检索结果-内蒙古大学图书馆

Event-Triggered Communication Network With Limited-Bandwidth Constraint for Multi-Agent Reinforcement Learning

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING systemS 2023年第8期34卷 3966-3978页

作者： Hu, Guangzheng Zhu, Yuanheng Zhao, Dongbin Zhao, Mengchen Hao, Jianye Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Huawei Noahs Ark Lab Beijing 100085 Peoples R China

Communicating agents with each other in a distributed manner and behaving as a group are essential in multi-agent reinforcement learning. However, real-world multi-agent systems suffer from restrictions on limited bandwidth communication. If the bandwidth is fully occupied, some agents are not able to send messages promptly to others, causing decision delay and impairing cooperative effects. Recent related work has started to address the problem but still fails in maximally reducing the consumption of communication resources. In this article, we propose an event-triggered communication network (ETCNet) to enhance communication efficiency in multi-agent systems by communicating only when necessary. For different task requirements, two paradigms of the ETCNet framework, event-triggered sending network (ETSNet) and event-triggered receiving network (ETRNet), are proposed for learning efficient sending and receiving protocols, respectively. Leveraging the information theory, the limited bandwidth is translated to the penalty threshold of an event-triggered strategy, which determines whether an agent at each step participates in communication or not. Then, the design of the event-triggered strategy is formulated as a constrained Markov decision problem and reinforcement learning finds the feasible and optimal communication protocol that satisfies the limited bandwidth constraint. Experiments on typical multi-agent tasks demonstrate that ETCNet outperforms other methods in reducing bandwidth occupancy and still preserves the cooperative performance of multi-agent systems at the most.

关键词： Bandwidth Protocols Reinforcement learning Task analysis Optimization Communication networks Multi-agent systems Event trigger limited bandwidth multi-agent communication multi-agent reinforcement learning (MARL)

来源：评论

学校读者我要写书评

暂无评论

A Novel Scenarios Engineering Methodology for Foundation Models in Metaverse

引用

IEEE TRANSACTIONS ON systemS MAN CYBERNETICS-systemS 2023年第4期53卷 2148-2159页

作者： Li, Xuan Tian, Yonglin Ye, Peijun Duan, Haibin Wang, Fei-Yue Peng Cheng Lab Dept Math & Theories Shenzhen 518000 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Beihang Univ Sch Automat Sci & Elect Engn Key Lab Virtual Real Technol & Syst Beijing 100083 Peoples R China

Foundation models are used to train a broad system of general data to build adaptations to new bottlenecks. Typically, they contain hundreds of billions of hyperparameters that have been trained with hundreds of gigabytes of data. However, this type of black-box vulnerability places foundation models at risk of data poisoning attacks that are designed to pass on misinformation or purposely introduce machine bias. Moreover, ordinary researchers have not been able to completely participate due to the rise in deployment standards. This study introduces the theoretical framework of scenarios engineering (SE) for building accessible and reliable foundation models in metaverse, namely, "SE-enabled foundation models in metaverse." Particularly, the research framework comprises a six-layer architecture (infrastructure layer, operation layer, knowledge layer, intelligence layer, management layer, and interaction layer), which can provide controllability, trustworthiness, and interactivity for the foundation models in metaverse. This creates closed-loop, virtual-real, and human-machine environments that provides the best indices and goals for the foundation models, which allows us to fully validate and calibrate the corresponding models. Then, examples of use cases from the automotive industry are listed to provide transparency on the possible use and benefits of our approach. Finally, the open research topics of related frameworks are discussed.

关键词： Foundation models knowledge automation management metaverse parallel intelligence scenarios engineering (SE)

来源：评论

学校读者我要写书评

暂无评论

MixGradient: A gradient-based re-weighting scheme with mixup for imbalanced data streams

引用

NEURAL NETWORKS 2023年第1期161卷 525-534页

作者： Peng, Xinyu Wang, Fei-Yue Li, Li Tsinghua Univ Dept Automat Beijing 100084 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100080 Peoples R China Tsinghua Univ Natl Lab Informat Sci & Technol Beijing 100084 Peoples R China

A challenge for contemporary deep neural networks in real-world problems is learning from an imbalanced data stream, where data tends to be received chunk by chunk over time, and the prior class distribution is severely imbalanced. Although many sophisticated algorithms have been derived, most of them overlook the importance of gradient information. From this perspective, the difficulty of learning from imbalanced data streams lies in the fact that the gradient estimated on an uneven class distribution is not informative enough to reflect the critical pattern of each class. To this end, we propose to assign higher weights on the training samples whose gradients are close to the gradient of corresponding typical samples, thus highlighting the important samples in minority classes and suppressing the noisy samples in majority classes. Such an idea can be combined with Mixup, which exploits the interpolation information of data to further compensate for the information of sample space that the typical samples do not provide and expand the role of the proposed re -weighting scheme. Experiments on artificially induced long-tailed CIFAR data streams and long-tailed MiniPlaces data stream show that the resulting method, termed MixGradient, boosts the generalization performance of DNNs under different imbalance ratios and achieves up to 10% accuracy improvement.(c) 2023 Elsevier Ltd. All rights reserved.

关键词： Deep learning Imbalanced data streams Sample gradient Typical samples Mixup

来源：评论

学校读者我要写书评

暂无评论

Crowdsensing Intelligence: Advancing Trustworthy, Intelligent, Interactive, and Cooperative Sensing and Computing for Transportation 5.0

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第8期8卷 3963-3967页

作者： Wang, Fei-Yue Chen, Bin Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Natl Univ Def Technol Coll Syst Engn Changsha 410073 Peoples R China

Dear All,

关键词： Transportation Simultaneous localization and mapping Object detection Laser radar Estimation Crowdsensing Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Dynamic Rigid Bodies Mining and Motion Estimation Based on Monocular Camera

引用

IEEE TRANSACTIONS ON CYBERNETICS 2023年第9期53卷 5655-5666页

作者： Gao, Xuanchang Liu, Xilong Cao, Zhiqiang Tan, Min Yu, Junzhi Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Peking Univ Coll Engn BIC ESAT Dept Adv Mfg & RobotState Key Lab Turbulence & C Beijing 100871 Peoples R China

Dynamic object perception is an important yet challenging direction in the field of robot navigation. Without any prior knowledge about motion and objects, a novel dynamic rigid bodies mining and motion estimation method based on monocular camera is proposed in this article. Different from the existing works based on sampling that associate feature points to motion hypotheses according to the reprojection errors, our work endeavors to find the intrinsic relevance among motion hypotheses. To represent this relevance, the concept of the probabilistic field on the Lie group Sim(3) manifold is introduced, which is established using random sampling. It provides a computable way for the regions on the manifold where rigid bodies possibly appear. The probability of a motion hypothesis falling on a region is expressed by its confidence. The regions with large confidences in the probabilistic field are selected as potential rigid bodies, whose corresponding feature points are further sampled for pose calculation. As a result, the randomness of sampling is reduced and the inliers for possible rigid bodies are enhanced, which guarantees the accuracy of motion estimation. On this basis, the tracking of rigid bodies is achieved. The proposed method distinguishes the feature points of dynamic objects with 3-D motion from those in the static background, thus enabling simultaneous localization and mapping (SLAM) to be initialized in dynamic environments. The experimental results on the KITTI, Hopkins 155, and MTPV62 datasets demonstrate the effectiveness. Comparison experiments indicate that our method outperforms the other methods in sensitivity of dynamic objects perception.

关键词： Dynamics Motion segmentation Cameras Manifolds Estimation Motion estimation Simultaneous localization and mapping Dynamic rigid bodies monocular camera motion estimation probabilistic field region confidence

来源：评论

学校读者我要写书评

暂无评论

Towards Human-Machine Recognition Alignment: An Adversarilly Robust Multimodal Retrieval Hashing Framework

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL systemS 2023年第5期10卷 2847-2859页

作者： Zhang, Xingwei Zheng, Xiaolong Liu, Bin Wang, Xiao Mao, Wenji Zeng, Daniel Dajun Wang, Fei-Yue Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 101408 Peoples R China West Virginia Univ Dept Management Informat Syst Morgantown WV 26506 USA

The multimodality nature of web data has necessitated complex multimodal information retrieval for a wide range of web applications. Deep neural networks (DNNs) have been widely employed to extract semantic features from raw samples to improve retrieval accuracy. In addition, hashing is widely used to improve computational and storage efficiency. As such, deep hashing frameworks have been applied for multimodal retrieval tasks. However, there is still a great recognitive gap between primate brain structure-inspired DNNs and humans. On computer vision tasks, well-crafted DNN models can be easily defeated by invisible small attacks, and this phenomenon indicates a large recognition gap between DNN models and humans. Recently, adversarial defense methods have been shown to improve the human-machine recognition alignment in several classification tasks. However, the robustness problem on the retrieval tasks, especially on the deep hashing-based multimodal retrieval models, is still not well studied. Therefore, in this article, we present an adversarially robust training mechanism to improve model robustness for the purpose of human-machine recognition alignment on retrieval tasks. Through extensive experimental results on several social multimodal retrieval benchmarks, we show that the robust training hashing framework proposed can mitigate the recognition gap on retrieval tasks. Our study highlights the necessity of robustness enhancement on deep hashing models.

关键词： Training Task analysis Semantics Perturbation methods Feature extraction Computational modeling Robustness Adversarial perturbation adversarially robust training deep hashing multimodal retrieval

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Stock Volatility Spillovers in Chinese Financial and Economic Sectors

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL systemS 2023年第1期10卷 269-284页

作者： Li, Jingyu Cheng, Lu Zheng, Xiaolong Wang, Fei-Yue Beijing Univ Technol Sch Econ & Management Beijing 100124 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100190 Peoples R China

By regarding the Chinese financial and economic sectors as a system, this article studies the stock volatility spillover in the system and explores its effects on the overall performance of the macroeconomy in China. The recent outbreak of COVID-19, U.S.-China trade friction, and three historical financial turbulences are involved to distinguish the changes in the spillover in these distinct crises, which has seldom been unveiled in the literature. By considering that the stock volatility spillover may vary over distinct timescales, the spillovers are disclosed through innovatively constructing the multi-scale spillover networks, followed by connectedness computation, based on variational mode decomposition (VMD) and generalized vector autoregression (GVAR) process. Our empirical analysis first demonstrates the different levels of increases in the total sectoral volatility spillover and changes in the roles of the sectors in the system under the aforementioned crises. Besides, the increases in the sectoral spillover in the long-term are verified to negatively impact the macroeconomy and can thereby act as warning signals.

关键词： COVID-19 financial and economic system network analysis stock volatility spillover variational mode decomposition (VMD)

来源：评论

学校读者我要写书评

暂无评论

Building intelligence identification system via large language model watermarking: a survey and beyond

引用

ARTIFICIAL INTELLIGENCE REVIEW 2025年第8期58卷 1-58页

作者： Wang, Xuhong Jiang, Haoyu Yu, Yi Yu, Jingru Lin, Yilun Yi, Ping Wang, Yingchun Qiao, Yu Li, Li Wang, Fei-Yue Shanghai Artificial Intelligence Lab Shanghai 200433 Peoples R China Shanghai Jiao Tong Univ Sch Cyber Sci & Engn Shanghai 200240 Peoples R China Tsinghua Univ Dept Automat BNRist Beijing 100084 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Large Language Models (LLMs) are increasingly integrated into diverse industries, posing substantial security risks due to unauthorized replication and misuse. To mitigate these concerns, robust identification mechanisms are widely acknowledged as an effective strategy. Identification systems for LLMs now rely heavily on watermarking technology to manage and protect intellectual property and ensure data security. However, previous studies have primarily concentrated on the basic principles of algorithms and lacked a comprehensive analysis of watermarking theory and practice from the perspective of intelligent identification. To bridge this gap, firstly, we explore how a robust identity recognition system can be effectively implemented and managed within LLMs by various participants using watermarking technology. Secondly, we propose a mathematical framework based on mutual information theory, which systematizes the identification process to achieve more precise and customized watermarking. Additionally, we present a comprehensive evaluation of performance metrics for LLM watermarking, reflecting participant preferences and advancing discussions on its identification applications. Lastly, we outline the existing challenges in current watermarking technologies and theoretical frameworks, and provide directional guidance to address these challenges. Our systematic classification and detailed exposition aim to enhance the comparison and evaluation of various methods, fostering further research and development toward a transparent, secure, and equitable LLM ecosystem.

关键词： Large language models Natural language processing Watermarking Identity recognition

来源：评论

学校读者我要写书评

暂无评论

Crowd Evacuation With Multi-Modal Cooperative Guidance in Subway Stations: Computational Experiments and Optimization

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL systemS 2023年第5期10卷 2536-2545页

作者： Zhou, Min Dong, Hairong Ioannou, Petros A. Wang, Fei-Yue Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing 100044 Peoples R China Univ Southern Calif Dept Elect Engn Los Angeles CA 90089 USA Univ Southern Calif Ctr Adv Transportat Technol Los Angeles CA 90089 USA Chinese Acad Sci CASIA State Key Lab Management & Control Complex Syst S Inst Automat Beijing 100190 Peoples R China

Setting up guidance equipment and leaders is widely used as an effective measure to improve the operation and evacuation efficiency of subway stations for the safety of passengers. Cooperation among different kinds of guidance modals can benefit the passenger evacuation process and reduce the operating and management costs as well as the risk of injury to people in subway stations. This article proposes a framework of multimodal cooperative guidance (MMCG) systems for commanding the crowd evacuation in case of emergency, where three types of guidance modes are considered. The bi-level MMCG optimization models are constructed to determine the optimal quantities and initial locations of multimodal guidance. The MMCG schemes are designed by minimizing cost functions taking into account the constraints of the number of guidance, valid coverage, and guiding expectation. An extended social force (SF) model is proposed to study crowd evacuation dynamics with multimodal guidance. The computational experiments are conducted to evaluate the performance of the proposed cooperative guidance schemes at the subway platform scenario. Three unimodal guidance schemes and a contrasted scheme without guidance are also proposed as comparison schemes. The results show that the crowd evacuation efficiency and the utilization ratio of exits are improved by taking into account the cooperation among different guidance modals.

关键词： Public transportation Computational modeling Behavioral sciences Force Broadcasting Rails Rail transportation Computational experiment crowd evacuation efficiency multimodal cooperative guidance (MMCG) safety social force (SF) model subway station

来源：评论

学校读者我要写书评

暂无评论

Implementation of Autonomous Docking and Charging for a Supporting Robotic Fish

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2023年第7期70卷 7023-7031页

作者： Dong, Huijie Wu, Zhengxing Wang, Jian Chen, Di Tan, Min Yu, Junzhi Taiyuan Univ Technol Key Lab Adv Transducers & Intelligent Control Sys Minist Educ Taiyuan 030024 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Peking Univ Coll Engn Dept Adv Mfg & Robot State Key Lab Turbulence & Complex Syst Beijing 100871 Peoples R China Guangdong Ocean Univ Coll Elect & Informat Engn Zhanjiang 524088 Peoples R China

Underwater energy supplements for autonom- ous underwater vehicles (AUVs) are significant for ocean exploitation owing to energy storage and data communication limitations. Aiming at the energy supplement for bionic robotic fish, an autonomous recharging-oriented docking approach is proposed in this article. First, an omnidirectional docking system containing a supporting robotic fish capable of visual recognition and wireless charging and a docking platform is presented. Next, five locomotive modes are designed and analyzed based on the hybrid swimming and gliding patterns for the robot fish. Utilizing the five modes, a docking procedure is planned, and an onboard-visual-based autonomous docking control strategy is presented. Aquatic experiments, including docking with the platform and refloating a small robot, are performed to verify the effectiveness of the proposed approach. The obtained results offer valuable insights into the development of autonomous docking of bionic robots, laying a solid foundation for the permanent operation of various underwater devices and robots.

关键词： Robots Visualization Tail Shape Batteries Cameras Buoyancy Autonomous docking gliding robotic fish motion control underwater energy supplementation underwater robotics

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：