检索结果-内蒙古大学图书馆

IET International Radar Conference 2023, IRC 2023

作者： Wang, Ziwen Wei, Yangkai Ding, Zegang Shan, Xueting Wu, Yifan School of Information and Electronics Beijing Institute of Technology Beijing China Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Beijing China

ISBN: (纸本)9781839539954

Synthetic Aperture Radar (SAR) image reconstruction fundamentally constitutes an ill-posed reconstruction conundrum, with the overarching objective of faithfully restoring the'authentic' SAR scenes via radar echo measurements and a forward model. The conventional FFT-based approach, in conjunction with matched filtering, tends to yield undesirable sidelobes and speckle artifacts. Conversely, the reconstruction challenge can be cast as a minimization problem, seeking to enhance outcomes by merging data-term and prior-related terms. This composite problem is amenable to resolution via proximal methods. In this paper, a novel data-driven methodology is employed, leveraging the plug-and-play (PNP) technique to train a neural network for acquiring target image priors. In comparison to traditional manually crafted priors and PNP priors, the proposed PNP deep priors exhibit the capacity to achieve superior reconstruction results. Experimental assessments involving synthetic and real SAR scenes underscore the robustness and efficacy of the proposed approach. © The Institution of Engineering & technology 2023.

关键词： Matched filters

来源：评论

学校读者我要写书评

暂无评论

A Hippocampus Spatial Cognition Model based on Predictive Coding 43

A Hippocampus Spatial Cognition Model based on Predictive Co...

引用

43rd Chinese Control Conference, CCC 2024

作者： Yu, Naigong Lv, Zexuan Yan, Jinhan Beijing University of Technology Faculty of information Technology Beijing100021 China Beijing Key Laboratory of Computing Intelligence and Intelligent System Beijing100021 China

ISBN: (纸本)9789887581581

In current computation neuroscience, it is widely accepted that the mammalian entorhinal-hippocampus complex provides representations of spatial environment, exhibiting specific responses to particular locations and directions. Various computation models of spatial cell firing have been proposed to unravel the mysteries of spatial cognition representation in the brain. However, an increasing body of experimental evidence suggests that the brain operates more akin to a predictive system. Actively acquiring and utilizing limited environmental information, the brain constructs internal models during interaction with the external world, generating predictive representations of internal states following environmental changes. Building upon this premise, we propose a predictive coding theory-based entorhinal-hippocampus spatial cognition model. This model incorporates vestibular proprioceptive cues and border vector cells discharge responses to initially derive unimodal place cell discharge fields, followed by hippocampal place cells projecting to the entorhinal cortex via excitatory-inhibitory synaptic connections, ultimately generating periodic hexagonal grid cell discharge fields. Experimental results demonstrate that the neuronal discharge patterns obtained by this model align with physiological research findings, thereby providing new insights for further investigations into brain cognitive mechanisms. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Mammals

来源：评论

学校读者我要写书评

暂无评论

Inter-cell Interference Exploitation through Distributed Symbol Level Precoding for Multi-cell MISO Systems

Inter-cell Interference Exploitation through Distributed Sym...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Zhang, Yukun Lv, Gangming Yang, Jianping Liao, Xuewen School of Information and Communications Engineering Xi'an Jiaotong University Xi'an China Shaanxi Key Laboratory of Deep Space Exploration Intelligent Information Technology Xi'an China

ISBN: (纸本)9798350351255

In this paper, we propose distributed symbol-level precoding (SLP) schemes to manage inter-cell interference in downlink multi-user multi-cell coordination systems. Initially, we introduce the constructiveness as a novel metric to quantify the received signal quality. We then define the square of the constructiveness-over-noise ratio (CoNR) to represent the equivalent signal-to-noise ratio (SNR). Subsequently, we propose a distributed precoding scheme where each base station (BS) aims to maximize the CoNR obtained by the worst user within its cell while ensuring inter-cell interference remains constructive. To further manage interference, we propose an additional distributed precoding scheme, where each BS enhances overall system performance by maximizing the sum of the minimum constructiveness from both intra-cell and inter-cell interference. Simulation results demonstrate that our proposed distributed precoding schemes surpass traditional block-level precoding in performance. © 2024 IEEE.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Sampled-data distributed control of mixed traffic flow with ACC-equipped vehicles 63

Sampled-data distributed control of mixed traffic flow with ...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Zhao, Hanxu Zhan, Jingyuan Zhang, Liguo Beijing University of Technology Faculty of Information Technology Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent Systems Beijing100124 China

ISBN: (纸本)9798350316339

This paper studies the sampled-data distributed control problem for mixed traffic flow described by the Aw-Rascle-Zhang (ARZ) model, which consists of both manual and adaptive cruise control-equipped (ACC-equipped) vehicles. A group of stationary sensing devices provides spatially averaged state measurements over the sampling spatial intervals, and then the sampled-data distributed controller is designed as the time-gap setting of ACC-equipped vehicles based on the state measurements sampled in space and time. The closedloop system is re-organized into an equivalent system containing a continuous time control loop and spatio-temporal sampling errors. Then sufficient conditions for ensuring exponential stability of the mixed traffic flow system are developed in terms of matrix inequalities, by employing the Lyapunov function method along with Wirtinger's and Jensen's inequalities in H1-norm. Finally, the effectiveness of the proposed method is verified by numerical simulations. © 2024 IEEE.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

PACE: Reputation-Driven Hierarchical Incentive Mechanism for Trusted Healthcare Transactions in Model Marketplace

引用

IEEE Transactions on Consumer Electronics 2024年第1期71卷 1571-1583页

作者： Lu, Jianfeng Dou, Xiaochi Rathore, Bharati Jhaveri, Rutvij H. Seid, Abegaz Mohammed Erbad, Aiman Wuhan University of Science and Technology School of Computer Science and Technology Wuhan430065 China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System China Ministry of Education Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology China United Kingdom Pandit Deendayal Energy University Department of Computer Science and Engineering School of Technology India Hamad Bin Khalifa University College of Science and Engineering Doha Qatar Qatar University College of Engineering Doha Qatar

Federated learning-based model marketplaces have the potential to securely leverage healthcare data for efficient healthcare transactions. However, the willingness to participate in this marketplace is severely hindered by self-interested model sellers, who maximize their personal gains via distorting the quality of their models. To this end, we propose a rePutation-driven hierArchical inCentive mEchanism, called PACE, which combines contract cooperation and game pricing to motivate model sellers to be honest, thereby improving the sustainability of the model marketplace via two-layer cooperation. Specifically, at the training layer, we design a reward payment rule based on multidimensional contracts, while at the trading layer, we use a competitive market pricing game to develop the accuracy pricing rule. In particular, the above rules cleverly combine the fine-grained model sellers' reputations with the willingness of healthcare devices to indirectly affect the model sellers' utilities. Theoretically, we prove that PACE can effectively incentivize model sellers to truthfully report model quality while satisfying both individual rationality and incentive compatibility with a fairness guarantee. Experimental results conducted on four real-world datasets show that our PACE improves the global performance by up to 12.85% and reduces the global loss by at least 19.23% compared with the state-of-the-art baselines. © 1975-2011 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

A Novel Environment Reconstruction Method based on Distributed NLOS Signals 16

A Novel Environment Reconstruction Method based on Distribut...

引用

16th International Conference on Signal processing Systems, ICSPS 2024

作者： Yu, Fangrui Li, Junlin Xie, Wei Zhang, Kehao Wan, Qun School of Information and Communication Engineering Nation Key Laboratory on Blind Signal Processing University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9781510689251

Integrated Sensing and Communication (ISAC) is a rapidly evolving field with extensive application prospects. Environmental reconstruction (ER) is an important content of ISAC. Existing ER techniques often require large sample sizes or specific signals, which significantly limit their application. User Equipments (UEs) widely distributed in the environment and their communication signals provide an adequate measurement basis. However, there are challenges in utilizing communication signals due to limited research, and difficulties in identifying and extracting Non-Line-of-Sight (NLOS) signals. This paper proposes a distributed ER algorithm based on Angle of Arrival (AOA) and Time of Flight (TOF) information of NLOS signals, enabling identification and utilization of various order NLOS signals under complex NLOS conditions. A series of simulation delays validate the effectiveness of the proposed method. © 2025 SPIE.

关键词： Non line of sight propagation Reflection Reconstruction algorithms Mirror pointing Signal processing Environmental sensing Wireless communications

来源：评论

学校读者我要写书评

暂无评论

Diffusion Ranking Scores Based Improved Hypergraph Generation Method for Visual Classification Tasks 13

Diffusion Ranking Scores Based Improved Hypergraph Generatio...

引用

13th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2024

作者： Wang, Shuai Wang, Kang Li, Xiaoli Beijing University of Technology Faculty of Information Technology Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing100124 China

ISBN: (纸本)9798350361674

Visual classification has attracted considerable research attention in the last few decades. This paper presents an approach to improve the hypergraph structure using a diffusion ranking method and employs hypergraph neural networks for such tasks. Hyperedges are formed by connecting a set of vertices, and the generation of the hypergraph structure is typically task-dependent, making hypergraph generation methods less generalizable. Previous approaches have employed implicit hypergraphs for visual tasks, especially in visual classification, using attribute-based or neighborhood-based methods. However, these approaches cannot fully explore the global manifold structure of the feature space. To address this problem, this paper proposes a novel two-stage hypergraph construction method, which fully utilizes the ability of diffusion process to capture the manifold structure of feature data. Initially, the hypergraph structure is constructed using a neighbor-based approach, and subsequently, the final hypergraph structure is obtained by ranking scores of diffusion processes that reflect the degree of vertex similarity. Comparing with state-of-the-art hypergraph neural network algorithms on classical 3D visual image datasets, experimental results demonstrate the effectiveness of the proposed algorithm. © 2024 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Policy Network-Based Dual-Agent Deep Reinforcement Learning for Multi-Resource Task Offloading in Multi-Access Edge Cloud Networks

引用

China Communications 2024年第4期21卷 53-73页

作者： Feng Chuan Zhang Xu Han Pengchao Ma Tianchun Gong Xiaoxue School of Communications and Information Engineering Chongqing University of Posts and TelecommunicationsChongqing 400065China Institute of Intelligent Communication and Network Security Chongqing University of Posts and TelecommunicationsChongqing 400065China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and TelecommunicationsChongqing 400065China School of Information Engineering Guangdong University of TechnologyGuangzhou 510006China

The Multi-access Edge Cloud(MEC) networks extend cloud computing services and capabilities to the edge of the networks. By bringing computation and storage capabilities closer to end-users and connected devices, MEC networks can support a wide range of applications. MEC networks can also leverage various types of resources, including computation resources, network resources, radio resources,and location-based resources, to provide multidimensional resources for intelligent applications in 5/***, tasks generated by users often consist of multiple subtasks that require different types of resources. It is a challenging problem to offload multiresource task requests to the edge cloud aiming at maximizing benefits due to the heterogeneity of resources provided by devices. To address this issue,we mathematically model the task requests with multiple subtasks. Then, the problem of task offloading of multi-resource task requests is proved to be NP-hard. Furthermore, we propose a novel Dual-Agent Deep Reinforcement Learning algorithm with Node First and Link features(NF_L_DA_DRL) based on the policy network, to optimize the benefits generated by offloading multi-resource task requests in MEC networks. Finally, simulation results show that the proposed algorithm can effectively improve the benefit of task offloading with higher resource utilization compared with baseline algorithms.

关键词： benefit maximization deep reinforcement learning multi-access edge cloud task offloading

来源：评论

学校读者我要写书评

暂无评论

Performance Bound on Blind Estimation of Environmental Parameters and Radiation Source Locations with Misspecified Multipath TOA Measurements 16

Performance Bound on Blind Estimation of Environmental Param...

引用

16th International Conference on Signal processing Systems, ICSPS 2024

作者： Wen, Hao Jiao, Yang Zhang, Kehao Peng, Xiangyu Wan, Qun Nation Key Laboratory on Blind Signal Processing School of Information and Communication Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9781510689251

Multipath propagation has attracted extensive attention due to its inclusion of environmental information. However, it is difficult to match multipath with the environment without a priori knowledge, making it challenging to exploit multipath. This paper focuses on the performance bound of the estimation problem in a rectangular room. Due to the lack of parameter information of the room in base station (BS), the estimation of environmental parameters and locations of user equipment (UE) distributed in the room are blind estimation problems. Measurements are the time of arrival (TOA) of first-order non-line-of-sight (NLOS) paths and line-of-sight (LOS) path between the BS and UEs, but the specific pairing between NLOS paths and the environment remains unknown. The paper first describes the pairing problem, which causes misspecified multipath TOA measurements, and subsequently derives the likelihood function and the performance bound known as the misspecified Cramer-Rao bound (MCRB) under various pairing conditions. Simulation results demonstrate that only under correct pairings or just a few wrong pairings, the MCRB will significantly less than the other case. © 2025 SPIE.

关键词： Cramer-Rao bounds

来源：评论

学校读者我要写书评

暂无评论

Impact Investigation of Adversarial Samples on CNN-Based SAR Image Target Detectors 6

Impact Investigation of Adversarial Samples on CNN-Based SAR...

引用

6th IEEE International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2023

作者： Zhou, Peng Xiao, Shunping Li, Mingdian Deng, Junwu Xing, Xiangwei Chen, Siwei National University of Defense Technology College of Electronic Science and Technology Changsha China Satellite Information Intelligent Processing and Application Research Laboratory Beijing China

ISBN: (纸本)9798350325485

In recent years, deep learning algorithms based on convolutional neural networks (CNN) have made breakthroughs in the field of target detection in Synthetic Aperture Radar (SAR) images. However, CNN may be vulnerable to adversarial examples, raising security concerns for practical deployment. To gain a deeper understanding of adversarial examples and provide a theoretical basis for building robust detection networks, this study comprehensively investigates the impacts of adversarial samples generated by deep recognition networks (DRN) in SAR images on the performance of target detection networks with different principles, using YOLOv3 and Faster-RCNN as examples. Experimental results on the MiniSAR vehicle target dataset show that adversarial samples pose a more serious threat to the single-stage detection network YOLOv3. Simply adding small perturbation that are invisible for human eyes to the SAR image can mislead the detector into missing the majority of targets. In contrast, two-stage detection networks like Faster-RCNN exhibit stronger robustness with their detection performance being less influenced by the adversarial examples generated by different DRN. © 2023 IEEE.

关键词： Synthetic aperture radar

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：