检索结果-内蒙古大学图书馆

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Muhammad Faraz Karim Yunjie Deng Luyao Niu Bhaskar Ramasubramanian Michail Alexiou Dinuka Sahabandu Radha Poovendran Sukarno Mertoguno Georgia Institute of Technology Atlanta GA USA Department of Electrical and Computer Engineering Network Security Lab University of Washington Seattle WA USA Electrical and Computer Engineering Western Washington University Bellingham WA USA Kennesaw State University Marietta GA USA

ISBN: (数字)9798331527235

ISBN: (纸本)9798331527242

Reinforcement learning (RL) is a well-studied framework to solve complex decision-making problems in unknown environments. The actor-critic model in RL facilitates autonomy transfer by allowing agents to iteratively update their policies using ongoing dynamic evaluations of value functions via a critic. In this paper, we examine the impact of using different pretrained critics on the performance of actor-critic algorithms. First, in any single given environment, we show that a pretrained critic can be effective in reducing the duration of an initial training phase, thereby accelerating convergence by a factor of up to 2×. In this setting, we identify the critical range of the number of episodes for which a critic will need to be trained in order for it to be an effective pretrained critic. Second, we show that a critic trained in one environment enables transfer of autonomy by aiding learning of behaviors in a different, yet related environment. We carry out extensive experiments on a bipedal locomotion task in the MuJoCo physics engine to verify our hypotheses. Our results in this paper mark the first step towards demonstrating the role and impact of pretrained critics to achieve rapid autonomy transfer for complex reinforcement learning tasks while minimizing costs associated with retraining in new environments.

关键词： Training Legged locomotion Decision making Reinforcement learning Learning (artificial intelligence) Information processing Stairs Robots Physics Optimization

来源：评论

学校读者我要写书评

暂无评论

MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading

arXiv

引用

arXiv 2024年

作者： Zhang, Wenhao Wang, Jun Luo, Yong Yu, Lei Yu, Wei He, Zheng Shen, Jialie School of Computer Science National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China School of Electronics and Information Wuhan University China Department of Computer Science City University of London United Kingdom

Lip-reading is to utilize the visual information of the speaker’s lip movements to recognize words and sentences. Existing event-based lip-reading solutions integrate different frame rate branches to learn spatio-temporal features of varying granularities. However, aggregating events into event frames inevitably leads to the loss of fine-grained temporal information within frames. To remedy this drawback, we propose a novel framework termed Multi-view Temporal Granularity aligned Aggregation (MTGA). Specifically, we first present a novel event representation method, namely time-segmented voxel graph list, where the most significant local voxels are temporally connected into a graph list. Then we design a spatio-temporal fusion module based on temporal granularity alignment, where the global spatial features extracted from event frames, together with the local relative spatial and temporal features contained in voxel graph list are effectively aligned and integrated. Finally, we design a temporal aggregation module that incorporates positional encoding, which enables the capture of local absolute spatial and global temporal information. Experiments demonstrate that our method outperforms both the event-based and video-based lip-reading counterparts. Copyright © 2024, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Towards Cost-Optimal Policies for DAGs to Utilize IaaS Clouds with Online Learning

引用

IEEE Transactions on Services Computing 2025年

作者： Wu, Xiaohu Yu, Han Casale, Giuliano Gao, Guanyu Beijing University of Posts and Telecommunications National Engineering Research Center of Mobile Network Technologies Beijing China Nanyang Technological University WeBank-NTU Joint Research Centre on Fintech Singapore Singapore Nanyang Technological University School of Computer Science and Engineering Singapore Singapore Imperial College London Department of Computing London United Kingdom Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

Premier cloud service providers (CSPs) offer on-demand and spot instances (i.e., virtual machines) with time-varying features in availability and price. While interacting with a CSP, what concerns users is the process of cost-effectively utilizing these instances, possibly in addition to self-owned instances. A job in data-intensive applications is represented by a directed acyclic graph (DAG) whose nodes represent tasks and the DAG can further be transformed into a chain of tasks. The key to achieving cost efficiency is determining the allocation of a specific deadline to each task, as well as the allocation of different types of instances to the task. In this paper, we make some mild assumptions on the usage of various instances and give an analytical understanding of the expected behaviors while utilizing instances. Based on this, we propose informed heuristic policies to determine the allocation of deadlines and instances. The policies are parametric to support the usage of online learning to infer the optimal values against the dynamics of cloud markets. Finally, intuitive greedy policies are used as baselines to validate the effectiveness of the proposed analytical solutions. The cost improvement is up to 23.58% when spot and on-demand instances are considered and up to 50.08% when self-owned instances are also considered. © 2008-2012 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Delay-Optimal and Incentive-Aware Computation Offloading for Reconfigurable Intelligent Surface-Assisted Mobile Edge Computing

IEEE Networking Letters

引用

IEEE networking Letters 2022年第3期4卷 127-131页

作者： Kumar, Vikas Mukherjee, Mithun Lloret, Jaime Zhang, Qi Kumari, Mamta Bharat Sanchar Nigam Ltd. Network and Co-ordination Section Patna800001 India Nanjing University of Information Science and Technology School of Artificial Intelligence Nanjing210044 China Instituto de Investigacion Para la Gestion Integrada de Zonas Costears Universitat Politecnica de Valencia Valencia46022 Spain Aarhus University Department of Electrical and Computer Engineering Digit Aarhus8000 Denmark Ramchandra Chandravansi Institute of Technology Department of Computer Science and Engineering Bishrampur822124 India

To take the advantage of computing resource of edge server, the end-users must pay the service charge for task processing. However, the transmission delay plays an important role in communication-computation of edge computing. To address this, we aim to leverage reconfigurable intelligent surface (RIS) in mobile edge computing (MEC). In this letter, we propose an offloading policy to maximize the revenue of edge server while satisfying the end-user's goal of minimizing both the latency and cost based on the price by edge server. We provide an insight on required computing resources at the edge server for delay-sensitive task processing. © 2019 IEEE.

关键词： computation offloading

来源：评论

学校读者我要写书评

暂无评论

State Estimation of UAV under network Attack 2

State Estimation of UAV under Network Attack

引用

2nd International Conference on Algorithms, High Performance Computing and Artificial Intelligence, AHPCAI 2022

作者： Liu, Xiaoqi Zhu, Jiangning Liu, Qingquan College of Equipment Engineering Shenyang Ligong University Shenyang China Chaoyang Teachers College Department of Mathematics and Computer Chaoyang China Fujian Zhongrui Network Co. LTD Fuzhou350015 China

ISBN: (纸本)9798350334784

When the sensors of UAVs send back their state information, they may be attacked by the network, resulting in a large gap between the state information sent back by the sensors and the actual state information. This paper studies the state estimation of UAVs under network attack. First of all, the state equation of the sensor of the UAV is established when it is attacked by the network and interfered with by the input after sending the state information. Secondly, the judgment conditions of UAVs being attacked by networks are analyzed. Then, the model of UAV state estimation is established under the condition that network attack and interference exist simultaneously. Finally, the algorithm of UAV state estimation is designed. The rationality of the algorithm is verified by comparing the state estimation value with the state data of the UAV with and without a network attack. © 2022 IEEE.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning based Joint Spectrum Allocation and Configuration Design for STAR-RIS-Assisted V2X Communications

arXiv

引用

arXiv 2023年

作者： Aung, Pyae Sone Nguyen, Loc X. Tun, Yan Kyaw Han, Zhu Hong, Choong Seon The Department of Computer Science and Engineering Kyung Hee University Gyeonggi-do Yongin-si17104 Korea Republic of Division of Network and Systems Engineering School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Brinellvägen 8 Stockholm114 28 Sweden The Electrical and Computer Engineering Department University of Houston HoustonTX77004 United States

Vehicle-to-Everything (V2X) communications play a crucial role in ensuring safe and efficient modern transportation systems. However, challenges arise in scenarios with buildings, leading to signal obstruction and coverage limitations. To alleviate these challenges, reconfigurable intelligent surface (RIS) is regarded as an effective solution for communication performance by tuning passive signal reflection. RIS has acquired prominence in 6G networks due to its improved spectral efficiency, simple deployment, and cost-effectiveness. Nevertheless, conventional RIS solutions have coverage limitations. Therefore, researchers have started focusing on the promising concept of simultaneously transmitting and reflecting RIS (STAR-RIS), which provides 360°coverage while utilizing the advantages of RIS technology. In this paper, a STAR-RIS-assisted V2X communication system is investigated. An optimization problem is formulated to maximize the achievable data rate for vehicle-to-infrastructure (V2I) users while satisfying the latency and reliability requirements of vehicle-to-vehicle (V2V) pairs by jointly optimizing the spectrum allocation, amplitudes, and phase shifts of STAR-RIS elements, digital beamforming vectors for V2I links, and transmit power for V2V pairs. Since it is challenging to solve in polynomial time, we decompose our problem into two sub-problems. For the first sub-problem, we model the control variables as a Markov Decision Process (MDP) and propose a combined double deep Q-network (DDQN) with an attention mechanism so that the model can potentially focus on relevant inputs. For the latter, a standard optimization-based approach is implemented to provide a real-time solution, reducing computational costs. Extensive numerical analysis is developed to demonstrate the superiority of our proposed algorithm compared to benchmark schemes. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Computing Palindromes on a Trie in Linear Time 33

Computing Palindromes on a Trie in Linear Time

引用

33rd International Symposium on Algorithms and Computation, ISAAC 2022

作者： Mieno, Takuya Funakoshi, Mitsuru Inenaga, Shunsuke Department of Computer and Network Engineering University of Electro-Communications Tokyo Japan Department of Informatics Kyushu University Fukuoka Japan Japan Society for the Promotion of Science Tokyo Japan PRESTO Japan Science and Technology Agency Tokyo Japan

ISBN: (纸本)9783959772587

A trie T is a rooted tree such that each edge is labeled by a single character from the alphabet, and the labels of out-going edges from the same node are mutually distinct. Given a trie T with n edges, we show how to compute all distinct palindromes and all maximal palindromes on T in O(n) time, in the case of integer alphabets of size polynomial in n. This improves the state-of-the-art O(n log h)-time algorithms by Funakoshi et al. [PSC 2019], where h is the height of T . Using our new algorithms, the eertree with suffix links for a given trie T can readily be obtained in O(n) time. Further, our trie-based O(n)-space data structure allows us to report all distinct palindromes and maximal palindromes in a query string represented in the trie T , in output optimal time. This is an improvement over an existing (naïve) solution that precomputes and stores all distinct palindromes and maximal palindromes for each and every string in the trie T separately, using a total O(n2) preprocessing time and space, and reports them in output optimal time upon query. © Takuya Mieno, Mitsuru Funakoshi, and Shunsuke Inenaga.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

Continual Reinforcement Learning for Digital Twin Synchronization Optimization

引用

IEEE Transactions on Mobile Computing 2025年

作者： Tong, Haonan Chen, Mingzhe Zhao, Jun Hu, Ye Yang, Zhaohui Liu, Yuchen Yin, Changchuan Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence Beijing Advanced Information Network Laboratory Beijing China College of Computing and Data Science Singapore University of Miami Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing Coral Gables33146 United States University of Miami Department of Industrial and Systems Engineering Coral Gables33146 United States Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China North Carolina State University Department of Computer Science RaleighNC27695 United States Beijing Key Laboratory of Network System Architecture and Convergence China Beijing University of Posts and Telecommunications Beijing Advanced Information Network Laboratory Beijing100876 China

This article investigates the adaptive resource allocation scheme for digital twin (DT) synchronization optimization over dynamic wireless networks. In our considered model, a base station (BS) continuously collects factory physical object state data from wireless devices to build a real-time virtual DT system for factory event analysis. Due to continuous data transmission, maintaining DT synchronization must use extensive wireless resources. To address this issue, a subset of devices is selected to transmit their sensing data, and resource block (RB) allocation is optimized. This problem is formulated as a constrained Markov process (CMDP) problem that minimizes the long-term mismatch between the physical and virtual systems. To solve this CMDP, we first transform the problem into a dual problem that refines RB constraint impacts on device scheduling strategies. We then propose a continual reinforcement learning (CRL) algorithm to solve the dual problem. The CRL algorithm learns a stable policy across historical experiences for quick adaptation to dynamics in physical states and network capacity. Simulation results show that the CRL can adapt quickly to network capacity changes and reduce normalized root mean square error (NRMSE) between physical and virtual states by up to 55.2%, using the same RB number as traditional methods. © 2025 IEEE. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Deep Reinforcement Learning-Based Cooperative Perception and Computation in VEC

引用

IEEE Internet of Things Journal 2025年第12期12卷 21350-21363页

作者： Zhao, Liang Li, Longjia Tan, Zhiyuan Hawbani, Ammar He, Qiang Liu, Zhi Shenyang Aerospace University School of Computer Science Shenyang110136 China Edinburgh Napier University School of Computing EdinburghEH10 5DT United Kingdom Northeastern University School of Medicine and Biological Information Engineering Shenyang110169 China The University of Electro-Communications Department of Computer and Network Engineering Tokyo Japan

Connected and autonomous vehicles (CAVs) are an important paradigm of intelligent transportation systems. Cooperative perception (CP) and vehicular edge computing (VEC) enhance CAVs' perception capacity of the region of interest (RoI) while alleviating the pressure of intensive computation on onboard resources. However, existing CP and computation schemes are based on inefficient broadcast communications and still face challenges such as highly dynamic communication link channel conditions caused by vehicle mobility, and limited computing resources in VEC environments. Considering the delay sensitivity of CAVs' perception tasks and the need for enhanced perception, we propose a unicast-based cooperative perception and computation scheme to achieve more efficient resource utilization and perception task execution in VEC scenarios. Our goal is to maximize CP gain and minimize task execution delay by optimizing the decision of each ego CAVs. To solve the sequential decision-making problem of multi-objective optimization, we propose a solution based on improved multi-agent proximal policy optimization deep reinforcement learning, where CAVs agents make adaptive decisions distributed based on partial observations. Simulation results show that compared with the baseline algorithm, our proposed scheme effectively reduces the execution delay of ego CAVs perception tasks and ensures a high perception gain. © 2025 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

The microscale organization of directed hypergraphs

arXiv

引用

arXiv 2024年

作者： Lotito, Quintino Francesco Vendramini, Alberto Montresor, Alberto Battiston, Federico Department of Information Engineering and Computer Science University of Trento via Sommarive 9 Trento38123 Italy Department of Network and Data Science Central European University Vienna1100 Austria

Many real-world complex systems are characterized by non-pairwise – higher-order – interactions among system’s units, and can be effectively modeled as hypergraphs. Directed hypergraphs distinguish between source and target sets within each hyperedge, and allow to account for the directional flow of information between nodes. Here, we provide a framework to characterize the structural organization of directed higher-order networks at their microscale. First, we extract the fingerprint of a directed hypergraph, capturing the frequency of hyperedges with a certain source and target sizes, and use this information to compute differences in higher-order connectivity patterns among real-world systems. Then, we formulate reciprocity in hypergraphs, including exact, strong, and weak definitions, to measure to which extent hyperedges are reciprocated. Finally, we extend motif analysis to identify recurring interaction patterns and extract the building blocks of directed hypergraphs. We validate our framework on empirical datasets, including Bitcoin transactions, metabolic networks, and citation data, revealing structural principles behind the organization of real-world systems. Copyright © 2024, The Authors. All rights reserved.

关键词： Large scale systems

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：