检索结果-内蒙古大学图书馆

Causal Attention Transformer for Video Text Retrieval

IET Image Processing 2025年第1期19卷

作者： Lan, Hua Lv, Chaohui School of Information and Communication Engineering Communication University of China Beijing China Key Laboratory of Acoustic Visual Technology and Intelligent Control System Ministry of Culture and Tourism Beijing China

In the metaverse, video text retrieval is an urgent and challenging need for users in social entertainment. The current attention-based video text retrieval models have not fully explored the interaction between video and text, and only brute force feature embedding. Moreover, Due to the unsupervised nature of attention weight training, existing models have weak generalization performance for dataset bias. Essentially, the model learns that false relevant information in the data is caused by confounding factors. Therefore, this article proposes a video text retrieval method based on causal attention transformer. Assuming that the confounding factors affecting the performance of video text retrieval all come from the dataset, a structural causal model that conforms to the video text retrieval task is constructed, and the impact of confounding effects during data training is reduced by adjusting the front door. In addition, we use causal attention transformer to construct a causal inference network to extract causal features between video text pairs, and replace the similarity statistical probability with causal probability in the video text retrieval framework. Experiments are conducted on the MSR-VTT, MSVD, and LSMDC datasets, which proves the effectiveness of the retrieval model proposed in this paper. © 2025 The Author(s). IET Image Processing published by John Wiley & Sons Ltd on behalf of The Institution of engineering and technology.

关键词： Interactive computer graphics

来源：评论

学校读者我要写书评

暂无评论

Adaptive communication Spectrum Sensing Algorithm Based on Energy Detection 7th

Adaptive Communication Spectrum Sensing Algorithm Based on E...

引用

7th International Conference on Wireless communications, Networking and Applications, WCNA 2023

作者： Shi, Weihong Tang, Tao Zhao, Runhui Wen, Hong Feng, Xuewei School of Aeronautics and Astronautics University of Electronic Science and Technology of China Chengdu611731 China Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province Chengdu611731 China Sichuan Intelligent loT Communication Technology Engineering Research Center UESTC Chengdu China

ISBN: (纸本)9789819624089

Based on the traditional energy detection algorithm, an adaptive communication spectrum sensing algorithm based on energy detection is proposed for signals whose noise power is difficult to be estimated accurately. The algorithm takes into account the problem of large error in calculating the energy detection judgment threshold by noise power when the estimated value of noise power is inaccurate, and is able to perform adaptive communication spectrum sensing for signals with less a priori information and noise power that cannot be estimated accurately. Simulation results show that the adaptive communication spectrum sensing algorithm based on energy detection can effectively improve the performance of spectrum sensing for signals, and the algorithm can effectively detect and sense signals under the condition of reasonable setting of judgment coefficients. © The Author(s) 2025.

关键词： Adaptive Cognitive radio Energy detection Spectrum sensing

来源：评论

学校读者我要写书评

暂无评论

An Offline Learning-Based Anti-interference communication Scheme for UAV Networks 7th

An Offline Learning-Based Anti-interference Communication Sc...

引用

7th International Conference on Wireless communications, Networking and Applications, WCNA 2023

作者： Tang, Tao Zhao, Runhui Wen, Hong Feng, Xuewei Shi, Weihong Peng, Yulin School of Aeronautics and Astronautics University of Electronic Science and Technology of China Chengdu611731 China Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province Chengdu611731 China Sichuan Intelligent IoT Communication Technology Engineering Research Center UESTC Chengdu China

ISBN: (纸本)9789819624089

Unmanned Aerial Vehicles (UAV) face challenges from advanced interference technologies, making them susceptible to malicious node attacks, data interception, and tampering. Traditional anti-interference decisions have limitations, as they cannot adaptively adjust to changes in interference signals. Moreover, anti-interference communication models based on Deep Reinforcement Learning (DRL) require prolonged interactions with the environment, demanding high requirements for anti-interference environments. This paper investigates an offline anti-interference decision based on Decision-Transformers, which can quickly and stably acquire practical anti-interference decision models. Simulation experiments have verified the effectiveness of this algorithm in making anti-interference decisions under AWGN and fading channel conditions. Furthermore, this offline approach can achieve the expected reward targets with fewer training iterations. © The Author(s) 2025.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Chaotic index modulation and subcarrier intra-block-inter-block shuffling for secure CO-OFDM-PON based on a hybrid 4D chaos

引用

Optics Express 2025年第10期33卷 21217-21235页

作者： Wang, Yun Pan, Xiaolong Zhang, Qi Xin, Xiangjun Gao, Ran Yao, Haipeng Tian, Feng Wang, Fu Li, Zhipei Liu, Xiangyu Tian, Qinghua Wang, Yongjun Yang, Leijing Zhou, Sitong Li, Zuolin Li, Ying School of Electronic Engineering Beijing University of Posts and Telecommunications (BUPT) Beijing 100876 China Beijing Key Laboratory of Space-round Interconnection and Convergence BUPT Beijing 100876 China School of Information and Electronics Beijing Institute of Technology (BIT) Beijing 100081 China School of Information and Communication Engineering BUPT Beijing 100876 China Beijing Institute of Control and Electronic Technology Beijing 100038 China Beijing Institute of Remote Sensing Equipment Beijing 100039 China

In this paper, a four-dimensional (4-D) encryption scheme with chaotic index modulation (IM) and subcarrier intra-block-inter-block shuffling is proposed to enhance the physical layer security of coherent orthogonal frequency division multiplexing passive optical network (CO-OFDM-PON). The scheme utilizes a hybrid 4-D chaotic scheme consisting of 1-D Cubic chaotic mapping and 3-D T-S Fuzzy chaotic system to generate four dynamic scrambling factors to achieve 4-D ultra-high security encryption of index bits, data bits, intra-subcarrier block, and inter-subcarrier block. Firstly, the chaotic many-to-many mapping rule between index bits and subcarrier activation patterns (SAPs) is constructed based on the IM principle to realize the index bit encryption;secondly, the data bit encryption is realized by heterodyning with chaotic bits. Further, the chaotic shuffling algorithm is proposed to disrupt and rearrange the symbols within and between subcarrier blocks to realize OFDM-IM symbol secondary encryption. To validate the feasibility of the proposed encryption scheme, simulations in a CO-OFDM-PON system evaluate the performance of a 63.76 Gb/s encrypted 16 quadrature amplitude modulation (QAM) OFDM-IM signal over transmission distances of 25 km and 80 km through standard single-mode fiber (SSMF). The results demonstrate that legitimate users can successfully recover the encrypted signals, while eavesdroppers consistently experience a bit error rate (BER) close to 0.5, making it nearly impossible to extract useful information. The initial value sensitive tolerance precision of the key (x0, y0, z0, w0, a1, b1, c1, a2, b2, c2, a3, b3, c3, µ) is (10⁻¹⁵, 10⁻¹⁵, 10⁻¹⁴, 10⁻¹⁶, 10⁻¹⁵, 10⁻¹⁴, 10⁻¹⁵, 10⁻¹⁴, 10⁻¹⁶, 10⁻¹⁶, 10⁻¹⁵, 10⁻¹⁵, 10⁻¹⁵, 10⁻¹⁵), and the key space is as high as 10²¹⁰. The proposed scheme achieves th

关键词： Frequency division multiplexing Laser communications Neural networks Optical access networks Signal transmission Single mode fibers

来源：评论

学校读者我要写书评

暂无评论

Robust Federated Learning Algorithm Based on Chaotic Encryption and Dual-Server Detection

引用

IEEE Internet of Things Journal 2025年

作者： Kang, Shouqiang Wu, Yuxuan Wang, Yujing Wang, Qingyan Liang, Xintao Harbin University of Science and Technology School of Measurement and Control Technology and Communication Engineering Harbin150080 China

Federated learning allows users to collaboratively train models, but studies have shown that local model parameters may leak users’ privacy. Furthermore, the global model in federated learning could be compromised by Byzantine attacks. To address these issues, a robust federated learning algorithm based on chaotic encryption and dual-server detection (CDRFL) is proposed. First, CDRFL introduces a lightweight chaotic encryption method, where ciphertexts have a unique property of mutual cancellation, allowing the plaintext global model parameters to be derived without decryption. Moreover, CDRFL allows users to encrypt with different keys, further reducing the risk of privacy leakage. Next, a dual-server detection scheme is designed to defend against Byzantine attacks while preserving user privacy. Lastly, a reputation score mechanism with a forgetting function is proposed to fairly distinguish Byzantine participants. Experimental results demonstrate that, compared with popular robust aggregation schemes, CDRFL improves testing accuracy by 3.26% to 9.06%. When compared to existing chaotic encryption federated learning schemes, CDRFL enhances the ability to defend against Byzantine attacks and reduces time and communication overhead by 73.63% and 95.40%, respectively. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Review of Machine Tool Motorized Spindle Variable Pressure Preload technology Research

引用

Recent Patents on engineering 2025年第5期19卷

作者： Dai, Ye Deng, Hao Pan, Gaofeng Chen, Xinda Key Laboratory of Advanced Manufacturing and Intelligent Technology Ministry of Education School of Mechanical and Power Engineering Harbin University of Science and Technology Harbin150080 China School of College of Measurement and Control Technology and Communication Engineering Harbin University of Science and Technology Harbin150080 China

High-precision spindles are a vital study topic because of the growing demand for high-speed, high-precision, reliable, and long-lasting machine tools. Bearing preload is the primary means of improving the accuracy of the spindle rotor system. This patent study aims to summarize the research results, systematically analyze and evaluate the machine tool motorized spindle variable pressure preload technology, and provide a scientific basis for the practical application of the motor spindle variable pressure preload technology. This study is an in-depth analysis of the basic principles of the electric spindle preloading technology, the study of its influence mechanism on the thermal deformation, stiffness, slewing error, and life of the spindle system, and a discussion of the current shortcomings in the field of spindle preloading to provide a reference for the subsequent optimization. In the spindle system, the performance of rolling bearings and the design of bearing preload have an important impact on the spindle's accuracy and stability. The traditional preload method has yet to meet the requirements of modern high-speed machine tools. Real-time controllable preload has become the new direction of development, but the current preload technology still has certain limitations and needs to be further improved. In the future, the spindle bearing variable pressure preload technology will be more efficient and intelligent. © 2025 Bentham Science Publishers.

关键词： Machine tools

来源：评论

学校读者我要写书评

暂无评论

OS-SEI: Open-Set Specific Emitter Identification Based on Outlier Exposure and Label Smoothing

引用

IEEE Internet of Things Journal 2025年

作者： Wang, Juzhen Wang, Hanhong Wang, Wei Zha, Haoran Hangzhou Dianzi University School of Communication Engineering Hangzhou310018 China Binjiang Institute of Artificial Intelligence of Zhejiang University of Technology Hangzhou310052 China Science and Technology on Communication Information Security Control Laboratory Jiaxing314033 China Harbin Engineering University College of Information and Communication Engineering Harbin150009 China

Specific Emitter Identification (SEI), based on the inevitable hardware imperfections of emitters, plays a crucial role in physical layer security, independent of upper-layer cryptographic methods. In recent years, SEI combined with deep learning has demonstrated exceptional performance and considerable potential. However, most SEI methods are designed for closed, independent identically distributed environments, which contrasts with real-world open scenarios. This discrepancy leads to significant security vulnerabilities when deploying models in practical applications. To address this challenge, we propose a novel Open-Set SEI (OS-SEI) framework, Outlier Exposure with Label Smoothing (OELS), which utilizes partial exposure to auxiliary anomalous data during the training phase and introduces specific loss functions to mitigate the open-set risk. By constructing smooth decision boundaries through label smoothing and applying thresholds to class confidence, our SEI framework demonstrates robust open-set authentication capabilities. Extensive experiments conducted on ADS-B and WiFi datasets show that the OELS method achieves outstanding open-set recognition performance, with F1 scores of 83.77% and 93.14% at an openness level of 0.10557. Furthermore, ablation experiments confirm the effectiveness and potential of our framework’s components. By increasing the diversity of auxiliary unknown data, we further improve performance in OS-SEI tasks. © 2014 IEEE.

关键词： Hardware security

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Solution to Quantum Process Tomography: Error Analysis and Optimal Design

引用

IEEE Transactions on Information Theory 2025年第3期71卷 1803-1823页

作者： Xiao, Shuixin Wang, Yuanlong Zhang, Jun Dong, Daoyi Mooney, Gary J. Petersen, Ian R. Yonezawa, Hidehiro University of New South Wales School of Engineering and Technology CanberraACT2600 Australia University of Michigan-Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai200240 China The Australian National University School of Engineering CanberraACT2601 Australia Chinese Academy of Sciences Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Beijing100190 China The Australian National University CIICADA Laboratory School of Engineering CanberraACT2601 Australia The University of Melbourne School of Physics ParkvilleVIC3010 Australia RIKEN Center for Quantum Computing Saitama351-0198 Japan Centre for Quantum Computation and Communication Technology Australian Research Council CanberraACT2600 Australia

Quantum process tomography is a critical task for characterizing the dynamics of quantum systems and achieving precise quantum control. In this paper, we propose a two-stage solution for both trace-preserving and non-trace-preserving quantum process tomography. Utilizing a tensor structure, our algorithm exhibits a computational complexity of O(MLd2) where d is the dimension of the quantum system and M, L(M≥ d2, L≥ d2) represent the numbers of different input states and measurement operators, respectively. We establish an analytical error upper bound and then design the optimal input states and the optimal measurement operators, which are both based on minimizing the error upper bound and maximizing the robustness characterized by the condition number. Numerical examples and testing on IBM quantum devices are presented to demonstrate the performance and efficiency of our algorithm. © 1963-2012 IEEE.

关键词： Error analysis

来源：评论

学校读者我要写书评

暂无评论

Frequency Agile Strategy Design of Radar Network for Wideband Sweep Jamming via Coalition Formation Game

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Liao, Maosen Xiong, Kui Zhang, Long Yu, Xianxiang Cui, Guolong University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Laboratory of Electromagnetic Space Cognition and Intelligent Control Technology Beijing100089 China School of Information and Communication Engineering Chengdu611731 China UESTC Shenzhen Institute for Advanced Study Chengdu611731 China

This article proposes an intelligent frequency agile design strategy for radar network using coalition game theory to counter wideband sweep jamming, which is formulated as a two-stage decision-making problem. In the first stage, the entire frequency agile range is divided into several non-overlapping agile subrange, and each radar selects a frequency agile subrange to join, which is solved by the coalition formation algorithm. Then, after achieving a stable coalition partition, a distributed multi-agent reinforcement learning algorithm is developed to address the specific carrier frequency selection problem within each coalition. By combining these two stages of the frequency agile design strategy, a joint coalition formation game and distributed Q-learning algorithm (CFDQ) is proposed. Finally, numerical simulations are conducted to illustrate the superiority of the proposed algorithm over several typical frequency agile strategies. © 1965-2011 IEEE.

关键词： Jamming

来源：评论

学校读者我要写书评

暂无评论

DSAC-T Based Resource Allocation Strategy for Delay Minimization in RIS-Aided MEC Networks

DSAC-T Based Resource Allocation Strategy for Delay Minimiza...

引用

IEEE Conference on Wireless communications and Networking

作者： Tianyu Pang Fuhao Liu Xinpei Chen Jiansong Miao Junsheng Mu Zaodi Song School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China North Automatic Control Technology Institute Taiyuan China

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

With the explosive growth of user data in 6G networks, existing infrastructures face significant scalability and latency challenges. Mobile Edge Computing (MEC) partially alleviates these issues by deploying computational resources closer to users, but still struggles to fully meet the growing demands. Re-configurable Intelligent Surfaces (RIS) enhance communication performance by improving channel quality. However, optimizing resource allocation in RIS-aided MEC systems remains a critical challenge due to the complexity of real-time optimization of multiple parameters. Although Deep Reinforcement Learning (DRL) methods like Deep Deterministic Policy Gradient (DDPG) have been applied, they often suffer from Q-value overestimation and instability, resulting in suboptimal performance in dynamic environments. This paper focuses on a single-cell RIS-aided MEC network where multiple user devices offload computational tasks to an edge server. We propose an optimized resource allocation scheme using an improved Distributed Soft Actor-Critic (DSAC-T) algorithm. This approach jointly optimizes power control, computation offloading, edge computing resource allocation, and RIS phase shifts, aiming to minimize total offloading delay to ensure real-time service requirements. Simulation results demonstrate that DSAC-T outperforms multiple baseline methods (e.g., DDPG and SAC) in reducing offloading delay by 46.39% and 16.70%, respectively, while significantly enhancing system stability and convergence speed.

关键词： Heuristic algorithms Simulation Power control Stability analysis Real-time systems Delays Resource management Servers Optimization Convergence

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：