检索结果-内蒙古大学图书馆

Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5520-5537页

作者： Jian Liu Wei Sun Hui Yang Pengchao Deng Chongpei Liu Nicu Sebe Hossein Rahmani Ajmal Mian National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering School of Robotics and the State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China Department of Information Engineering and Computer Science University of Trento Trento Italy School of Computing and Communications Lancaster University Lancaster U.K. Department of Computer Science The University of Western Australia Crawley WA Australia

Nine-degrees-of-freedom (9-DoF) object pose and size estimation is crucial for enabling augmented reality and robotic manipulation. Category-level methods have received extensive research attention due to their potential for generalization to intra-class unknown objects. However, these methods require manual collection and labeling of large-scale real-world training data. To address this problem, we introduce a diffusion-based paradigm for domain-generalized category-level 9-DoF object pose estimation. Our motivation is to leverage the latent generalization ability of the diffusion model to address the domain generalization challenge in object pose estimation. This entails training the model exclusively on rendered synthetic data to achieve generalization to real-world scenes. We propose an effective diffusion model to redefine 9-DoF object pose estimation from a generative perspective. Our model does not require any 3D shape priors during training or inference. By employing the Denoising Diffusion Implicit Model, we demonstrate that the reverse diffusion process can be executed in as few as 3 steps, achieving near real-time performance. Finally, we design a robotic grasping system comprising both hardware and software components. Through comprehensive experiments on two benchmark datasets and the real-world robotic system, we show that our method achieves state-of-the-art domain generalization performance.

关键词： Shape Solid modeling Three-dimensional displays Pose estimation Training Robots Grasping Diffusion models Real-time systems Point cloud compression

来源：评论

学校读者我要写书评

暂无评论

H ∞ Asynchronous control for Discrete-Time Semi-Markov Jump Systems

引用

IFAC-PapersOnLine 2022年第3期55卷 143-148页

作者： Liqiang Jin Yanyan Yin Yanqing Liu Kok Lay Teo Fei Liu National Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education) Institute of Automation Jiangnan University Wuxi 214122 China School of Electrical Engineering Computing and Mathematical Sciences Curtin University Perth Western Australia 6102 Australia School of Mathematical Sciences Sunway University Kuala Lumpur 47500 Malaysia Tianjin University of Finance and Economics Tianjin China

This paper investigates the problem of H ∞ asynchronous control for discrete-time semi-Markov jump systems. In practice, it is difficult to ensure that controller modes and system modes are updated synchronously. Therefore, a hidden semi-Markov model is introduced to characterize such an asynchronous phenomenon between system modes and controller modes. Meanwhile, the switching signal of the controller is generated by a given conditional probability related to the system mode. Based on the mode-dependent and elapsed-time-dependent Lyapunov function, together with the semi-Markov kernel (SMK) method, sufficient conditions constructed by linear matrix inequalities (LMIs) are derived to ensure the existence of an asynchronous controller such that the resulting system is σ-error mean square stable and satisfies an H ∞ performance index. Finally, a numerical example is given to illustrate the effectiveness and feasibility of the method proposed.

关键词： Asynchronous control semi-Markov jump systems hidden semi-Markov model semi-Markov kernel (SMK) σ-error mean square stable

来源：评论

学校读者我要写书评

暂无评论

keystone rhizospheric diazotrophs may promote the pioneer plant growth in mine tailings

引用

Soil Security 2024年 16卷

作者： Li, Yongbin Yang, Rui Khan, Ajmal Soleimani, Mohsen Guo, Lifang Sun, Xiaoxu Li, Baoqin Liu, Huaqing Jin, Shenghua Sun, Weimin Key Laboratory of Industrial Ecology and Environmental Engineering (Ministry of Education) School of Environmental Science and Technology Dalian University of Technology Dalian 116024 China 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 Management Institute of Eco-environmental and Soil Sciences Guangdong Academy of Sciences 808 Tianyuan Road Guangdong Guangzhou 510650 China Department of Natural Resources Isfahan University of Technology Isfahan 84156-83111 Iran Shaanxi Environmental Survey and Assesment Center Xi an 710054 China

Nitrogen (N) shortage often hinders the bioremediation of mining-generated tailings. For pioneer plants living in mine tailings, biological N fixation (BNF) is an essential source of N. However, the diazotrophs in the rhizosphere of pioneer plants are rarely investigated. In this study, the pioneer plant Miscanthus sinensis samples were collected from four different tailings across Southwest China, and the 16S rRNA amplicon sequencing, multivariable statistical tools, ¹⁵N₂ DNA-SIP, metagenomic-binning, cultural screening methods, and pot experiment were applied to analyze the roles of diazotrophs in rhizosphere of M. sinensis. Firstly, genera Stenotrophomonas and Pseudomonas were identified as keystone taxa in the rhizosphere of M. sinensis cultivated in the tailings. Furthermore, ¹⁵N₂ DNA-SIP demonstrated that Stenotrophomonas and Pseudomonas were the rhizospheric diazotrophs. The metagenome-assembled genomes of Stenotrophomonas and Pseudomonas contained some genes involved in BNF, plant growth promotion, and metal(loid) resistance (As, Sb, Ni, Co, Zn, Mn, Cu, and Cd). Subsequent diazotrophic isolation was conducted, and two diazotrophic strains (Pseudomonas sp. R21 (nitrogenase activities, 1,161.9 nmol C₂H₄ mg⁻¹ protein h⁻¹) and Stenotrophomonas sp. R30 (1,890.2 nmol C₂H₄ mg⁻¹ protein h⁻¹)) were isolated from the rhizosphere soil of M. sinensis. Pot assay demonstrated that inoculation with Pseudomonas sp. R21 and Stenotrophomonas sp. R30 could promote plant growth, N content, and metal(loid) (arsenic and antimony) accumulation, which confirmed nitrogenase activity and plant growth-promoting ability of the two identified keystone taxa, highlighting the exciting opportunities of applying some keystone rhizospheric diazotrophs in the pioneer plants through microbiome manipulation for the bioremediation of tailings. © 2024

关键词： Bioremediation Miscanthus sinensis Rhizosphere Tailings

来源：评论

学校读者我要写书评

暂无评论

A Survey on Deep Reinforcement Learning for Traffic Signal control

A Survey on Deep Reinforcement Learning for Traffic Signal C...

引用

第33届中国控制与决策会议

作者： Wei Miao Long Li Zhiwen Wang GS-Unis Intelligent Transportation System&Control Technology Co .Ltd College of Electrical and Information Engineering Lanzhou University of Technology Key Laboratory of Gansu Advanced Control for Industrial Processes Lanzhou University of Technology National Demonstration Center for Experimental Electrical and Control Engineering Education Lanzhou University of Technology

Traffic congestion is one of the most important and complex problems in urban governance for a long *** traffic lights are used at intersections,traffic bottlenecks still appear with the increasing number of private *** recent years,with the continuous development of related technologies in the field of intelligent transportation,more attention has been paid to the automatic driving scheme with intelligent vehicle infrastructure cooperative systems as the *** a kind of advanced artificial intelligence method,deep reinforcement learning(DRL) is applied to traffic signal control(TSC) to achieve the purpose of optimizing roadside traffic *** this paper,we introduce the background of TSC(i.e.,main parameters,methods and simulation tools),and then summarize the representation of DRL model(i.e.,state,action and reward) and the application of DRL in *** research scenarios of TSC are divided into single-agent and ***,according to existing works in this field,the problems to be solved are put forward and the paper is summarized.

关键词： Deep reinforcement learning Traffic signal control Multi-agent Intersection

来源：评论

学校读者我要写书评

暂无评论

Zwitterionic Liquid Hydrogel Sustained-Release Strategy for High-Performance Nanofiltration Membrane

SSRN

引用

SSRN 2022年

作者： Xiao, Luqi Bai, Ju Lai, Wei Jiao, Yang Wu, Qi Liu, Hongyan Zhang, Yizhou Shan, Linglong Luo, Shuangjiang School of Rare Earths University of Science and Technology of China Hefei230026 China CAS Key Laboratory of Green Process and Engineering State Key Laboratory of Multiphase Complex Systems Beijing Key Laboratory of Ionic Liquids Clean Process Institute of Process Engineering Chinese Academy of Sciences Beijing100190 China Ganjiang Innovation Academy Chinese Academy of Sciences Ganzhou341000 China Key Laboratory of Organic Compound Pollution Control Engineering Ministry of Education School of Environmental and Chemical Engineering Shanghai University Shanghai200444 China Langfang Green Industrial Technology Center Langfang065000 China

controlling amine monomer diffusion behavior plays a crucial role in fabricating well-defined architecture and high-performance nanofiltration (NF) membranes through interfacial polymerization. Herein, a zwitterionic liquid hydrogel transition layer was introduced to the sustained-release amine monomer to the regulated interfacial polymerization process to fabricate a high-performance NF membrane. The hydrogel (Gel) was fabricated via in-situ one-step UV photo-initiated free-radical polymerization between 1-vinyl-3-ethylimidazolium chloride ([VEIm][Cl]) and 3-sulfopropyl methacrylate potassium salt (SMP) on PES substrate membrane surface. Then polyamide layer formed on the Gel layer surface under the regulation of mitigating the amine diffusion behavior. Low-field time-domain NMR (LF-NMR) analysis and water-absorbing demonstrated that the Gel-PA membrane showed high water-membrane interaction. Positron annihilation lifetime spectroscopy (PALS) also confirmed the Gel-PA composite membrane possessed enlarged free volume . Membrane surface and cross-sectional SEM morphologies also showed the Gel-PA membrane with a less ridge-and-valley loose structure and thinner thickness. Combined with the uptake ability of the Gel layer, the obtained Gel-PA composite membrane displayed a high permeance of 13.22 L m -2 h -1 bar -1 , a high Na 2 SO 4 rejection of 98.23%, a favorable NaCl/Na 2 SO 4 selectivity of 49.75, and excellent long-term operational stability . This sustained-release strategy provides a facial and feasible approach to controlling the IP process and obtaining high-performance nanofiltration membranes. © 2022, The Authors. All rights reserved.

关键词： Nanofiltration

来源：评论

学校读者我要写书评

暂无评论

Photochemical fate of nonionic polyacrylamide induced by hydroxyl radicals in the natural water: Mineralization mechanism exploration and half-life time evaluation

引用

Science of the Total Environment 2024年 947卷 174485页

作者： Jia, Daqing Therias, Sandrine Voelker, François Kieffer, Johann Favero, Cédrick Mailhot, Gilles Université Clermont Auvergne CNRS Institut de Chimie de Clermont-Ferrand Clermont-FerrandF-63000 France SNF ZAC de milieux 42160 SA Andrézieux-Bouthéon France National Engineering Laboratory for Industrial Wastewater Treatment School of Resources and Environmental Engineering East China University of Science and Technology Shanghai200237 China State Environmental Protection Key Laboratory of Environmental Risk Assessment and Control on Chemical Process East China University of Science and Technology Shanghai200237 China Université Clermont Auvergne CNRS Laboratoire de Météorologie Physique Clermont-FerrandF-63000 France

Water-soluble polyacrylamide (PAM) compounds have been used extensively in various sectors. The abundance of PAM in the environment raises concerns about its environmental impact. However, the mineralization of PAM in water under natural light irradiation remains insufficiently explored. This study utilizes nonionic PAM (nPAM) as a representative model to investigate both the mechanism and efficiency of nPAM degradation in water when exposed to ultraviolet (UV) light with hydrogen peroxide (H2O2) as the hydroxyl radical source. In the dark or with only UVA irradiation, negligible mineralization of nPAM occurred. In contrast, the presence of hydroxyl radicals (produced by the UVA/H2O2 system) produced 50 % nPAM mineralization over 7 days under our experimental conditions. The corresponding molecular weight (MW) of the nPAM was swiftly reduced from 1.58 ×106 Da to 1.59 ×103 Da in 3 days. Moreover, five carboxylic acids and nitrate ions were identified as the photodegradation intermediates of nPAM. The efficiencies of nPAM photodegradation by the UVA/H2O2 system in different natural waters and environmental conditions were assessed. The rate constant for the reaction between the hydroxyl radical and nPAM was 2.17 ×109 M-unit−1 s−1. The half-lives of nPAM in the sea and continental surface waters were determined to be several years and dozens of days, respectively. The application of UVB obviously accelerated the mineralization of nPAM in ultrapure water (71 % degradation in 7 days). Moreover, mineralization of concentrated nPAM (200 mg/L) in sea water was more efficient when both UVA- and UVB-activated H2O2 were used. Additionally, toxic acrylamide was not generated during nPAM photodegradation. Moreover, the photodegradation intermediates from nPAM were found to be neither acutely nor chronically toxic to aquatic organisms. This comprehensive study sheds light on the photochemical fate of nPAM in natural waters and provides essential insight for practical treatment of

关键词： Rate constants

来源：评论

学校读者我要写书评

暂无评论

Multi-grain cascade recurrent neural network for nonlinear time-varying process soft sensor modeling 8

Multi-grain cascade recurrent neural network for nonlinear t...

引用

8th IEEE Data Driven control and Learning Systems Conference, DDCLS 2019

作者： Yi, Jinjing Yao, Le Ge, Zhiqiang Song, Zhihuan State Key Laboratory of Industrial Control Technology Institute of Industrial Process Control College of Control Science and Engineering Zhejiang University Hangzhou Zhejiang China

ISBN: (纸本)9781728114545

Soft sensor provides accurate online estimation of primary variables based on historical data of secondary variables. Recurrent neural network exhibits better performance on sequence data. Deep forest shows quite robust performance across nonlinear data from different domains. In this paper, a multi-grain cascade recurrent neural network(gcRNN) is put forward to soft sensor modeling for nonlinear time-varying processes. Based on deep forest framework, LSTM and GRU are chosen as individual learners in multi-grain moving window scanning and cascade structure to deal with sequence data. Performance of the proposed method is tested and verified on two industrial cases with different process characteristics. Compared to the PLS, RF, LSTM and GRU soft sensing approaches, the root mean squared errors (RMSE) of gcRNN are the smallest. The prediction results also illustrated that gcRNN achieves better performance for primary variable quality prediction in nonlinear time-varying processes. © 2019 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Abnormal Adipose Tissue-Derived Microbes Drive Metabolic Disorder and Exacerbate Postnatal Growth Retardation in Piglet

SSRN

引用

SSRN 2023年

作者： Song, Tongxing Qi, Ming Zhu, Yucheng Wang, Nan Liu, Zhibo Li, Na Yang, Jiacheng Han, Yanxu Wang, Jing Tao, Shiyu Ren, Zhuqing Yin, Yulong Zheng, Jinshui Tan, Bie College of Animal Science and Technology Huazhong Agricultural University Wuhan430070 China College of Animal Science and Technology Hunan Agricultural University Changsha410000 China Laboratory of Animal Nutritional Physiology and Metabolic Process CAS Key Laboratory of Agro-ecological Processes in Subtropical Region National Engineering Laboratory for Pollution Control and Waste Utilization in Livestock and Poultry Production Institute of Subtropical Agriculture Chinese Academy of Sciences Changsha410125 China State Key Laboratory of Agricultural Microbiology Huazhong Agricultural University Wuhan430070 China Hubei Key Laboratory of Agricultural Bioinformatics Huazhong Agricultural University Wuhan430070 China

Postnatal growth retardation (PGR) frequently occurs during early postnatal development of piglets and induces high mortality. To date, the mechanism of PGR remains poorly understood. Adipose tissue-derived microbes have been documented to be associated with several disorders of metabolism and body growth. However, the connection between microbial disturbance of adipose tissue and pig PGR remains unclear. Here, we investigated piglets with PGR, and found that the adipose tissue of PGR piglets was characterized by metabolism impairment, adipose abnormality, and specific enrichment of culturable bacteria from Proteobacteria. The relative abundance of the Sphingomonas genus from the alphaproteobacteria class was significantly negatively associated with piglet body weight;and gavage of Sphingomonas pauchimobilis induced PGR in piglets. Moreover, this bacterium could also lead to metabolic disorders and susceptibility to acute stress and thereby weight loss in mice. Mechanistically, multi-omics analysis indicated the changes in lipid metabolism as a response of adipose tissue to abnormal microbial composition. Further experimental test proved that phosphatidylethanolamine, one of the changing lipids likely produced from adipose tissue, could rescue the metabolism disorder and growth retardation by suppressing the amount of Sphingomonas in the adipose tissue. Together, these results highlight that the microbe-host crosstalk may regulate the metabolic function of adipose tissue in response to PGR. © 2023, The Authors. All rights reserved.

关键词： Metabolism

来源：评论

学校读者我要写书评

暂无评论

Detection of False Data Injection Attacks in smart grids based on cubature Kalman Filtering

Detection of False Data Injection Attacks in smart grids bas...

引用

第33届中国控制与决策会议

作者： Zhiwen Wang Qi Zhang Hongtao Sun Jiqiang Hu College of Electrical and Information Engineering Lanzhou University of Technology Key Laboratory of Gansu Advanced Control for Industrial Processes Lanzhou University of Technology National Demonstration Center for Experimental Electrical and Control Engineering Education Lanzhou University of Technology College of Engineering Qufu Normal University

The false data injection attacks(FDIAs) in smart grids can offset the power measurement data and it can bypass the traditional bad data detection *** solve this problem,a new detection mechanism called cosine similarity ratio which is based on the dynamic estimation algorithm of square root cubature Kalman filter(SRCKF) is proposed in this *** is,the detection basis is the change of the cosine similarity between the actual measurement and the predictive measurement before and after the *** the system is suddenly attacked,the actual measurement will have an abrupt ***,the predictive measurement will not vary promptly with it owing to the delay of Kalman filter ***,the cosine similarity between the two at this moment has undergone a *** causes the ratio of the cosine similarity at this moment and that at the initial moment to fluctuate considerably compared to safe *** the detection threshold is triggered,the system will be judged to be under ***,the standard IEEE-14 bus test system is used for simulation experiments to verify the effectiveness of the proposed detection method.

关键词： Smart grids False Data Injection Attacks Attack detection Square root cubature Kalman filter Cosine similarity

来源：评论

学校读者我要写书评

暂无评论

Emerging contaminants:A One Health perspective

引用

The Innovation 2024年第4期5卷 140-170,139页

作者： Fang Wang Leilei Xiang Kelvin Sze-Yin Leung Martin Elsner Ying Zhang Yuming Guo Bo Pan Hongwen Sun Taicheng An Guangguo Ying Bryan WBrooks Deyi Hou Damian EHelbling Jianqiang Sun Hao Qiu Timothy MVogel Wei Zhang Yanzheng Gao Myrna JSimpson Yi Luo Scott XChang Guanyong Su Bryan MWong Tzung-May Fu Dong Zhu Karl JJobst Chengjun Ge Frederic Coulon Jean Damascene Harindintwali Xiankui Zeng Haijun Wang Yuhao Fu Zhong Wei Rainer Lohmann Changer Chen Yang Song Concepcion Sanchez-Cid Yu Wang Ali El-Naggar Yiming Yao Yanran Huang Japhet Cheuk-Fung Law Chenggang Gu Huizhong Shen Yanpeng Gao Chao Qin Hao Li Tong Zhang Natàlia Corcoll Min Liu Daniel SAlessi Hui Li Kristian KBrandt Yolanda Pico Cheng Gu Jianhua Guo Jianqiang Su Philippe Corvini Mao Ye Teresa Rocha-Santos Huan He Yi Yang Meiping Tong Weina Zhang Fidèle Suanon Ferdi Brahushi Zhenyu Wang Syed AHashsham Marko Virta Qingbin Yuan Gaofei Jiang Louis A.Tremblay Qingwei Bu Jichun Wu Willie Peijnenburg Edward Topp Xinde Cao Xin Jiang Minghui Zheng Taolin Zhang Yongming Luo Lizhong Zhu Xiangdong Li DamiàBarceló Jianmin Chen Baoshan Xing Wulf Amelung Zongwei Cai Ravi Naidu Qirong Shen Janusz Pawliszyn Yong-guan Zhu Andreas Schaeffer Matthias C.Rillig Fengchang Wu Gang Yu James M.Tiedje State Key Laboratory of Soil and Sustainable Agriculture Institute of Soil ScienceChinese Academy of SciencesNanjing 210008China University of Chinese Academy of Sciences Beijing 100049China Department of Chemistry Hong Kong Baptist UniversityHong KongChina HKBU Institute of Research and Continuing Education Shenzhen Virtual University ParkShenzhenChina Technical University of Munich TUM School of Natural SciencesInstitute of Hydrochemistry85748 GarchingGermany School of Resources&Environment Northeast Agricultural UniversityHarbin 150030China Climate Air Quality Research UnitSchool of Public Health and Preventive MedicineMonash UniversityMelbourneVICAustralia Faculty of Environmental Science&Engineering Kunming University of Science&TechnologyKunming 650500China Ministry of Education Key Laboratory of Pollution Processes and Environmental Criteria College of Environmental Science and EngineeringNankai UniversityTianjin 300350China Guangdong Key Laboratory of Environmental Catalysis and Health Risk Control School of Environmental Science and EngineeringInstitute of Environmental Health and Pollution ControlGuangdong University of TechnologyGuangzhou 510006China Ministry of Education Key Laboratory of Environmental Theoretical Chemistry South China Normal UniversityGuangzhouGuangdong 510006China Department of Environmental Science Baylor UniversityWacoTXUSA Center for Reservoir and Aquatic Systems Research(CRASR) Baylor UniversityWacoTXUSA School of Environment Tsinghua UniversityBeijing 100084China School of Civil and Environmental Engineering Cornell UniversityIthacaNY 14853USA Key Laboratory of Microbial Technology for Industrial Pollution Control of Zhejiang Province Zhejiang University of TechnologyHangzhou 310014China School of Environmental Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China Laboratoire d’Ecologie Microbienne Universite Claude Bernard Lyon 1UMR CNRS 5557UMR INRAE 1418VetAgro Sup69622 VilleurbanneFrance Department of Pla

Environmental pollution is escalating due to rapid global development that often prioritizes human needs over planetary *** global efforts to mitigate legacy pollutants,the continuous introduction of new substances remains a major threat to both people and the *** response,global initiatives are focusing on risk assessment and regulation of emerging contaminants,as demonstrated by the ongoing efforts to establish the UN’s Intergovernmental Science-Policy Panel on Chemicals,Waste,and Pollution *** review identifies the sources and impacts of emerging contaminants on planetary health,emphasizing the importance of adopting a One Health *** for monitoring and addressing these pollutants are discussed,underscoring the need for robust and socially equitable environmental policies at both regional and international *** actions are needed to transition toward sustainable pollution management practices to safeguard our planet for future generations.

关键词： pollution planet contaminants

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：