检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Ma, Huifang Wang, Yue Xiong, Rong Kodagoda, Sarath Luo, Qianhui State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Zhejiang China Centre for Autonomous Systems University of Technology Sydney Australia

Road attributes understanding is extensively researched to support vehicle’s action for autonomous driving, whereas current works mainly focus on urban road nets and rely much on traffic signs. This paper generalizes the same issue to the scenes with little or without traffic signs, such as campuses and residential areas. These scenes face much more individually diverse appearances while few annotated datasets. To explore these challenges, a weakly-supervised framework is proposed to infer and learn road affordances without manual annotation, which includes three attributes of drivable direction, driving attention center and remaining distance. The method consists of two steps: affordances inference from trajectory and learning from partially labeled data. The first step analyzes vehicle trajectories to get partial affordances annotation on image, and the second step implements a weakly-supervised network to learn partial annotation and predict complete road affordances while testing. Real-world datasets are collected to validate the proposed method which achieves 88.2%/80.9% accuracy on direction-level and 74.3% /66.7% accuracy on image-level in familiar and unfamiliar scenes respectively. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Towards navigation without precise localization: Weakly supervised learning of goal-directed navigation cost map

arXiv

引用

arXiv 2019年

作者： Ma, Huifang Wang, Yue Tang, Li Kodagoda, Sarath Xiong, Rong State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Zhejiang China Centre for Autonomous Systems University of Technology Sydney Australia

Autonomous navigation based on precise localization has been widely developed in both academic research and practical applications. The high demand for localization accuracy has been essential for safe robot planing and navigation while it makes the current geometric solutions less robust to environmental changes. Recent research on end-to-end methods handle raw sensory data with forms of navigation instructions and directly output the command for robot control. However, the lack of intermediate semantics makes the system more rigid and unstable for practical use. To explore these issues, this paper proposes an innovate navigation framework based on the GPS-level localization, which takes the raw perception data with publicly accessible navigation maps to produce an intermediate navigation cost map that allows subsequent flexible motion planning. A deterministic conditional adversarial network is adopted in our method to generate visual goal-directed paths under diverse navigation conditions. The adversarial loss avoids the pixel-level annotation and enables a weakly supervised training strategy to implicitly learn both of the traffic semantics in image perceptions and the planning intentions in navigation instructions. The navigation cost map is then rendered from the goal-directed path and the concurrently collected laser data, indicating the way towards the destination. Comprehensive experiments have been conducted with a real vehicle running in our campus and the results have verified the robustness to localization error of the proposed navigation system. Copyright © 2019, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Temporal and spatial variation in the environmental impacts of China’s resource extraction at the provincial scale

引用

Ecosystem Health and Sustainability 2020年第1期6卷 631-646,630页

作者： He-Ming Wang Yao Wei Shen Zhao Guang-Xin Liu Fengmei Ma Guo-Qiang Wang Yao Wang Xin-Zhe Wang Dong Yang Jing-Ru Liu Hong-Tao Wang Feng Shi Wei-Qiang Chen State Environmental Protection Key Laboratory of Eco-Industry Northeastern UniversityShenyangChina Land and Water Commonwealth Scientific and Industrial Research Organisation(CSIRO)CanberraAustralia Key Lab of Urban Environment and Health Institute of Urban EnvironmentChinese Academy of ScienceXiamenChina State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijingChina College of Economics and Management Shenyang Agricultural UniversityShenyangChina Institute of Science and Technology for Development of Shandong Qilu University of Technology(Shandong Academy of Sciences)JinanChina Research Centre for Eco-Environmental Sciences Chinese Academy of SciencesBeijingChina College of Architecture and Environment Sichuan UniversityChengduChina

Introduction:Over the past two decades,China has experienced rapid economic development,which has not only led to a rapid increase in the use of raw materials but has also created environmental *** research analyzes the environmental impacts of resource extraction in China at the provincial level,and fully considers the environmental impact of various resources *** addition,it is the first time to quantitatively study the spatial pattern and evolution characteristics of the environmental impacts of China’s resource extraction from multiple perspectives by means of spatial ***:The results showed that the center of gravity of abiotic depletion potential(ADP)moved northwest,respiratory inorganics(RI)moved southwest and global warming potential(GWP)moved *** results of the standard deviation ellipse showed that RI and GWP varied over time and space,while ADP showed a discrete *** addition,the distribution of the four in the northeast-southwest direction became more ***:To mitigate the environmental impacts of resource extraction,we recommend that regional governments implement measures to control environmental impacts in the provinces within the distributed ellipse and design targeted policies based on actual conditions.

关键词： Resource extraction MFA environmental impact spatial analysis China

来源：评论

学校读者我要写书评

暂无评论

A wireless acoustic wave sensor modified with biocompatible polymer for glucose monitoring

A wireless acoustic wave sensor modified with biocompatible ...

引用

IET Doctoral Forum on Biomedical Engineering, Healthcare, Robotics and Artificial Intelligence 2018, BRAIN 2018

作者： Li, Huiyan Sha, Pengfei Hu, Ruifen Li, Guang State Key Laboratory of Industrial Control Technology Institute of Cyber Systems and Control Zhejiang University Hangzhou310027 China

ISBN: (纸本)9781839530838

The dynamic monitoring of vivo blood glucose acts an important role for diabetic patients to ensure timely healthcare and help to prevent from multiple complications caused by diabetes. This report describes a new non-enzyme glucose sensor based on wireless quartz crystal microbalance (QCM) that can be adapted for use in implanted devices. The chitosan-based enzyme-free boronic-acid glucose sensor improves biocompatibility considering for future vivo implanting. The optimal response of the sensor is in chitosan: 4-Formylphenylboronic acid (4-FPBA) =3:2. In the case of pH 7.4, the sensor has good linear response to glucose and selectivity of sensor to fructose, mannose, urea, and lactic acid performs well under physiological conditions. At physiological temperature, the linear response was also repeated and the average response time was about 4 min. The characteristics of this sensor indicate that it can be applied to dynamic monitoring of implantable blood glucose concentrations. © 2018 Institution of Engineering and technology. All rights reserved.

关键词： Glucose sensors

来源：评论

学校读者我要写书评

暂无评论

Long-term manure and mineral fertilisation drive distinct pathways of soil organic nitrogen decomposition: Insights from a 180-year-old study

引用

Soil Biology and Biochemistry 2025年 207卷

作者： Pan, Wankun Tang, Sheng Zhou, Jingjie Wanek, Wolfgang Gregory, Andrew S. Ge, Tida Marsden, Karina A. Chadwick, David R. Liang, Yongchao Wu, Lianghuan Ma, Qingxu Jones, Davey L. Ministry of Education Key Lab of Environmental Remediation and Ecosystem Health College of Environmental and Resource Sciences Zhejiang University Hangzhou310058 China State Key Laboratory of Soil Pollution Control and Safety Zhejiang Provincial Key Laboratory of Agricultural Resources and Environment College of Environmental and Resource Sciences Zhejiang University Hangzhou310058 China School of Environmental and Natural Sciences Bangor University GwyneddLL57 2UW United Kingdom Innovation Center for Saline-alkali Land Comprehensive Utilization China National Rice Research Institute Hangzhou310006 China Division of Terrestrial Ecosystem Research Department of Microbiology and Ecosystem Science Center of Microbiology and Environmental Systems Science University of Vienna Djerassiplatz 1 ViennaA-1030 Austria Protecting Crops and the Environment Rothamsted Research Harpenden HertfordshireAL5 2JQ United Kingdom State Key Laboratory for Quality and Safety of Agro-Products International Science and Technology Cooperation Base for the Regulation of Soil Biological Functions and One Health of Zhejiang Province Ningbo University Ningbo315211 China

Soil organic nitrogen (SON) decomposition is a fundamental process in the nitrogen (N) cycle that influences N availability for plant uptake and soil health. However, the long-term effects of nutrient fertilisation on SON decomposition and its microbial drivers remain poorly understood. Here, we used the 180-year-old Broadbalk Winter Wheat Experiment to investigate how farmyard manure (FYM), mineral fertiliser (NPK), and no fertilisation input (NIL) affect crop yield, SON turnover, microbial community composition, and functional genes. Our findings showed that distinct and complementary microbial mechanisms regulate SON decomposition under different nutrient fertilisation treatments. FYM application increased gross N mineralisation to 43.1 mg N kg−1 soil d−1, by doubling microbial biomass and promoting bacterial-dominated protein and peptide decomposition. During the early stage of decomposition, CO2 release from protein and peptide turnover under FYM increased by 96 % and 44 %, respectively, compared to NIL. NPK fertilisation enhanced the decomposition of complex N compounds and promoted the turnover of high-molecular-weight N to support microbial growth by upregulating N-cycling genes and extracellular enzyme production. The carbon use efficiency of protein was increased to 0.68. NPK fertilisation also stimulated fungal and Actinobacteria populations, accelerating the turnover rate of peptides and amino acids to 22.7 and 2.4 mg N kg−1 soil d−1, respectively. These results provide new insights into how nutrient fertilisation practices affect microbialy-mediated N dynamics and crop productivity, emphasising the importance of microbial functional diversity in supporting soil N cycling and fertility. © 2025 Elsevier Ltd

关键词： Manures

来源：评论

学校读者我要写书评

暂无评论

Output Regulation of Multivariable Nonlinear systems Using Extra Outputs

引用

IFAC-PapersOnLine 2018年第13期51卷 13-18页

作者： Wang, Lei Marconi, Lorenzo Wen, Changyun Su, Hongye State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China CASY - DEI University of Bologna Italy School of Electrical and Electronic Engineering Nanyang Technological University Singapore

We consider the output regulation problem for a class of nonlinear multivariable systems in the case, besides the regulated error, also additional measurements not necessarily zero in steady state are available. To offset the steady state value of the extra measurements and make the latter effective for stabilisation purposes, we propose a control structure in which those measurements are filtered by a post-processor specifically designed to block their steady state value. The specific scenario we have in mind is the one of nonlinear systems that are nonminimum-phase between the input and the regulated error and for which extra measurements are necessary, or simply desirable, to succeed in robust output feedback stabilisation. © 2018

关键词： Nonlinear systems Multivariable systems Stabilization Internal modeling Multivariable nonlinear systems Nonlinear multivariable systems Normal form Output regulation Output regulation problem Robust output feedbacks Steady state values

来源：评论

学校读者我要写书评

暂无评论

Multi Mask Learning of Stone Segmentation for Auto-Monitoring System in TBM Construction

Multi Mask Learning of Stone Segmentation for Auto-Monitorin...

引用

第三十八届中国控制会议

作者： Zhenfeng Xue Lianhui Jia Wei Sun Fulong Lin Zhitao Liu Weijie Mao State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University China Railway Engineering Equipment Group Co. LTD

The tunnel boring machine(TBM) control parameters are usually hard to measure due to the complexity of geological structure and dynamic model of TBM. In order to improve the TBM operation performance, the information of the rock particles can be given back to the TBM driver. In this paper, the size distribution of produced rock particles during tunnelling is chosen as an index. However, as detecting the sizes of rock particles in our task is quite difficult, semantic segmentation technique in deep learning is applied to solve the problem. A new dataset with annotation tools is first taken, then two semantic segmentation networks are trained to extract rock object mask and rock contour mask, separately. Finally, two masks are mixed to get the prediction of rock area. The results show that the proposed method is effective and has good performance.

关键词： TBM size detection semantic segmentation multi mask learning

来源：评论

学校读者我要写书评

暂无评论

Inferring Flow Patterns of Subway Passengers Using a Dynamic Logistics Model with Automated Fare Collection and Automated Vehicle Location Data

SSRN

引用

SSRN 2022年

作者： Li, Chunya Xiong, Shifeng Xiong, Hui Sun, Xuan Yong, Qin School of Mathematics Physics and Statistics Shanghai University of Engineering Science Shanghai201620 China NCMIS KLSC Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China School of Mechanical Engineering Beijing Institute of Technology Beijing100081 China School of Traffic and Transportation Beijing Jiaotong University Beijing100044 China State Key Lab of Rail Traffic Control & Safety Beijing Jiaotong University Beijing100044 China

With large volume of passengers boarding and alighting through subway platforms, the stations are getting crowded, which results in drops of level of service and safety concerns, especially for subway systems operating at capacity during peak hours. Thus, it is crucial for subway agencies to sense changes in travel demand and adjust their management schemes accordingly. In this paper we propose a statistical approach to estimate dynamic passenger flows with automated data. First, we develop a dynamic logistic model for calculation passenger tap-out times, which can be employed to infer the passenger flow characters at the aggregate level. In addition, a new passenger-to-train assignment model is derived based on the dynamic model. Then, we apply an expectation-maximization (EM) algorithm to estimate the model parameters with automated fare collection (AFC) and automated vehicle location (AVL) data. Finally, a cross validation method is employed to validate our approach with data obtained from several routes in Beijing subway system in China. Results of 95% prediction intervals indicate the effectiveness of the models and the proposed estimation methods. © 2022, The Authors. All rights reserved.

关键词： Maximum principle

来源：评论

学校读者我要写书评

暂无评论

Conflict Detection of Device Linkage Rules in Smart Home systems

Conflict Detection of Device Linkage Rules in Smart Home Sys...

引用

Chinese Automation Congress (CAC)

作者： Ye Fu Daojuan Zhang Chonghua Wang Xi Luo Wenxin Liu Tianjie Luo Fuyang Fang Cyber space Institute of Advanced Technology Guangzhou University Guangzhou China State Grid Key Laboratory of Information&Network Security Global Energy Interconnection Research Institute co. Ltd Beijing China China Industrial Control Systems Cyber Emergency Response Team Beijing China Information Science Academy China Electronics Technology Group Corporation Beijing China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

With the increasing types and functions of smart home devices, due to the lack of experience of users, they may cause unexpected errors and risks when configuring a large number of device linkage *** response to the above problems, in this paper, we propose an efficient conflict detection method to avoid unexpected ***, to reduce the complexity of subsequent rule conflict detection, we divide each rule into five categories according to its functions and characteristics. At the same time, we configure the priority, user rights, and execution area for each rule. Second, we filter out the rules of the same priority, user rights, and execution area. Third, we define five types of rule conflicts. Finally, the conflict detection algorithm is used to determine whether the filtered rules conflict with the rules in the corresponding database. We have created 379 non-conflicting rules in each type of rule storage database to detect whether the newly created rules conflict with them. Through experimental comparison, we find that our approach has more advantages than previous work in terms of performance and conflict detection types.

关键词： Couplings Actuators Smart homes Sensors Databases Security Data mining

来源：评论

学校读者我要写书评

暂无评论

Lithium Extraction from High Magnesium Salt Lake Brine with an Integrated Membrane technology

SSRN

引用

SSRN 2022年

作者： Ashraf, Muhammad Awais Usman, Muhammad Hussain, Iftikhar Ahmad, Faraz Guo, Shiwei Zhang, Lu State Key Laboratory of Multiphase Complex Systems CAS Key Laboratory of Green Process and Engineering Institute of Process Engineering Chinese Academy of Sciences Beijing100190 PR China University of Chinese Academy of Sciences Beijing100049 China Washington State University United States Department of Mechanical Engineering City University of Hong Kong 83 Tat Chee Avenue Kowloon Hong Kong Key Laboratory of Coal Science and Technology Taiyuan University of Technology Taiyuan030024 China North China Electric Power University Hebei Key Lab of Power Plant Flue Gas Multi-Pollutants Control Department of Environmental Science and Engineering Baoding071000 China Faculty of Economics and Business

Lithium extraction is a great challenge from the high magnesium content salt solution. In this work, an integrated polyamide tight ultrafiltration (UF) and nanofiltration (NF) membranes are systematically investigated to separate Li+ from a high magnesium salt solution. Tight ultrafiltration UA001 and nanofiltration NF270 membranes in the integrated-cascade system not only increased Li+ permeation to 82.5% but also enhanced the high Mg2+ retention to 94.6% from the ternary salt solution of LiCl and MgCl2. The transport model was also developed to calculate the real retention of Li+ and Mg2+, under constant pressure mode. The separation efficiency SFLi/Mg for the ternary salt solution of LiCl+MgCl2+H2O was more than 15 at a constant pressure of 25 bars with an integrated membrane process, which was higher as compared to single-stage UF and NF270 membranes. Moreover, the high Mg2+/Li+ ratio was also reduced from 30 to 1.9 in the integrated-cascade membrane process. © 2022, The Authors. All rights reserved.

关键词： Magnesium compounds

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：