检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第8期5卷 3858-3871页

作者： Yang, Jing Lu, Ting Zhu, Youjie Hefei University of Technology Intelligent Interconnected Systems Laboratory of Anhui Province Hefei230009 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230009 China

Discovering causal relationships from a large amount of observational data is an important research direction in data mining. To address the challenges of discovering and constructing causal networks on nonlinear and high-dimensional data, this article proposes a new structural learning algorithm called spatial coordinates based (SCB). The SCB algorithm effectively discovers causal networks from large scale nonlinear data. In this article, we make three main contributions. Firstly, based on the Hilbert-Schmidt independence criterion (HSIC), we propose new independence test coefficients: spatial coordinate (SC) coefficient and conditional spatial coordinate (CSC) coefficient. We also prove that the statistical distribution of the CSC coefficient follows a standard normal distribution. Secondly, using the statistical distribution of the CSC coefficient, we redefine the correlation of variables and combine it with local learning to propose the SCB algorithm. Finally, we demonstrate the effectiveness of the algorithm through experiments on data generated from various nonlinear function dependencies. Compared to existing algorithms, the causal network models constructed using the SCB algorithm exhibit significant improvements in accuracy and time performance. The effectiveness of the proposed method is further validated on real power plant data. © 2020 IEEE.

关键词： Additive noise

来源：评论

学校读者我要写书评

暂无评论

Emergency multi-mode transportation path optimization based on modified customized non-dominated sorting genetic algorithmⅡ 8

Emergency multi-mode transportation path optimization based ...

引用

8th International Conference on Traffic engineering and Transportation System, ICTETS 2024

作者： Guo, Chunxian Lei, Hongtao Zhu, Cheng Zhang, Weiming National Key Laboratory of Information Systems and Engineering National University of Defense Technology Changsha China

ISBN: (数字)9781510686298

ISBN: (纸本)9781510686281

Based on multi-mode transportation, emergency supplies transportation with flexibility and robustness can effectively cope with various uncertain factors such as road congestion, enabling efficient and safe transportation of emergency supplies in complex conditions. This paper establishes an optimization model for emergency supplies multi-mode transportation routes with dual objectives of time and cost, and designs a Modified Customized Non-dominated Sorting Genetic Algorithm II (MCNSGA-II) for solving the optimization model. In the solution method, a feasible solution is constructed using an evolutionary solution framework and a two-stage encoding method. The Dijkstra algorithm is used to reconnect illegal paths, and a mutation strategy is introduced to escape from local optima. Through case analysis, MCNSGA-II can achieve better results compared to NSGA-II and SPEA-II algorithms. © 2024 SPIE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Multi-Intent Learning for Multi-Modal Recommendation 4

Multi-Intent Learning for Multi-Modal Recommendation

引用

4th International Conference on Electronic information engineering and Computer Communication, EIECC 2024

作者： Kong, Mengfan Luo, Aimin National University of Defense Technology National Key Laboratory of Information Systems Engineering Changsha China

ISBN: (纸本)9798331534622

Recommendation systems play an increasingly important role in social platforms, providing users with personalized content services. With the explosive growth of multi-modal contents, traditional recommendation systems based solely on interaction data can no longer meet user needs. In recent years, many researchers have attempted to integrate multi-modal features into recommendation system. Meanwhile, user intent determines whether users will interact with items or not. Intent modeling is crucial for capturing user preferences and explaining recommendation results. Recommendation system based on interaction data model user intents at a coarse-grained level, because the information contained in user IDs and item IDs is too limited. In contrast, multi-modal features can reflect finer-grained user preferences from a semantic perspective. To address this issue, we propose a Multi-Intent Learning method for Multi-Modal Recommendation (MIMM). Specifically, we design a Modality-Specific Intent Graph Convolution Network to disentangle user and item intents from different modalities and filter out self-supervision signals at the semantic level. Finally, a cross-modality intent contrastive learning task is introduced to align user intents across different modality. Experiments on real-world dataset demonstrate the effectiveness of our MIMM. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Time-tightly Coupled UAV Control Scheduling Scheme 9

A Time-tightly Coupled UAV Control Scheduling Scheme

引用

9th IEEE International Conference on Data Science in Cyberspace, DSC 2024

作者： Guo, Yuanyuan Zhu, Xianqiang Zhang, Qianzhen Liu, Bin National University of Defense Technology National Key Laboratory of Information Systems Engineering Changsha China

ISBN: (纸本)9798350391367

Aiming at the problem of unbalanced task scheduling and distribution of single-thread control task of control station under the background of multi-UAV collaboration, based on the planned UAV flight track and task execution time window, the whole UAV track is divided into two types of control periods: patrol time window and task execution time window, and a multi-objective optimization model with the minimum maximum task completion time, the minimum maximum load of the control station and the minimum load of the computer in the control station is constructed. By drawing a Gantt chart to visualize the allocation scheme of the simulation data set, the results show that the proposed algorithm can provide a more balanced effective control and scheduling scheme for UAV. © 2024 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

An AD-SPSO Algorithm for Solving the Measurement Resource Scheduling Problem with Satellite Cataloging Requirements

An AD-SPSO Algorithm for Solving the Measurement Resource Sc...

引用

2024 IEEE International Conference on Control Science and systems engineering, ICCSSE 2024

作者： Niu, Ge Jiao, Yuanyuan Pan, Xiaogang National University of Defense Technology National Key Laboratory of Information Systems Engineering Changsha China

ISBN: (纸本)9798331517199

Under the condition of limited ground measurement resources, the increasing scale of satellites brings more satellite cataloging requirements and aggravates the measured pressure. How to better utilize limited measurement resources is a crucial issue. In this paper, the measurement resource scheduling problem with satellite cataloging requirements is examined, a measurement resource scheduling model is established with the goal of maximizing profits from satellite cataloging task completion, and a switching particle swarm optimization algorithm based on adaptive large neighborhood search and dynamic neighborhood (AD-SPSO) is proposed. The AD-SPSO algorithm uses the time greedy strategy and chaos mapping to obtain an initial population with better quality. Then, the algorithm designs the dynamic neighborhood of the particle, after which the particle's velocity is updated by selecting the optimal position from the dynamic neighborhood of the particle, so as to enhance the inter-particle information interaction and utilize the population information. In addition, the AD-SPSO algorithm joins the adaptive large neighborhood search algorithm, which selects different particles for perturbation according to the population state. This effectively prevents its early convergence. To evaluate the performance of the AD-SPSO algorithm, this paper performs experiments in four scenarios, and in different scenarios, compared with other improved algorithms, the AD-SPSO algorithm can obtain higher and more stable overall profit for scheduling plans, which verifies its effectiveness in solving the measurement resource scheduling problem with satellite cataloging requirements. © 2024 IEEE.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Weapon Target Assignment Based on Deep Q-learning 9

Weapon Target Assignment Based on Deep Q-learning

引用

9th IEEE International Conference on Data Science in Cyberspace, DSC 2024

作者： Qin, Jianbo Wang, Yi Ding, Zhaoyun National University of Defense Technology National Key Laboratory of Information Systems Engineering ChangSha China

ISBN: (纸本)9798350391367

This paper introduces an innovative approach to addressing the Weapon Target Assignment (WTA) problem, utilizing the Deep Q-Learning (DQN) algorithm. The goal is to optimize the allocation between weapons and targets to achieve the most effective combat outcome. Initially proposed by Manne, the WTA problem is a multi-objective, multi-constraint NP-complete problem, the complexity of which increases with the number and variety of weapons and targets. The DQN model presented in this paper transforms the WTA problem into a reinforcement learning issue, effectively addressing the issues of low efficiency and the propensity to fall into local optima associated with traditional heuristic algorithms in large-scale scenarios. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Approach Based on Grey Wolf Optimizer for Path Planning in Searching Missing Submersibles 14

An Approach Based on Grey Wolf Optimizer for Path Planning i...

引用

14th International Conference on Logistics and systems engineering

作者： Zhang, Zhongyuan Yang, Zhenyu Ji, Xiaofeng Ren, Bangbang College of Systems Engineering National University of Defense Technology Hunan Changsha410073 China National Key Laboratory of Information Systems Engineering National University of Defense Technology China

ISBN: (纸本)9798331314347

In ocean search and rescue missions, how to efficiently locate missing submersibles is a challenging problem. The distribution of submersibles may remain relatively stable in some periods of time, but it may also show dynamic changes due to changes in environmental conditions such as terrain, density of seawater and ocean currents. Affected by factors such as minerals, the density of seawater generally increases linearly with the increase of depth. The partial derivative and gradient differential methods are used to simulate and analyze different terrain when it has great influence on submersible. The speed of ocean currents decreases with depth, and submarine currents are usually slow and steady. Ocean current data set is collected for data preprocessing. A large amount of real data is helpful to determine the direction and speed of ocean currents in each region quantitatively, and then analyze the motion trajectory of submersible, which proves the reliability of theory applied in practice. Considering the uncertainty of submersible position over time, this paper proposes a path planning method combining greedy algorithm and grey wolf optimization (GWO) algorithm together, and discusses the cooperative working mechanism of multiple searchers. The greedy algorithm is used to plan the path of a single search submersible, and the grey wolf optimization algorithm is introduced when considering the joint search of multiple search submersibles. Each step of greedy algorithm is to select the current optimal solution and build the overall path to the local optimal. Through programming, a route with a success rate of about 91% was obtained, and the shortest path was calculated to be about 50,155.69 meters. The GWO is solved by simulating the hunting behavior of wolves, combining the obstacle avoidance strategy of the submersible and the multi-agent cooperative method. When the search success rate remains above 90%, by applying GWO, the search efficiency is improved as the s

关键词： Seawater

来源：评论

学校读者我要写书评

暂无评论

The Journey/DAO/TAO of Embodied Intelligence: From Large Models to Foundation Intelligence and Parallel Intelligence

引用

IEEE/CAA Journal of Automatica Sinica 2024年第6期11卷 1313-1316页

作者： Tianyu Shen Jinlin Sun Shihan Kong Yutong Wang Juanjuan Li Xuan Li Fei-Yue Wang College of Information Science and Technology Beijing University of Chemical TechnologyBeijing 100029China School of Electrical and Information Engineering Jiangsu UniversityZhenjiang 212013China State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and RoboticsCollege of EngineeringPeking UniversityBeijing 100871China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Peng Cheng Laboratory Shenzhen 518000China State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190 Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China IEEE

THE tremendous impact of large models represented by ChatGPT[1]-[3]makes it necessary to con-sider the practical applications of such models[4].However,for an artificial intelligence(AI)to truly evolve,it needs to possess a physical“body”to transition from the virtual world to the real world and evolve through interaction with the real *** this context,“embodied intelligence”has sparked a new wave of research and technology,leading AI beyond the digital realm into a new paradigm that can actively act and perceive in a physical environment through tangible entities such as robots and automated devices[5].

关键词： Intelligence DAO TAO

来源：评论

学校读者我要写书评

暂无评论

Discriminative feature encoding for intrinsic image decomposition

引用

Computational Visual Media 2023年第3期9卷 597-618页

作者： Zongji Wang Yunfei Liu Feng Lu Key Laboratory of Network Information System Technology(NIST) Aerospace Information Research InstituteChinese Academy of SciencesBeijing 100190China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Peng Cheng Laboratory Shenzhen 518000China

Intrinsic image decomposition is an important and long-standing computer vision *** an input image,recovering the physical scene properties is *** physically motivated priors have been used to restrict the solution space of the optimization problem for intrinsic image *** work takes advantage of deep learning,and shows that it can solve this challenging computer vision problem with high *** focus lies in the feature encoding phase to extract discriminative features for different intrinsic layers from an input *** achieve this goal,we explore the distinctive characteristics of different intrinsic components in the high-dimensional feature embedding *** define feature distribution divergence to efficiently separate the feature vectors of different intrinsic *** feature distributions are also constrained to fit the real ones through a feature distribution *** addition,a data refinement approach is provided to remove data inconsistency from the Sintel dataset,making it more suitable for intrinsic image *** method is also extended to intrinsic video decomposition based on pixel-wise correspondences between adjacent *** results indicate that our proposed network structure can outperform the existing state-of-the-art.

关键词： intrinsic image decomposition deep learning feature distribution data refinement

来源：评论

学校读者我要写书评

暂无评论

Gauze:enabling communication-friendly block synchronization with cuckoo filter

引用

Frontiers of Computer Science 2023年第3期17卷 113-123页

作者： Xiaoqiang DING Liushun ZHAO Lailong LUO Junjie XIE Deke GUO Jinxi LI College of Intelligence and Computing Tianjin UniversityTianjin 300350China School of Computer Science and Technology Xidian UniversityXi’an 710071China Science and Technology on Information Systems Engineering Laboratory National University of Defense TechnologyChangsha 410073China Institute of Systems Engineering AMSPLABeijing 100141China

Block synchronization is an essential component of blockchain ***,blockchain systems tend to send all the transactions from one node to another for ***,such a method may lead to an extremely high network bandwidth overhead and significant transmission *** is crucial to speed up such a block synchronization process and save bandwidth consumption.A feasible solution is to reduce the amount of data transmission in the block synchronization process between any pair of ***,existing methods based on the Bloom filter or its variants still suffer from multiple roundtrips of communications and significant synchronization *** this paper,we propose a novel protocol named Gauze for fast block *** utilizes the Cuckoo filter(CF)to discern the transactions in the receiver’s mempool and the block to verify,providing an efficient solution to the problem of set reconciliation in the P2P(Peer-to-Peer Network)*** up to two rounds of exchanging and querying the CFs,the sending node can acknowledge whether the transactions in a block are contained by the receiver’s mempool or *** on this message,the sender only needs to transfer the missed transactions to the receiver,which speeds up the block synchronization and saves precious bandwidth *** evaluation results show that Gauze outperforms existing methods in terms of the average processing latency(about lower than Graphene)and the total synchronization space cost(about lower than Compact Blocks)in different scenarios.

关键词： block synchronization cuckoo filter probabilistic data structure

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：