaptive Scaling Framework for Enhancing th...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Xinyu Huang Xingxing Liao Jie Yang Wei You Wenhao Wu Shiru Min Xinsheng Ji School of Cyber Science and Engineering Southeast University Nanjing China Purple Mountain Laboratories Nanjing China National Digital Switching Engineering & Technological R&D Center Zhengzhou China Information Engineering University Zhengzhou China

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

As containerization technology progresses, the network functions within the 5G core are abstracted into Virtual Network Functions (VNFs), operating within a cloud-based ecosystem. To bolster network resilience, autoscaling strategies dynamically allocate resources in response to workloads, ensuring the Quality of Service (QoS) is maintained. However, the inherent openness of 5G networks exposes them to signaling storms and unexpected disturbances, leading to substantial workload fluctuations and bursts. Current reactive autoscaling strategies are slow to respond to these challenges, falling short of user expectations for low-latency, high-quality internet services. To address this challenge, we propose a novel auto-scaling framework specifically designed for the 5G cloud core network system, dubbed 5G-PPdE. Our framework harnesses the Crossformer model for accurate workload forecasting and employs a Multi-Layer Perceptron (MLP) classification model to offer four distinct scaling strategies. The scaling-down decision algorithm implements a Gradual decrease Strategy (GdS) for resource management, while the burst scaling strategy adapts to sudden workload changes by referencing the maximum service quantities observed during historical window periods. We have constructed a validation system leveraging the open-source Free5GC and Free5GMANO, using the wrk tool to simulate burst traffic scenarios. Prometheus is utilized for real-time data collection, thereby validating the efficacy of our proposed framework. The findings demonstrate that our method effectively mitigates the impact of burst traffic, outperforming current solutions.

关键词： Cloud computing Adaptation models Adaptive systems 5G mobile communication Quality of service Predictive models Security resource management Forecasting resilience

来源：评论

学校读者我要写书评

暂无评论

A Security Survey of NFV: From Causes to Practices

A Security Survey of NFV: From Causes to Practices

引用

Consumer Electronics and Computer engineering (ICCECE), 2021 IEEE International Conference on

作者： Gang He Xingxing Liao Caixia Liu School of Cyber Science and Engineering Southeast University Nanjing China Purple Mountain Laboratories Nanjing China R&D Center National Digital Switching System Engineering &Technological Zhengzhou China Academy of Military Sciences Institute of System Engineering Beijing China

Network Function Virtualization (NFV) is proposed as new technology to address massive proprietary devices, high operation costs, poor flexibility and other problems in current traditional network. By separating network functions and proprietary devices, NFV can significantly reduce operation costs and enable flexible configuration of services, etc. Now NFV is widely used in various fields. However, due to virtualization and softwareization and other technical characteristics, NFV faces more serious security threats compared to traditional networks. This paper focuses on analyzing the NFV security threats under the new technology and summarizes them according to the causes of security threats. Subsequently, based on the results of the analysis, we propose the corresponding safety practice solutions. Finally, we prospect the research directions for improving NFV security.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unified Accelerator for Attention and Convolution in Inference Based on FPGA

Unified Accelerator for Attention and Convolution in Inferen...

引用

IEEE International Symposium on Circuits and systems (ISCAS)

作者： Tianyang Li Fan Zhang Xitian Fan Jianliang Shen Wei Guo Wei Cao Information Engineering University Zhengzhou China National Digital Switching System Engineering and Technological R&D Center Zhengzhou China Shanghai HONGZHEN Information Science & Technology Corporation Shanghai China Institute for Big Data Fudan University Shanghai China

Many models combining Transformers with convolutional neural networks (CNNs) for computer vision tasks have achieved state-of-the-art results. However, due to the different computation patterns between attention and convolution, using a dedicated Transformer or CNN accelerator will inevitably reduce the computing efficiency of the other. To overcome this problem, we propose a unified architecture for attention and convolution on FPGA. We reduce runtime overhead by offloading part of self-attention computations offline before inference. Furthermore, we present a unified mapping method according to the computing characteristics of attention-based and convolution-based models. This accelerator implements multi-head attention in Transformer, independent resNet-50 and hybrid blocks of attention and con-volution in BoTNet-50 at 200MHz on Xilinx Virtex Ultrascale+ XCVU37P. Experimental results show that the solution is nearly 3.62 times more energy-efficient than the NVIdIA V100 GPU, and the computational efficiency is 11.86% and 28.29% higher than the state-of-the-art Transformer and resNet-50 accelerators, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Named Entity recognition Incorporating Chinese Segmentation Information

Named Entity Recognition Incorporating Chinese Segmentation ...

引用

Advanced Computing and Endogenous Security, International Conference on

作者： Shiyuan Yu Shuming Guo ruiyang Huang Jianpeng Zhang Ke Su Nan Hu School of Cyberspace Securitym Zhengzhou University Zhengzhou China National Digital Switching System Engineering and Technological R&D Center Zhengzhou China

ISBN: (纸本)9781665424509

Word-level information is crucial for Chinese named entity recognition. Presently, most works have achieved better performance by extracting word-level information into character-level representations through existing lexicons, but the maintenance of lexical lists is a major challenge. In this paper, we present the NIMSI model, proposing the incorporation of multiple segmentation information to enhance recognition, using a trilogy to align character-level attention with word-level attention to construct features of segmented information in Chinese text. Also, we use a simple but effective method to directly incorporate multi-segmentation information into character-level representations. Finally, as the experiments on the three benchmark datasets show, our model effectively incorporates segmentation information and alleviates the segmentation errors.

关键词： Text recognition Benchmark testing Maintenance engineering Feature extraction Character recognition Security data mining

来源：评论

学校读者我要写书评

暂无评论

deepWeave: Accelerating job completion time with deep reinforcement learning-based coflow scheduling 29

DeepWeave: Accelerating job completion time with deep reinfo...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Sun, Penghao Guo, Zehua Wang, Junchao Li, Junfei Lan, Julong Hu, Yuxiang National Digital Switching System Engineering and Technological R&D Center Beijing Institute of Technology China

ISBN: (纸本)9780999241165

To improve the processing efficiency of jobs in distributed computing, the concept of coflow is proposed. A coflow is a collection of flows that are semantically correlated in a multi-stage computation task. A job consists of multiple coflows and can be usually formulated as a directed-Acyclic Graph (dAG). A proper scheduling of coflows can significantly reduce the completion time of jobs in distributed computing. However, this scheduling problem is proved to be NP-hard. different from existing schemes that use hand-crafted heuristic algorithms to solve this problem, in this paper, we propose a deep reinforcement Learning (drL) framework named deepWeave to generate coflow scheduling policies. To improve the inter-coflow scheduling ability in the job dAG, deepWeave employs a Graph Neural Network (GNN) to process the dAG information. deepWeave learns from the history workload trace to train the neural networks of the drL agent and encodes the scheduling policy in the neural networks, which make coflow scheduling decisions without expert knowledge or a pre-assumed model. The proposed scheme is evaluated with a simulator using real-life traces. Simulation results show that deepWeave completes jobs at least 1.7× faster than the state-of-the-art solutions. © 2020 Inst. Sci. inf., Univ. defence in Belgrade. All rights reserved.

关键词： reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

design and implementation of a novel enterprise network defense system by maneuvering multi-dimensional network properties

引用

Frontiers of Information technology & Electronic engineering 2019年第2期20卷 238-252页

作者： Yang CHEN Hong-chao HU Guo-zhen CHENG National Digital Switching System Engineering & Technological R&D Center

Although the perimeter security model works well enough when all internal hosts are credible, it is becoming increasingly difficult to enforce as companies adopt mobile and cloud technologies, i.e., the rise of bring your own device(BYOd). It is observed that advanced targeted cyber-attacks usually follow a cyber kill chain;for instance, advanced targeted attacks often rely on network scanning techniques to gather information about potential targets. In response to this attack method, we propose a novel approach, i.e., an "isolating and dynamic"cyber defense, which cuts these potential chains to reduce the cumulative availability of the gathered ***, we build a zero-trust network environment through network isolation, and then multiple network properties are maneuvered so that the host characteristics and locations needed to identify vulnerabilities cannot be ***, we propose a software-defined proactive cyber defense solution(SPd) for enterprise networks and design a general framework to strategically maneuver the IP address, network port, domain name, and path, while limiting the performance impact on the benign network user. Third, we implement our SPd proof-of-concept system over a software-defined network controller(Opendaylight). Finally, we build an experimental platform to verify the system's ability to prevent scanning, eavesdropping, and denial-of-service attacks. The results suggest that our system can significantly reduce the availability of network reconnaissance scan information, block network eavesdropping, and sharply increase the cost of cyber-attacks.

关键词： Intranet defense Software-defined network Multi-dimensional maneuvering

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：