检索结果-内蒙古大学图书馆

ArguteDUB: Deep Learning Based Distributed Uplink Beamforming in 6G-Based IoV

IEEE TRANSACTIONS ON MOBILE COMPUTING 2024年第4期23卷 2551-2565页

作者： Yi, Xingrui Li, Jianqiang Liu, Yutong Kong, Linghe Shao, Ying Chen, Guihai Liu, Xue Mumtaz, Shahid Rodrigues, Joel J. P. C. Shanghai Jiao Tong Univ Dept Comp Sci & Engn Shanghai 200240 Peoples R China Beihang Univ Beijing 100191 Peoples R China Shanghai Acad Spaceflight Technol Shanghai 200243 Peoples R China Shanghai Tech Inst Elect & Informat Shanghai 201411 Peoples R China McGill Univ Sch Comp Sci Montreal PQ H3A 2A7 Canada Silesian Tech Univ Dept Appl Informat PL-44100 Gliwice Poland Nottingham Trent Univ Engn Dept Nottingham NG1 4FQ England China Univ Petr East China Coll Comp Sci & Technol Qingdao 266555 Peoples R China Inst Telecomunicacoes P-6201001 Covilha Portugal

In the last decade, MIMO spatial multiplexing and distributed beamforming play a significant role in improving data throughput through cooperative transmission. It has been widely used in wireless communication, especially in 6G. However, the distributed uplink beamforming is still an open problem in highly dynamic environments. However, the proposed 6G technology represents the further integration of deep learning and wireless communication. In this article, we propose Argute Distributed Uplink Beamforming (ArguteDUB), which uses a feedback algorithm with an offline-trained deep learning model to implement highly dynamic distributed uplink beamforming for the Internet of Vehicles (IoV) in 6G. Specifically, each vehicle enables the base station (BS)/access point (AP) to separate different channel state information (CSI) by inserting orthogonal sequences into the sending data. The BS adopts deep learning to filter the noise and predict the beamforming weight to achieve phase synchronization. Unlike traditional distributed uplink beamforming, ArguteDUB can be adapted to the highly dynamic time-varying channels. The simple network structure ensures the fast response of ArguteDUB. In addition, we make ArguteDUB Orthogonal Frequency Division Multiplexing (OFDM) compatible so that it can be easily deployed in 6G networks. Our evaluation shows that ArguteDUB has an signal-to-noise ratio (SNR) gain of about 5 dB to 5.3 dB over the single vehicle transmission mode.

关键词： 6G deep learning distributed uplink beamforming highly dynamic internet of vehicles

来源：评论

学校读者我要写书评

暂无评论

Harmfulness metrics in digital twins of social network rumors detection in cloud computing environment

引用

JOURNAL OF CLOUD COMPUTING-ADVANCES SYSTEMS AND APPLICATIONS 2024年第1期13卷 1-14页

作者： Li, Hao Yang, Wu Wang, Wei Wang, Huanran Harbin Engn Univ Coll Comp Sci & Technol Harbin 150001 Heilongjiang Peoples R China

Social network rumor harm metric is a task to score the harm caused by a rumor by analyzing the spreading range of the rumor, the users affected, the repercussions caused, etc., and then the harm caused by the rumor. Rumor hazard metric models can help rumor detection digital twins to understand and analyze user behaviors and assist social network network managers to make more informed decisions. However, there is a lack of models that can quantify the harm of rumors and automated harm metric models in rumor detection digital twins. To address this issue, this paper proposes an innovative social network rumor harm metric based on rumor propagation knowledge and a large language model (LLM), RSK-T5. The method first completes the joint task of rumor comment stance detection and sentiment analysis to capture critical features of rumor propagation. Then, this knowledge is used in the pre-training process of LLM to improve the model's understanding of rumor propagation patterns. Finally, the fine-tuning phase focuses on the hazard metrics task to improve the generalization energy. We compare with some existing variants of rumor detection methods, and experimental results demonstrate that RSK-T5 achieves the lowest MSE scores on three well-known rumor detection datasets. The ablative learning work demonstrates the effectiveness of RSK-T5's knowledge of two rumor spreads.

关键词： Rumor hazard metric Digital twins Large language model Rumor propagation Rumor stance detection Rumor sentiment analysis Social network

来源：评论

学校读者我要写书评

暂无评论

UAV-Assisted Wireless Cooperative Communication and Coded Caching: A Multiagent Two-Timescale DRL Approach

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2024年第5期23卷 4389-4404页

作者： Tian, Bingxin Wang, Li Xu, Lianming Pan, Wen Wu, Huaqing Li, Liang Han, Zhu Beijing Univ Posts & Telecommun Sch Elect Engn Beijing 100876 Peoples R China Beijing Univ Posts & Telecommun Sch Comp Sci Natl Pilot Software Engn Sch Beijing 100876 Peoples R China Minist Educ Key Lab Universal Wireless Commun Beijing 100876 Peoples R China Minist Emergency Management Key Lab Applicat Innovat Emergency Command Commun Beijing 100876 Peoples R China Beijing Xiaomi Mobile Software Co Ltd Beijing 100085 Peoples R China Univ Calgary Dept Elect & Software Engn Calgary T2N 1N4 AB Canada Univ Houston Dept Elect & Comp Engn Houston TX 77004 USA Kyung Hee Univ Dept Comp Sci & Engn Seoul 446701 South Korea

In emergency scenarios, strong mobility and serious interference cause unstable transmission of on-site information such as close-up photos and high resolution videos, which requires a robust temporary communication network. In this paper, we focus on a UAV-assisted wireless cooperative communication and coded caching network, where emergency command vehicles and a UAV serve as content providers (CPs) to cache and transmit coded fragments or complete files for rescuers regarded as content requesters (CRs). The delivery success probability and content hit ratio are theoretically derived by incorporating the physical connectivity and social relationship between CPs and CRs. Aiming at maximizing the overall content hit ratio, we propose a multiagent two-timescale deep reinforcement learning (MA2T-DRL) algorithm to jointly optimize the transmission power and caching strategies for CPs. Specifically, we develop a two tier deep-Q networks (DQNs) framework integrating a slow-timescale DQN (ST-DQN) and a fast-timescale DQN (FT-DQN) for caching decision-making and power decision-making respectively, and then the QMIX framework is leveraged to aggregate all the outputs from local ST-DQNs. Considering the cooperative characteristics of coded caching, we further propose a novel clustering method for CPs such that CPs in the same cluster have the same willingness to serve CRs, and each cluster is regarded as the agent for training which further reduces the aggregation scale of the mixing network. Simulation results show that the proposed MA2T-DRL algorithm is efficient in model training, and presents the advantages in performance and complexity compared with the single-agent centralized training and the multiagent independent distributed training.

关键词： Wireless coded caching resource allocation deep reinforcement learning social relationship

来源：评论

学校读者我要写书评

暂无评论

CCA security for contracting (quasi-)Feistel constructions with tight round complexity

引用

DESIGNS CODES AND CRYPTOGRAPHY 2024年第8期92卷 2103-2129页

作者： Guo, Chun Song, Ling Shandong Univ Sch Cyber Sci & Technol Qingdao 266237 Shandong Peoples R China Shandong Univ Key Lab Cryptol Technol & Informat Secur Minist Educ Qingdao 266237 Shandong Peoples R China Shandong Res Inst Ind Technol Jinan 250102 Shandong Peoples R China Jinan Univ Guangzhou Peoples R China

Feistel constructions using contracting round functions were introduced in 1990s and generalized by Yun et al. (Des Codes Cryptogr 58(1):45-72, 2011) to a quasigroup-based definition. To our knowledge, the minimal number of rounds sufficient for CCA security remains elusive. We bridge this gap: for the general quasigroup-based contracting Feistel construction using round functions Fi:Xb-1 -> X\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$F_i: \mathcal {X}<^>{b-1} \rightarrow \mathcal {X}$$\end{document}, b >= 3\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$b \ge 3$$\end{document}, we prove CCA security at b+1\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$b+1$$\end{document} rounds. This matches the attacked rounds of Patarin et al. (in: Lai, Chen (ed) ASIACRYPT, Springer, Heidelberg, 2006). Interestingly, this means 4 rounds are already sufficient for CCA security of the case b=3\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$b=3$$\end{document}, which is the same as the balanced Feistel.

关键词： Feistel construction Contracting function Provable security Tightness

来源：评论

学校读者我要写书评

暂无评论

Influence of Initial Cloud Droplet Number Concentration on Warm-Sector Rainstorm in the Sichuan Basin

引用

PURE AND APPLIED GEOPHYSICS 2024年第12期181卷 3681-3701页

作者： Zhang, Peiwen Zhao, Pengguo Heng, Zhiwei Zheng, Qing Feng, Yong Jiang, Xingwen China Meteorol Adm Inst Tibetan Plateau Meteorol Heavy Rain & Drought Flood Disaster Plateau & Basi Chengdu 610072 Peoples R China Chengdu Univ Informat Technol Coll Atmospher Sci Plateau Atmosphere & Environm Key Lab Sichuan Prov Chengdu Plain Urban Meteorol & Environm Observat & Chengdu 610225 Peoples R China

Warm-sector rainstorms (WSR) are among the main weather events that cause significant casualties in the Sichuan Basin (SCB). These events are challenging to predict accurately using numerical models, partly due to the locally high air pollution that complicates WSR microphysical and precipitation processes. Aerosols affect the initial cloud droplet number concentration (CDNC) directly, and the CDNC is a key parameter in microphysical schemes that directly influences precipitation prediction. However, how and to what extent the CDNC affects WSR predictions in the SCB remains unclear. In this study, sensitivity experiments were conducted using a cloud-resolving model to investigate how the CDNC affects WSRs in the SCB. The study showed that when the CDNC is high, warm rainfall is reduced, while the cold rainfall is increased, which changes with convection development. First, a higher initial CDNC inhibits warm rainfall during the initial stage of convection. Second, during convection development, a higher initial CDNC accelerates graupel growth and its transformation into rainwater. The cold rainfall process plays a dominant role in this process, leading to an increase in rainfall intensity. Finally, during the convection mature stage, the promoting effect of the CDNC on the cold rainfall process weakens, leading to a decreased rainfall intensity in the higher initial CDNC. In the "initial-development-mature" stage, a higher initial CDNC distinctly affects the precipitation intensity in the form of "suppression-promotion-suppression." The findings of this study contribute to the ability to anticipate the development of WSRs based on pollution conditions in the SCB.

关键词： Cloud droplet number concentration microphysical processes warm-sector rainstorm Sichuan Basin

来源：评论

学校读者我要写书评

暂无评论

Edge Data Caching With Consumer-Centric Service Prediction in Resilient Industry 5.0

引用

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 2024年第1期70卷 1482-1492页

作者： Liu, Guoqiang Bao, Guanming Bilal, Muhammad Jones, Angel Jing, Zhipeng Xu, Xiaolong Nanjing Univ Informat Sci & Technol Sch Software Nanjing 210044 Peoples R China Nanjing Univ Informat Sci & Technol Sch Comp Sci Nanjing 210044 Peoples R China Univ Lancaster Sch Comp & Commun Lancaster LA1 4WA England Univ Virginia Sch Continuing & Profess Studies Charlottesville VA 22904 USA Nanjing Univ Informat Sci & Technol Reading Acad Nanjing 210044 Peoples R China

Industry 5.0, emerging as a promising industry paradigm, unleashes the potential of improving consumer experience by delivering consumer-centric services, facilitating substantial growth in consumer electronics. To improve the resilience of industry 5.0, edge data caching enables sustainable and low-latency service provision by caching data at edge servers (ESs) closer to production. However, the limited caching capacity of ESs presents a formidable challenge to efficient edge data caching. Moreover, the dynamic of consumer-centric service requests further complicates the effective implementation of caching strategies. In response to the above challenges, we propose an edge data caching scheme, named SPM-ECDP, with consumer-centric service prediction for Industry 5.0. Initially, a time-series prediction model is employed to forecast the service demands. To ensure the confidentiality of data, federated learning is introduced in the model training phase. Subsequently, reinforcement learning is adopted to enable ESs to make intelligent decisions on edge data caching, consequently enhancing caching efficiency. Through comprehensive simulation experiments, the effectiveness and superiority of the proposed scheme in increasing caching hit ratio and reducing data delivery delays are demonstrated. The experimental results demonstrate that the proposed SPM-ECDP method has enhanced the hit ratio by 7.05% - 48.5% when compared to the baseline method.

关键词： Industries Training Production facilities Federated learning Data privacy Data models Servers Consumer-centric industry 50 edge caching edge computing privacy preservation reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Subsystem Measurement-Based Condition Assessment for Power Transformers via Joint Inference of Data and Knowledge

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1-12页

作者： Tian, Jiapeng Song, Hui Sheng, Gehao Jiang, Xiuchen Shanghai Jiao Tong Univ Dept Elect Engn Shanghai 200240 Peoples R China

Based on various measurements, the condition assessment of power transformers ensures transformer reliability for achieving a stable power supply and improves economic benefits. However, the existing methods suffer from artificially summarized rules, heavy data dependence, incomprehensive measurement analysis, superficial information fusion, or unexplainable assessment results. Therefore, an interpretable joint inference method based on subsystem measurements is proposed to automatically extract the knowledge and data features, enabling profound information fusion and reducing the impact of poor-quality data. First, the sparse autoencoders (SAEs) and graph convolutional networks (GCNs) extract features from the subsystem condition data and the archive knowledge graph (KG) representing the maintenance histories, respectively. Next, the method assigns weights to the features according to the mask vectors. Then, a Bayesian neural network (BNN) analyzes uncertainties to recognize the condition grade, and the health index (HI) is calculated through fitting distributions and Monte Carlo sampling. Finally, a local interpretable model is designed to interpret the decisions made by the proposed method. Verified by experiments, the proposed method achieves an F-measure of 97.28% on grade recognition, which is 20.94% higher than contrast models. Moreover, the method is also proven to outperform the other models in dealing with disturbed and incomplete data.

关键词： Condition assessment health index (HI) joint inference knowledge graph (KG) measurement analysis power transformer

来源：评论

学校读者我要写书评

暂无评论

Applying a Nanoantenna Array on Metal To Improve the Efficiency of Phosphorescent OLEDs at High Luminance

引用

ACS APPLIED MATERIALS & INTERFACES 2025年第14期17卷 21544-21551页

作者： An, Di Huang, Wenzhe Kang, Jiachen Xia, Zixiang Zhao, Yu Kong, Peng He, Gufeng Shanghai Jiao Tong Univ Dept Elect Engn Shanghai 200240 Peoples R China

Phosphorescent organic light-emitting diodes (OLEDs) are suitable for display and lighting applications due to their superior luminance and efficiency. However, the strong efficiency roll-off severely hinders their potential applications in transparent displays, virtual reality, and other high-luminance-demanding fields, which is mainly attributed to severe triplet-triplet annihilation (TTA) and triplet-polaron quenching (TPQ). In this study, by employing a thin Ag anode close to the phosphorescent emitter, a Purcell factor over 5 has been achieved, nearly triple that of a conventional indium tin oxide (ITO)-based device. This enhancement significantly accelerates the exciton decay rate and reduces exciton concentration, thereby considerably lowering the incidence of TTA and TPQ. Meanwhile, such devices are capable of nearly eliminating waveguide modes, with over 77% of the energy being coupled into a surface plasmon polariton (SPP). A nanoantenna array on metal (NAoM), situated on the exterior surface of the thin Ag anode, efficiently extracts the SPP when the plasmonic antenna modes resonate with the gap modes within the NAoM. This configuration yields an efficiency enhancement of 100% at 40,000 cd/m2 compared to conventional phosphorescent devices with similar structures, providing a promising avenue for high-luminance phosphorescent OLED.

关键词： phosphorescent OLEDs high luminance surfaceplasmon polariton waveguide modes nanoantenna high efficiency

来源：评论

学校读者我要写书评

暂无评论

Effects of halogen elements on a humidity sensor based on a thin film bulk acoustic wave resonator incorporated with Cs3Bi2X9 (X = Cl,Br, I) perovskites

引用

JOURNAL OF MATERIALS CHEMISTRY C 2024年第6期12卷 1988-1995页

作者： Zhao, Lishuai Ouyang, Peidong Yi, Xinyan Li, Guoqiang South China Univ Technol State Key Lab Luminescent Mat & Devices Guangzhou 510641 Peoples R China Guangzhou Aifo Commun Technol Co Ltd Guangzhou 510700 Peoples R China

All-inorganic perovskites have attracted extensive attention due to their exceptional performance in the realm of optoelectronics. However, there are few reports on the applications of all-inorganic perovskites in humidity detection. This study highlights the applications of thin film bulk acoustic wave resonators (FBARs) integrated with Cs3Bi2X9 (X = Cl, Br, and I) perovskites in humidity sensing. Through comprehensive exploration of the effects of halogen elements, it was found that Cs3Bi2Br9 integrated with FBARs displayed the smallest hysteresis of 6%, a response/recovery time of 130/143 s, reversible repeatability and the highest response of 253 kHz at 85% RH, which was about two times and four times as large as those of the Cs3Bi2X9 and Cs3Bi2I9 perovskites integrated with FBARs. These results have demonstrated the feasibility of the FBAR incorporated with perovskites as a promising platform for humidity sensing.

关键词： Perovskite

来源：评论

学校读者我要写书评

暂无评论

Dynamic System Modeling Using a Multisource Transfer Learning-Based Modular Neural Network for Industrial Application

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2024年第5期20卷 7173-7182页

作者： Duan, Haoshan Meng, Xi Tang, Jian Qiao, Junfei Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China Beijing Lab Smart Environm Protect Beijing 100124 Peoples R China Minist Educ Engn Res Ctr Intelligence Percept & Autonomous Con Beijing 100124 Peoples R China

Establishing an accurate model of dynamic systems poses a challenge for complex industrial processes. Due to the ability to handle complex tasks, modular neural networks (MNN) have been widely applied to industrial process modeling. However, the phenomenon of domain drift caused by operating conditions may lead to a cold start of the model, which affects the performance of MNN. For this reason, a multisource transfer learning-based MNN (MSTL-MNN) is proposed in this study. First, the knowledge-driven transfer learning process is performed with domain similarity evaluation, knowledge extraction, and fusion, aiming to form an initial subnetwork in the target domain. Then, the positive transfer process of effective knowledge can avoid the cold start problem of MNN. Second, during the data-driven fine-tuning process, a regularized self-organizing long short-term memory algorithm is designed to fine-tune the structure and parameters of the initial subnetwork, which can improve the prediction performance of MNN. Meanwhile, relevant theoretical analysis is given to ensure the feasibility of MSTL-MNN. Finally, the effectiveness of the proposed method is confirmed by two benchmark simulations and a real industrial dataset of a municipal solid waste incineration process. Experimental results demonstrate the merits of MSTL-MNN for industrial applications.

关键词： Multi-layer neural network Task analysis Neurons Dynamical systems Computational modeling Prediction algorithms Mathematical models Dynamic system long short-term memory (LSTM) modular neural network (MNN) multisource transfer learning

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：