检索结果-内蒙古大学图书馆

Parallel Seeds:From Foundation Models to Foundation Intelligence for Agricultural Sustainability

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 481-484页

作者： Laiyi Fu Shunkang Ling Danyang Wu Mengzhen Kang Fei-Yue Wang Hequan Sun the Shool of Automation Science and Engineering Faculty of Electronic and Information Engineering Xi'an Jiaotong University the College of Information Engineering Northwest A&F University IEEE the State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences

THE development of agriculture faces significant challenges due to population growth, climate change, land depletion, and environmental pollution, threatening global food security [1]. This necessitates the development of sustainable agriculture, where a fundamental step is crop breeding to improve agronomic or economic traits, e.g., increasing yields of crops while decreasing resource usage and minimizing pollution to the environment [2].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Knowledge As Not Only Justified True Beliefs in Vision

引用

IEEE/CAA Journal of Automatica Sinica 2025年第2期12卷 297-299页

作者： Wenbo Zheng Fei-Yue Wang IEEE School of Computer Science and Artificial Intelligence Wuhan University of Technology Sanya Science and Education Innovation Park of Wuhan University of Technology the State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences

COMPUTATIONAL knowledge vision [1] is emphasized as a novel perspective or field in this paper. It first proposes the visual hierarchy and its connection to knowledge, stating that knowledge is a justified true belief. To further the previous research, we concisely summarize our recent works and suggest a new direction that knowledge is also a thought framework in vision.

关键词： Computational modeling Visualization Artificial intelligence Data models Visual perception Visual databases Training data

来源：评论

学校读者我要写书评

暂无评论

Monitoring fossil fuel CO_(2) emissions from co-emitted NO_(2) observed from space:progress,challenges,and future perspectives

引用

Frontiers of Environmental Science & Engineering 2025年第1期19卷 23-45页

作者： Hui Li Jiaxin Qiu Kexin Zhang Bo Zheng Shenzhen Key Laboratory of Ecological Remediation and Carbon Sequestration Institute of Environment and EcologyTsinghua Shenzhen International Graduate SchoolTsinghua UniversityShenzhen 518055China State Environmental Protection Key Laboratory of Sources and Control of Air Pollution Complex Beijing 100084China

Developing an anthropogenic carbon dioxides(CO_(2))emissions monitoring and verification support(MVS)capacity is essential to support the Global Stocktake(GST)and ratchet up Nationally Determined Contributions(NDCs).The 2019 IPCC refinement proposes top-down inversed CO_(2)emissions,primarily from fossil fuel(FFCO_(2)),as a viable emission *** substantial progress in directly inferring FFCO_(2)emissions from CO_(2)observations,substantial challenges remain,particularly in distinguishing local CO_(2)enhancements from the high background due to the long atmospheric ***,using short-lived and co-emitted nitrogen dioxide(NO_(2))as a proxy in FFCO_(2)emission inversion has gained *** methodology is broadly categorized into plume-based and emission ratios(ERs)-based inversion *** the plume-based methods,NO_(2)observations act as locators,constraints,and validators for deciphering CO_(2)plumes downwind of sources,typically at point source and city *** ERs-based inversion approach typically consists of two steps:inferring NO_(2)-based nitrogen oxides(NO_(x))emissions and converting NO_(x)to CO_(2)emissions using CO_(2)-to-NO_(x)*** integrating NO_(2)observations into FFCO_(2)emission inversion offers advantages over the direct CO_(2)-based methods,uncertainties persist,including both structural and data-related *** these uncertainties is a primary focus for future research,which includes deploying nextgeneration satellites and developing advanced inversion ***,data caveats are necessary when releasing data to users to prevent potential *** NO_(2)-based CO_(2)emission inversion requires interdisciplinary collaboration across multiple communities of remote sensing,emission inventory,transport model improvement,and atmospheric inversion algorithm development.

关键词： Fossil fuel CO_(2) emissions CO_(2) satellites NO_(2) satellites Emission inversion methods Uncertainty management Future perspectives

来源：评论

学校读者我要写书评

暂无评论

Grand challenges of mitigating O3-related mortality in China by 2060

引用

Science Bulletin 2025年第9期70卷 1429-1431页

作者： Jiang, Yueqi Sun, Yisheng Li, Shengyue Yin, Dejia Dong, Zhaoxin Zheng, Haotian Zhao, Bin Wang, Shuxiao State Key Laboratory of Regional Environment and Sustainability School of Environment Tsinghua University Beijing100084 China Key Laboratory of Sources and Control of Air Pollution Complex Ministry of Ecology and Environment Beijing100084 China

来源：评论

学校读者我要写书评

暂无评论

A Stochastic Traffic Flow Model-Based Reinforcement Learning Framework For Advanced Traffic Signal control

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第1期26卷 714-723页

作者： Zhu, Yifan Lv, Yisheng Lin, Shu Xu, Jungang Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 101408 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

In addressing the complex challenge of Traffic Signal control (TSC), Deep Reinforcement Learning (DRL) has emerged as a popular solution. In traditional DRL methods applied to TSC problems, deep neural networks are sensitive to minor input changes, which complicates accurate predictions. This ambiguity hampers algorithm convergence, speed, and overall performance. Additionally, existing DRL methods for TSC employ high-dimensional state spaces, escalating computational complexity. This study addresses these challenges by introducing an innovative approach, SLFMLight, that integrates a stochastic traffic flow model with DRL algorithm for TSC. Our method employs an innovative network update algorithm that integrates traffic flow prediction in Q-value learning process to enhance interpretability and accelerate algorithm convergence. Utilizing mode-based multi-actor networks to handle diverse traffic conditions, SLFMLight excels in decision-making towards complex traffic scenarios, especially in congested ones. Concise state definition improves computational efficiency. SLFMLight contributes to the advancement of intelligent traffic management by providing an effective DRL solution that improves interpretability, efficiency, and adaptability in TSC.

关键词： Stochastic processes Prediction algorithms Green products Turning Convergence Vectors Computational modeling Artificial neural networks Signal to noise ratio Markov decision processes Traffic signal control traffic networks deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

The formation of public attitudes toward and acceptance of automated driving technology

引用

Transportation Research Part F: Traffic Psychology and Behaviour 2025年 113卷 344-356页

作者： Feng, Xue Qin, Chuanshen School of International and Public Affairs Shanghai Jiao Tong University China Key Laboratory of Urban Complex Risk Control and Resilience Governance Shanghai Emergency Management Shanghai Jiao Tong University China School of Emergency Management Shanghai Jiao Tong University China

As the market for Level 3 and Level 4 automated driving vehicles matures, public interest in this technology has increased. However, the risks and benefits associated with automated driving technology have resulted in varying public perceptions. This study aimed to determine the factors leading to the creation of attitude groups and their corresponding levels of automated driving technology acceptance. To this end, a survey questionnaire was conducted with 825 respondents in Shanghai, China's leading city for automated driving technology. The data were analyzed using cluster analysis and multinomial logistic regression. The findings showed that (1) in terms of attitudes toward automated driving technology, the following groups exist: positive (21.21%), negative (36.00%), and ambivalent (42.79%). (2) Ambivalent attitudes mainly result from higher levels of consideration of future consequences and lower self-efficacy levels. (3) While those in the negative group were hesitant to embrace any kind of automated driving technology, those in the ambivalent group were mainly reluctant to embrace Level 4 automated driving technology. (4) In terms of social trust, trust in the government improved acceptance of automated driving technology among the positive and negative groups, while trust in automated driving technology companies raised the acceptance levels of the ambivalent group. The study explores how the public weighs the risks and benefits of automated driving technology, identifies various attitudes toward it, and provides practical advice for communicating the risks of Level 3 and Level 4 automated driving technology. © 2025 Elsevier Ltd

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Nitrogen-removed organic matters from cyanobacterial decomposition promote the release of nitrogen from lake sediment

引用

Environmental Science and Pollution Research 2025年第13期32卷 8219-8230页

作者： Wang, Mengmeng Zhan, Yixuan Wang, Chenyu Song, Xiaohua Gan, Lin Lu, Hao Yang, Liuyan Key Laboratory of Taihu Basin Water Resources Management Ministry of Water Resources Nanjing210012 China State Key Laboratory of Pollution Control and Resource Reuse Key Laboratory of Aquatic Ecosystem Health in the Middle and Lower Reaches of Yangtze River School of Environment Nanjing University Nanjing210023 China

Cyanobacterial blooms, which carry a lot of nitrogen (N) and phosphorus (P), have emerged as one of the most severe environmental issues in freshwater ecosystems. However, there are few studies on the effect of organic matters released during cyanobacterial decomposition in promoting N release from lake sediments that remain underexplored. An essential step is to eliminate the impact of the N contributions from cyanobacteria when evaluating sedimentary N release. The response surface methodology (RSM) was developed to optimize the struvite precipitation model, and the results indicated that 1.3 of Mg/N, 1.0 of P/N, and pH 9.5 were the optimum conditions for N removal from cyanobacterial pyrolysis liquid. Following this, calcium phosphate crystallization (at pH 10 and Ca/P = 4.98) removed residual P, and zeolite adsorption (at pH 8 and 10 g/L zeolite dosage) eliminated the remaining N. Ultimately, 99.3% of N was removed with the two methods in cyanobacterial pyrolysis liquid. The cyanobacterial pyrolysis liquid, stripped of N, was found to significantly enhance the release of N from lake sediment under anaerobic conditions, which can then be reutilized by cyanobacteria. These findings reveal that organic matter derived from cyanobacterial decomposition promotes sedimentary N release, creating a feedback loop that sustains cyanobacterial blooms in freshwater ecosystems. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Blooms (metal)

来源：评论

学校读者我要写书评

暂无评论

Recent advancements of nonlinear dynamics in mode coupled microresonators:a review

引用

Applied Mathematics and Mechanics(English Edition) 2025年第2期46卷 209-232页

作者： Xuefeng WANG Zhan SHI Qiqi YANG Yuzhi CHEN Xueyong WEI Ronghua HUAN Department of Engineering Mechanics MIIT Key Laboratory of Dynamics and Control of Complex SystemsNorthwestern Polytechnical UniversityXi’an 710129China Department of Mechanics Key Laboratory of Soft Machines and Smart Devices of Zhejiang ProvinceZhejiang UniversityHangzhou 310027China State Key Laboratory for Manufacturing Systems Engineering Xi’an Jiaotong UniversityXi’an 710054China

Due to scale effects,micromechanical resonators offer an excellent platform for investigating the intrinsic mechanisms of nonlinear dynamical phenomena and their potential *** review focuses on mode-coupled micromechanical resonators,highlighting the latest advancements in four key areas:internal resonance,synchronization,frequency combs,and mode *** origin,development,and potential applications of each of these dynamic phenomena within mode-coupled micromechanical systems are investigated,with the goal of inspiring new ideas and directions for researchers in this field.

关键词： mode coupling micro-electro-mechanical system(MEMS)resonator nonlinear dynamics

来源：评论

学校读者我要写书评

暂无评论

Cd/Pb behavior during combustion in a coal-fired power plant and their spatiotemporal impacts on soils:New insights from Cd/Pb isotopes

引用

Journal of Environmental Sciences 2025年第4期150卷 582-593页

作者： Yafei Xia Ting Gao Yuhui Liu Meng Qi Jian-Ming Zhu Hui Tong Yiwen Lv Chengshuai Liu State Key Laboratory of Environmental Geochemistry Institute of GeochemistryChinese Academy of SciencesGuiyang 550081China National-Regional Joint Engineering Research Center for Soil Pollution Control and Remediation in South China Guangdong Key Laboratory of Integrated Agro-environmental Pollution Control and ManagementGuangdong Institute of Eco-environmental Science&TechnologyGuangdong Academy of SciencesGuangzhou 510650China University of Chinese Academy of Sciences Beijing 100049China State Key Laboratory of Geological Processes and Mineral Resources China University of GeosciencesBeijing 100083China

Coal power plants annually generate quantities of byproducts that release environmentally hazardous heavy metals like Cd and *** the behavior and spatiotemporal impacts on soils of these releases is crucial for pollution *** study investigated the concentrations and isotope ratios of Cd/Pb in combustion byproducts,depositions and soils collected froma coal-fired power plant or its surrounding *** pulverized fuel ash(PFA)and desulfurized gypsum(DG)exhibited heavier Cd isotopes withΔ^(114)Cd values of 0.304‰and 0.269‰,respectively,while bottom ash(BA)showed lighter Cd isotopes(Δ^(114)CdBA-coal=–0.078‰),compared to feed *** proposed a two-stage condensation process that governs the distribution of Cd/Pb,including accumulation on PFA and DG within electrostatic precipitators and desulfurization unit,as well as condensation onto fine particles upon release from the *** from combustion and large-scale transport make a significant contribution to deposition,while the dispersion of Cd/Pb in deposition is primarily influenced by the prevailing wind ***,the distribution of Cd/Pb in soils not only exhibit predominant wind control but is also potentially influenced by the resuspension of long-term storage *** power plant significantly contributes to soil in the NW–N–NE directions,even at a considerable distance(66%–79%),demonstrating its pervasive impact on remote regions along these ***,based on the vertical behavior in the profile,we have identified that Cd tends to migrate downward through leaching,while variations in Pb respond to the historical progression of dust removal.

关键词： Heavy metal diffusion Coal combustion Source tracing Atmospheric deposition Isotope fractionation Soil pollution

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 Laboratory Shanghai200433 China School of Cyber Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Automation BNRist Tsinghua University Beijing100084 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 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. © The Author(s) 2025.

关键词： Natural language processing 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：