检索结果-内蒙古大学图书馆

IEEE 99th Vehicular technology Conference (VTC-Spring)

作者： Li, Lihua Li, Tong Fan, Siyi Ji, Xuan Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China

ISBN: (纸本)9798350387414

In order to meet the requirement of high spectrum efficiency of MIMO systems, the number of antennas has been greatly increased to support simultaneous communication of multiple users, and higher order modulation is expected to be employed in the system at the same time, which make signal detection a difficult task. However, most traditional algorithms reply on the channel state information (CSI) accuracy get by channel estimation at receivers. DeepSIC, developed in the existing literature, is a promising framework that introduces data-driven deep learning methods into iterative soft interference cancellation (SIC) algorithms that can address challenges of unknown CSIs and improved performance. In this paper, a signal detection algorithm is designed for MIMO systems under high-order modulation when CSI is unknown, called ResLight-DeepSIC. ResLight-DeepSIC is based on DeepSIC, introducing the idea of residual network (ResNet), and achieves betterdetection performance and lower complexity with lightweight network. Link-level simulation shows that the improved algorithm has a gain of about 1 dB on the symbol error rate (SER), and reduces complexity by about 37% and 63% under 16 QAM and 64 QAM modulation, respectively. Therefore, the ResLight-DeepSIC proposed in this article has advantages in both performance and complexity with large multiple stream transmission and high order modulation.

关键词： Interference cancellation Residual network deep learning Signal detection

来源：评论

学校读者我要写书评

暂无评论

Emotional boundaries and intensity aware model for incomplete multimodal sentiment analysis

引用

DIGITAL SIGNAL PROCESSING 2025年 160卷

作者： Zhang, Yuqing Xie, Dongliang Luo, Dawei Sun, Baosheng Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Beijing Jinghang Res Inst Comp & Commun Beijing Peoples R China

Multimodal sentiment analysis aims to obtain comprehensive emotional features from multiple data sources when all modalities are accessible. However, in real-world scenarios, it is often impossible for all modalities to be available all the time. This issue leads to a significant degradation in the performance of multimodal sentiment analysis. There are two major challenges in this field: accurately identifying samples near the classification boundaries is difficult, and the recognition performance varies significantly among different modality combinations. In this article, we propose an Emotional Boundaries and Emotional Intensity Aware (EBIA) model to enhance the robustness of incomplete multimodal sentiment analysis. Specifically, we design a Boundary Fuzzy Aware (BFA) module to learn the intra-class and inter-class consistency of samples, transferring full modalities integrity information to the missing modality environment, and prompting the model to focus on samples near the class boundaries. Additionally, we introduce a Weak Modality Aware (WMA) module that calculates additional predictions for each modality, guiding the model to focus on weak modality combinations. Extensive experiments and analyses conducted on three popular benchmark datasets demonstrate the effectiveness of our proposed method compared with several baseline methods.

关键词： Multimodal sentiment analysis Missing modality Classification boundary fuzzy Weak modality aware

来源：评论

学校读者我要写书评

暂无评论

Access Control and Collision Resolution for Massive Random Access in Satellite Internet of Things Networks 7

Access Control and Collision Resolution for Massive Random A...

引用

IEEE 7th International Workshop on Radio Frequency and Antenna technologies (IEEE IWRF and AT)

作者： Yuan, Hao Wang, Ying Jia, Huaiqi Zhang, Qiuyang Zhang, Yifan Feng, Linqing Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China

ISBN: (纸本)9798350384765;9798350384772

Satellite Internet of Things (IoT) networks are characterized by the wide coverage. However, a large number of access requests within the same beam may lead to conflicts and collisions among preamble sequences, hindering the performance and effectiveness of the access of machine-type devices (MTDs). Additionally, different from 5G networks, the satellite-terrestrial networks are accompanied by longer transmission delays, which present challenges for time-sensitive services. To solve the problem of collision fallback resulting from overload during massive random access, a dynamic distributed queue-based random access (DDQRA) approach is proposed to control the overload of satellite IoT networks. The proposed DDQRA can reduce the access delay by adopting the two-step random access approach compared to the traditional four-step random access approach. Moreover, the access class barring (ACB) scheme and the preamble collision resolution algorithm are adopted to control the random access overload and the access priority of different terminal services and resolve the conflict of overload respectively. The simulation results demonstrate that the proposed approach significantly enhances the overall success rate of random access, thereby satisfying the access requirements of time-sensitive MTDs.

关键词： Satellite Internet of Things massive random access dynamic distributed queue access class barring

来源：评论

学校读者我要写书评

暂无评论

Two-tier Multi-zone Consensus: Enable Intelligence Sharing for AIoT with Enhanced Security

Two-tier Multi-zone Consensus: Enable Intelligence Sharing f...

引用

IEEE Annual Congress on Artificial Intelligence of Things (IEEE AIoT)

作者： Liu, Weikang Cao, Bin Peng, Mugen Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China

ISBN: (纸本)9798350392302;9798350392296

With the advent of intelligence-of-everything in 6G, the explosion of Internet of Things (IoT) devices will bring massive volumes of data. Though injecting artificial intelligence (AI) technologies into IoT, namely AI of things (AIoT), can release the data value, it still faces many challenges, such as poor efficiency, lack of trust, etc. As a promising technology with decentralization, scalability, and security, leveraging blockchain in AIoT has attracted widespread attention in recent years. However, isolatability and scalability are two critical issues that hinder blockchain from building efficient, secure, and trusted intelligence-sharing platforms for AIoT. Blockchain interoperability addresses isolatability between heterogeneous blockchains, while sharding-based blockchain achieves scalability by solving isolatability of homogeneous blockchains running in different shards. To ensure atomicity between different blockchains, both blockchain interoperability and sharding-based blockchain need to enhance the resistance to double-spending attacks of the blockchain to which the cross-chain transaction originator belongs. To this end, this work presents a two-tier multi-zone consensus, where Consensus Zone in tier-1 features blockchain interoperability and sharding-based blockchain by allowing different blockchains run in different zones, while Coordination Layer in tier-2 is to enhance each zone's security by allowing them to interoperate as a Direct Acyclic Graph (DAG) in a distributed and parallel manner. Then, stochastic models are used to capture the consensus process and analyze the probability of successful double-spending attacks. From the numerical results, this consensus is proved to be with enhanced security.

关键词： blockchain direct acyclic graph scalability interoperability security

来源：评论

学校读者我要写书评

暂无评论

Adaptive robust control without initial stabilizing for constrained-states nonlinear multiplayer mixed zero-sum game systems with matched input disturbances

引用

APPLIED INTELLIGENCE 2025年第2期55卷 1-19页

作者： Qiao, Xiaopeng Qin, Chunbin Wang, Jinguang Zhang, Zhongwei Shang, Ziyang Henan Univ Sch Artificial Intelligence Zhengzhou 450000 Peoples R China Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China

In this paper, for the multiplayer mixed zero-sum game (MZSG) problem of the constrained-states nonlinear systems with matched input disturbances, an adaptive robust control method without initial stabilizing is presented on account of barrier function (BF) transformation. Firstly, the original system with state constraints is converted to a transformed system without state constraints by barrier function transformation. Secondly, to overcome the influence of matched input disturbances, considering the nominal system related to the transformation system, the cost function corresponding to each player is appropriately selected, and the robust regulation scheme with matched input disturbances is converted to the optimal regulation scheme. In addition, a novel weight tuning law is designed for the critic neural network (NN) by combining the experience replay (ER) mechanism and the index function. Then, the corresponding cost function of each player is approximated by the critic NN without requiring initial stabilizing control. Utilizing the Lyapunov stability theory, under the influence of state constraints and matched input disturbances, the critic NN weights and states within the multiplayer system are ensured to be uniformly ultimately bounded (UUB). Ultimately, the validity of the proposed method is verified by two simulation examples.

关键词： Adaptive robust control Mixed zero-sum game (MZSG) Barrier function (BF) state constraints Matched input disturbances

来源：评论

学校读者我要写书评

暂无评论

Feature Importance-Aware Task-Oriented Semantic Transmission and Optimization

引用

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND networking 2024年第4期10卷 1175-1189页

作者： Wang, Yining Han, Shujun Xu, Xiaodong Liang, Haotai Meng, Rui Dong, Chen Zhang, Ping Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Peng Cheng Lab Dept Broadband Commun Shenzhen 518066 Peoples R China

Incorporating both semantic level information and effectiveness level performance, the task-oriented semantic communication system has been designed for various tasks of different datatype. Although semantic communication improves the spectral utilization to some extent, indiscriminate transmission of semantic information for task-oriented semantic communication can still result in waste of wireless resources. In this paper, we propose an importance-aware joint source-channel coding (I-JSCC) framework for task-oriented semantic communications. A joint semantic-channel transmission (JSCT) mechanism is designed by selectively transmitting task-important features to reduce communication overhead. We define a new metric named task-oriented semantic spectral efficiency (TOSSE) to evaluate the effectiveness and efficiency of the proposed system, which measures the effective semantic information carried by each semantic symbol. An importance-aware semantic resource allocation problem is formulated to maximize the total TOSSE of all users by jointly optimizing the channel assignment and feature selection vector. To solve this problem, a knowledge-assisted proximal policy optimization (K-PPO) based reinforcement learning (RL) algorithm is proposed. The experimental results conducted on CIFAR100 dataset demonstrate the efficacy of the K-PPO algorithm, while also highlighting the superiority of the importance-aware semantic communication system in terms of the TOSSE.

关键词： Semantics Task analysis Resource management Wireless communication Feature extraction Communication systems Optimization Task-oriented semantic communication feature importance resource allocation spectral efficiency reinforcement learning (RL)

来源：评论

学校读者我要写书评

暂无评论

EclipseFortify: Imperceptible Shuffle-Based Moving Target Defense for Budget-Friendly Web Service DDoS Protection

EclipseFortify: Imperceptible Shuffle-Based Moving Target De...

引用

IEEE International Conference on Web Services (IEEE ICWS)

作者： Yan, Lin Zhou, Zan Yang, Shujie Xu, Changqiao Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China

ISBN: (纸本)9798350368567;9798350368550

Distributed Denial of Service (DDoS) attacks continue to pose a significant threat to web services, making effective defense strategies crucial. However, traditional DDoS protection solutions are often expensive and may not be feasible for all organizations. To address this challenge, this paper presents EclipseFortify, a novel approach that combines the principles of Moving Target Defense (MTD) with cost-effective measures. EclipseFortify leverages the concept of reverse proxies as moving targets, employing proactive shuffling techniques to dynamically allocate valid proxies to users. By disrupting the correlation between users and reverse proxies, EclipseFortify effectively rejects attack traffic, significantly reducing the cost of defense. Furthermore, the method introduces a dynamically updated suspicious rating system to counter advanced attackers who adapt their strategies. To ensure uninterrupted service, EclipseFortify embeds scripts in reverse proxy forwarding, establishing a control link with user-side browsers. This enables seamless switching of reverse proxies without affecting users' browsing experience. Experimental evaluations demonstrate the effectiveness of EclipseFortify in mitigating DDoS attacks while remaining imperceptible to legitimate users. A demo of EclipseFortify is available at https://***/r/frogsoftware/eclipse-fortify.

关键词： DDoS protection moving target defense reverse proxies web services budget friendly

来源：评论

学校读者我要写书评

暂无评论

A Revocable and key Secure Ciphertext-Policy Attribute-based Encryption Scheme Based on Blockchain 24

A Revocable and Key Secure Ciphertext-Policy Attribute-based...

引用

3rd International Conference on Cyber Security, Artificial Intelligence and Digital Economy (CSAIDE)

作者： Zhou, Xingyu Li, Wenmin Zhang, Huimin Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China

ISBN: (纸本)9798400718212

Amidst the surge in privacy breaches in the era of big data, individuals are increasingly concerned about the security of their personal information. This paper centers its research on personal privacy data in the realm of big data, specifically focusing on CP-ABE. The proposed Blockchain-based User Revocation-CPABE (BUR-CP-ABE) scheme enhances distributed security by integrating blockchain and smart contract technologies. Using smart contracts for managing user lists and employing searchable encryption algorithms to protect on-chain data privacy enable flexible user revocation. To address key leakage concerns, the key fragmentation approach divides the decryption key into on-chain and off-chain segments, effectively mitigating potential key exposure risks. BURCP-ABE offers a revocable and key secure CP-ABE scheme.

关键词： CP-ABE Blockchain User Revocation Searchable Encryption

来源：评论

学校读者我要写书评

暂无评论

Near-Field Tracking with Extremely Large-Scale RIS: A Sparse Learning Approach 25

Near-Field Tracking with Extremely Large-Scale RIS: A Sparse...

引用

IEEE Wireless Communications and networking Conference (IEEE WCNC)

作者： Yuan, Ye Chen, Yuanbin Guo, Xufeng Wang, Ying Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China

ISBN: (纸本)9798350303582;9798350303599

In this paper, we investigate the employment of the extremely large-scale reconfigurable intelligent surface (XL-RIS) in dynamic near-field wireless communication systems. Given the spherical-wavefront nature in the near-field context, channel estimation becomes more challenging, in particular for time-varying channels due to the mobility of the transceivers. This implies that frequent feedback of high-dimensional cascaded channel state information (CSI) associated with XL-RIS entails substantial overhead. To tackle this challenge, we propose a channel tracking scheme for the near-field XL-RIS regime. Specifically, a Kalman filter (KF) based framework is proposed, in which two learning-based networks are employed for obtaining the channel information of the first time slot, thereby acquiring initial prior information for the KF technique. Subsequently, leveraging the known prior information and the temporal correlation of the time-varying channel, the cascaded channel matrix for the next time slot is continuously predicted. Following that, the prediction is updated and refined using the observation from the current time slot as a benchmark, enhancing the accuracy and reliability of the channel tracking process. Finally, simulation results are provided to verify the effectiveness of the proposed scheme.

关键词： XL-RIS near-field time-varying channel tracking Kalman filter

来源：评论

学校读者我要写书评

暂无评论

Joint Power Allocation and Reliability Optimization with Generative AI for Wireless Networked Control Systems

Joint Power Allocation and Reliability Optimization with Gen...

引用

IEEE/CIC International Conference on Communications in China (ICCC)

作者： Wang, Xudong Feng, Lei Zhou, Fanqin Li, Wenjing Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China

ISBN: (纸本)9798350377675;9798350377682

Leveraging the characteristics of wireless connectivity, wireless networked control systems (WNCSs) offer high flexibility and low deployment costs, garnering widespread interest. However, the time-varying nature of wireless channels poses significant challenges to the control reliability of WNCS. To meet the stringent control reliability and rate performance demands in factory automation scenarios, we propose a novel joint optimization design for the uplink transmission of sensors in multiloop WNCSs. Our goal is to maximize the sum rate by jointly optimizing power allocation at the base station and reliability at the control systems (CSs), while considering practical constraints such as packet error rate (PER), control stability, and energy. We derive an expression for the PER and system state convergence to guide the co-design process, and then introduce a generative AI-based joint power and reliability optimization strategy. Numerical results demonstrate that the proposed algorithm outperforms several baseline algorithms, significantly enhancing the sum rate performance while ensuring system control stability.

关键词： Wireless networked control system diffusion model generative AI power allocation

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：