检索结果-南通市图书馆

VLCA: vision-language aligning model with cross-modal attention for bilingual remote sensing image captioning

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2023年第1期34卷 9-18页

作者： WEI Tingting yuan weilin LUO Junren ZHANG Wanpeng LU Lina College of Intelligence Science and Technology National University of Defense TechnologyChangsha 410073China

In the field of satellite imagery, remote sensing image captioning(RSIC) is a hot topic with the challenge of overfitting and difficulty of image and text alignment. To address these issues, this paper proposes a vision-language aligning paradigm for RSIC to jointly represent vision and language. First, a new RSIC dataset DIOR-Captions is built for augmenting object detection in optical remote(DIOR) sensing images dataset with manually annotated Chinese and English contents. Second, a Vision-Language aligning model with Cross-modal Attention(VLCA) is presented to generate accurate and abundant bilingual descriptions for remote sensing images. Third, a crossmodal learning network is introduced to address the problem of visual-lingual alignment. Notably, VLCA is also applied to end-toend Chinese captions generation by using the pre-training language model of Chinese. The experiments are carried out with various baselines to validate VLCA on the proposed dataset. The results demonstrate that the proposed algorithm is more descriptive and informative than existing algorithms in producing captions.

关键词： remote sensing image captioning(RSIC) vision-language representation remote sensing image caption dataset attention mechanism

3D Surface velocity retrieval of mountain glacier using an offset tracking technique applied to ascending and descending SAR constellation data:a case study of the Yiga Glacier

在线全文

学校读者我要写书评

暂无评论

International Journal of Digital Earth 2019年第6期12卷 614-624页

作者： Qun Wang Jinghui Fan Wei Zhou Liqiang Tong Zhaocheng Guo Guang Liu weilin yuan Joaquim Joao Sousa Zbigniew Perski School of Land Science and Technology China University of GeosciencesBeijingPeople’s Republic of China Division of Remote Sensing for Environment China Aero Geophysical Survey and Remote Sensing Center for Land and ResourcesBeijingPeople’s Republic of China Key Laboratory of Digital Earth Science Institute of Remote Sensing and Digital EarthChinese Academy of SciencesBeijingPeople’s Republic of China School of Sciences and Technology University of Trás-os-Montes e Alto DouroVila RealPortugal Centre for Robotics in Industry and Intelligent Systems INESC TECPortoPortugal Polish Geological Institute—National Research Institute CracowPoland

COSMO-SkyMed is a constellation of four X-band high-resolution radar satellites with a minimum revisit period of 12 *** satellites can obtain ascending and descending synthetic aperture radar(SAR)images with very similar periods for use in the three-dimensional(3D)inversion of glacier *** this paper,based on ascending and descending COSMO-SkyMed data acquired at nearly the same time,the surface velocity of the Yiga Glacier,located in the Jiali County,Tibet,China,is estimated in four directions using an offset tracking technique during the periods of 16 January to 3 February 2017 and 1 February to 19 February *** the geometrical relationships between the measurements and the SAR images,the least square method is used to retrieve the 3D components of the glacier surface velocity in the eastward,northward and upward *** results show that applying the offset tracking technique to COSMO-SkyMed images can be used to derive the true 3D velocity of a glacier’s *** the two periods,the Yiga Glacier had a stable velocity,and the maximum surface velocity,2.4 m/d,was observed in the middle portion of the glacier,which corresponds to the location of the steepest slope.

关键词： Mountain glacier inversion of 3D movement offset tracking SAR constellation data

Transformer in reinforcement learning for decision-making:a survey

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2024年第6期25卷 763-790页

作者： weilin yuan Jiaxing CHEN Shaofei CHEN Dawei FENG Zhenzhen HU Peng LI Weiwei ZHAO College of Information and Communication National University of Defense TechnologyWuhan 430014China College of Intelligence Science and Technology National University of Defense TechnologyChangsha 410072China Laboratory for Parallel and Distributed Processing National University of Defense TechnologyChangsha 410072China

Reinforcement learning(RL)has become a dominant decision-making paradigm and has achieved notable success in many real-world ***,deep neural networks play a crucial role in unlocking RL’s potential in large-scale decision-making *** by current major success of Transformer in natural language processing and computer vision,numerous bottlenecks have been overcome by combining Transformer with RL for *** paper presents a multiangle systematic survey of various Transformer-based RL(TransRL)models applied in decision-making tasks,including basic models,advanced algorithms,representative implementation instances,typical applications,and known *** work aims to provide insights into problems that inherently arise with the current RL approaches,and examines how we can address them with better TransRL *** our knowledge,we are the first to present a comprehensive review of the recent Transformer research developments in RL for *** hope that this survey provides a comprehensive review of TransRL models and inspires the RL community in its pursuit of future *** keep track of the rapid TransRL developments in the decision-making domains,we summarize the latest papers and their open-source implementations at https://***/williamyuanv0/Transformer-in-Reinforcement-Learning-for-Decision-Making-A-Survey.

关键词： Transformer Reinforcement learning(RL) Decision-making(DM) Deep neural network(DNN) Multi-agent reinforcement learning(MARL) Meta-reinforcement learning(Meta-RL)

Research on Algorithm for Dynamic Weapon Target Assignment Based on the Improved Markov Decision Model

在线全文

学校读者我要写书评

暂无评论

Research on Algorithm for Dynamic Weapon Target Assignment B...

Adult split liver transplantation to treat liver cancer: a single-center retrospective study

第37届中国控制会议

作者： Wei Duan weilin yuan Liang Pan College of Intelligence Science and Engineering National University of Defense Technology

In this paper,we propose a multi-stage Dynamic Weapon Target Assignment(DWTA) model to resolve the DWTA ***,we make some improvements on the Markov decision model for DWTA,so that it can be applied to the real air defense *** then,the improved Markov decision model is applied to each distribution stage in the DWTA ***,considering the dynamic stochastic antagonism characteristic of DWTA process,we introduce the concept of time window to describe the time constraints and deal with the stochastic events based on the theory of Random Service System(RSS).As a result,the multi-stage DWTA model is ***,we compare our algorithm with other two algorithms,and the experimental results show that our algorithm can achieve greater benefits than other algorithms under the same conditions,which shows the effectiveness of our algorithm.

关键词： Markov Decision Process Dynamic Weapon Target Assignment Random Service System Time Window

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

World Journal of Emergency Medicine 2025年第1期16卷 57-62页

作者： Qiang Sun Haoze Cao Xuesong Bai Xin Han Wanlu You Zhongquan Sun Yixin Zhang Xiaochang Wu Feng Fang Fan Wu Lianyue Yang Sheng Yan yuan Ding weilin Wang Department of Hepatobiliary Pancreatic Surgery the Second Affiliated Hospital of Zhejiang University School of MedicineHangzhou 310009China Department of Hepatobiliary Surgery Huzhou Central HospitalZhejiang University Huzhou HospitalHuzhou 313002China Department of General Surgery Xiangya HospitalCentral South UniversityChangsha 410008China

BACKGROUND: The increasing morbidity of liver cancer has led to a growing demand for transplantation. Split liver transplantation(SLT) is a promising way to ameliorate organ shortages. However, the safety and efficacy of SLT are still controversial. The aim of this study was to assess the clinical outcome of SLT in liver cancer patients at our center. METHODS: A total of 74 patients who received liver transplantation at a tertiary hospital from March 2019 to July 2023 were retrospectively studied, of whom 37 recipients underwent SLT and 37 recipients underwent whole-graft liver transplantation(WGLT). Clinical data were analyzed and compared between patients who underwent SLT and ***: SLT and WGLT were successfully performed, with no intraoperative transplantrelated mortality. Postoperatively, no significant differences in total bilirubin(TB, P=0.266), alanine transaminase(ALT, P=0.403) and aspartate transaminase(AST, P=0.160) levels within 30 d were detected between the two groups. The transplant-related mortality rates were 8.1% in the SLT group and 5.4% in the WGLT group within 30 d of surgery(P=1.000), and 10.8% and 8.1%, respectively, at 90 d after surgery(P=1.000). There were no significant differences in overall survival(OS) and progress-free survival(PFS) between the SLT and WGLT groups(P=0.910, P=0.190). CONCLUSION: Our results show that SLT does not imply additional risks in treating liver cancer compared with WGLT.

关键词： Adult Split liver transplantation Liver cancer Prognosis Retrospective

在线全文

学校读者我要写书评

暂无评论

面向多最优解组合优化问题的决策求解算法

国防科技大学学报 2022年第3期44卷 31-40页

作者：胡振震袁唯淋罗俊仁邹明我陈璟国防科技大学智能科学学院湖南长沙410073

针对具有固定物品总和、多最优解特征的组合优化问题,以固定总和实数子集问题和购买鸡翅问题为例,给出了这类多最优解组合优化问题的形式化表示。在分析枚举等经典算法基础上,提出了基于整数状态表示和实数状态表示的0-1决策递归搜索多... 详细信息

针对具有固定物品总和、多最优解特征的组合优化问题,以固定总和实数子集问题和购买鸡翅问题为例,给出了这类多最优解组合优化问题的形式化表示。在分析枚举等经典算法基础上,提出了基于整数状态表示和实数状态表示的0-1决策递归搜索多最优解动态规划算法。针对该算法在最优解数量较大时,时间复杂度趋向O(m^(n))的问题,提出了基于相同决策路径合并和基于0-x决策的两种改进算法。实验中两种改进算法的计算时间基本符合与O(nb+nm)的正比关系,表明对于这类多最优解组合优化问题具有良好的求解性能。

关键词：组合优化多最优解动态规划固定总和实数子集问题

Stabilities of delay stochastic McKean-Vlasov equations in the G-framework

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2025年第1期68卷 255-277页

作者： Haiyan yuan Quanxin ZHU Department of Mathematics Heilongjiang Institute of Technology Key Laboratory of Computing and Stochastic Mathematics (Ministry of Education) School of Mathematics and Statistics Hunan Normal University

This article focuses on a type of stochastic Mc Kean-Vlasov equation in the G-framework(G-SMVE) and addresses the stability issue for delay stochastic Mc Kean-Vlasov equations in the G-framework(G-SMVDEs). Distribution dependence and uncertainty prevent us from directly applying the stochastic analysis method for stochastic Mc Kean-Vlasov equations(SMVEs)to G-SMVEs directly. To overcome this difficulty, we introduce definitions, including the derivative of a function with a law under the G-expectation and the Lions derivatives. Then we construct a new G-It? formula for G-SMVEs according to the G-It? formula for stochastic differential equations in the G-framework(G-SDEs) and the It? formula for SMVEs. Using the new G-It? formula and the Lyapunov functional method, we investigate the moment exponential stability and almost sure asymptotic stability of G-SMVDEs. To overcome the difficulty in obtaining the distribution dependence of the exact solution to the G-SMVDE, we introduce the empirical measure and the corresponding interacting particle system, and then prove the stability equivalence between the underlying G-SMVDE and the corresponding interacting particle system. Two examples are used to confirm our theoretical results.

关键词： delay stochastic McKean-Vlasov equations Wasserstein distance G-Brownian motion Lions derivative stability

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

多智能体博弈学习研究进展

系统工程与电子技术 2024年第5期46卷 1628-1655页

作者：罗俊仁张万鹏苏炯铭袁唯淋陈璟国防科技大学智能科学学院湖南长沙410073

随着深度学习和强化学习而来的人工智能新浪潮,为智能体从感知输入到行动决策输出提供了“端到端”解决方案。多智能体学习是研究智能博弈对抗的前沿课题,面临着对抗性环境、非平稳对手、不完全信息和不确定行动等诸多难题与挑战。本文... 详细信息

随着深度学习和强化学习而来的人工智能新浪潮,为智能体从感知输入到行动决策输出提供了“端到端”解决方案。多智能体学习是研究智能博弈对抗的前沿课题,面临着对抗性环境、非平稳对手、不完全信息和不确定行动等诸多难题与挑战。本文从博弈论视角入手,首先给出了多智能体学习系统组成,进行了多智能体学习概述,简要介绍了各类多智能体学习研究方法。其次,围绕多智能体博弈学习框架,介绍了多智能体博弈基础模型及元博弈模型,均衡解概念和博弈动力学,学习目标多样、环境(对手)非平稳、均衡难解且易变等挑战。再次,全面梳理了多智能体博弈策略学习方法,离线博弈策略学习方法,在线博弈策略学习方法。最后,从智能体认知行为建模与协同、通用博弈策略学习方法和分布式博弈策略学习框架共3个方面探讨了多智能体学习的前沿研究方向。

关键词：博弈学习多智能体学习元博弈在线无悔学习

维普期刊数据库博看期刊

Numerical simulation of microstructure and microporosity morphology in directional solidification of aluminum-copper alloys:Effect of copper content and withdrawal rate

在线全文

学校读者我要写书评

暂无评论

China Foundry 2025年第1期22卷 33-44页

作者： Wei yuan Hai-dong Zhao Xu Shen Chun Zou yuan Liu Qing-yan Xu National Engineering Research Center of Near-Net-Shape Forming for Metallic Materials South China University of TechnologyGuangzhou 510640China Key Laboratory for Advanced Materials Processing Technology(Ministry of Education) Tsinghua UniversityBeijing 100084China

Microporosity formed in the solidification process of Al alloys is detrimental to the alloy properties.A two-dimensional cellular automaton(CA)model was developed to simulate the microstructure and microporosity formation in Al-Cu alloys,considering variations in Cu content and solidification *** results indicate that the Cu content primarily influences the growth of *** validate the model,directional solidification experiments were conducted on Al-Cu alloys with varing Cu contents and withdrawal *** experimental results of dendrites and microporosity characteristics agree well with the predictions from the developed model,thus confirming the validity of the *** alloy’s liquidus temperature,dendrite morphology,and hydrogen saturation solubility arising from different Cu contents have significant effects on microporosity *** withdrawal rate primarily affects the nucleation of hydrogen microporosity by altering cooling rates and dendritic growth rates,resulting in different microporosity characteristics.

关键词： microporosity dendrites cellular automaton Al-Cu alloys directional solidification