检索结果-内蒙古大学图书馆

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第6期8卷 3523-3526页

作者： Wang, Fei-Yue Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

From January 1 to May 30, 2023, we have received 1214 submissions, averaging 8.09 submissions per day. Based on this SPD, we are on track to surpass our estimated 2500 submissions by November [1], [2]. This implies more work for processing and evaluation; therefore we need to speed up our effort to recruit more able and responsible Associate Editors and Reviewers. I need help from you in this task with great appreciation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A review and evaluation of nonroad diesel mobile machinery emission control in China

引用

Journal of Environmental Sciences 2023年第1期123卷 30-40页

作者： Pengju Bie Liang Ji Huanxing Cui Gang Li Shunli Liu Ying Yuan Kebin He Huan Liu State Key Joint Laboratory of ESPC State Environmental Protection Key Laboratory of Sources and Control of Air Pollution ComplexSchool of EnvironmentInternational Joint Laboratory on Low Carbon Clean Energy InnovationTsinghua UniversityBeijing 100084China State Environmental Protection Key Laboratory of Vehicle Emission Control and Simulation Chinese Research Academy of Environmental SciencesBeijing 100012China Jinan Automobile Testing Center Co Ltd.Jinan 250102China

China’s emission control for nonroad diesel mobile machinery(NDMM)must deal with a fast increase in stock as well as regulations that are two decades behind those for on-road *** study provides the first large-scale review and evaluation of China’s NDMM policies,along with emission measurements and an investigation on diesel fuel *** sulfur contents of the investigated diesel declined from 430 ppm(median value)in 2011 to6-8 ppm during the 2017-2018 *** emission control of NO_(x)and PM greatly improved with the shift from the China II to China IV standards,as demonstrated by engine tests and field NO_(x)***,the NO_(x)emission factors for non-type-approved engines were approximately twice the limits of the China II *** compliance based on bench tests was not sufficient to control actual emissions because the field-measured NO_(x)emission factors of all machinery ranged from 24%to 225%greater than the respective emission limits for the *** circumstances adversely affected the effectiveness of the regulations and policies for China’s emission control of ***,the policies on new and in-use NDMM,as well as diesel fuel quality,prevented NO_(x)and PM emissions amounting to 4.4 Tg and 297.8 Gg during the period 2008-2017,*** emission management strategy contributed to enhancing the international competitiveness of China’s NDMM industries by promoting advanced *** effective NDMM emission control in the future,portable testing and noncontact remote supervision should be strengthened;also,the issue of noncompliant diesel should be addressed through rigorous control measures and financial penalties.

关键词： Nonroad mobile machinery Emission reduction Emission control policy Emission factor Diesel fuel quality

来源：评论

学校读者我要写书评

暂无评论

Open Set Domain Adaptation with Zero-shot Learning on Graph 23

Open Set Domain Adaptation with Zero-shot Learning on Graph

引用

4th International Conference on Computing, Networks and Internet of Things, CNIOT 2023

作者： Zhang, Xinyue Yang, Xu Liu, Zhiyong School of Artificial Intelligence University of Chinese Academy of Sciences China and State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798400700705

Open set domain adaptation focuses on transferring the information from a richly labeled domain called source domain to a scarcely labeled domain called target domain, while classifying the unseen target samples as one unknown class in an unsupervised way. Compared with the close set domain adaptation, where the source domain and the target domain share the same class space, the classification of the unknown class makes it easy to adapt to the real environment. Particularly, after the recognition of the unknown samples, the model can either ask for manually labeling or further develop the classification ability of the unknown classes based on pre-stored knowledge. Inspired by this idea, we propose a model for open set domain adaptation with zero-shot learning on the unknown classes in this paper. We utilize adversarial learning to align the two domains while rejecting the unknown classes. Then the knowledge graph is introduced to generate the classifiers for the unknown classes with the employment of the graph convolution network (GCN). Thus the classification ability of the source domain is transferred to the target domain, and the model can distinguish the unknown classes in detail with prior knowledge. We evaluate our model on digits datasets and the result shows superior performance. © 2023 Owner/Author.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Short-Term Wind Power Prediction Based on KNN-BiGRU 5

Short-Term Wind Power Prediction Based on KNN-BiGRU

引用

5th International Conference on Power Engineering, ICPE 2024

作者： Fan, Xinyu Wu, Zhenlong Bian, Guibin Liu, Yanhong Zhengzhou University School of Electrical and Information Engineering Zhengzhou China State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798331531140

Wind power generations have received widespread concern recently, however, due to the continuity of time series, ordinary machine learning models cannot learn the dependencies of continuous time series data well. To better predict the time series and improve the prediction effect of wind power, a shortterm wind power prediction method based on K-Nearest Neighbor(KNN) and Bidirectional Gated Recurrent Unit(BiGRU) is proposed. Firstly, KNN is used to detect outliers in the wind speed-power sequence in the field collected data, and then the wind speed value of all abnormal data is modified to the mean value of wind speed. Then the modified data is input to the bidirectional gated recurrent unit for prediction. The bidirectional gated recurrent unit can efficiently learn the context information of the data and improve the prediction effect. The experimental results show that the proposed prediction method based on KNN-BiGRU obtains a good prediction effect on a single unit. Compared with other methods, it has the best prediction effect on multi-unit where the accuracy rate is 8 4. 3 0 4 %. © 2024 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Parallel Training: An ACP-Based Training Framework for Iterative Learning in Uncertain Driving Spaces

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第4期8卷 2832-2841页

作者： Wang, Jiangong Wang, Xiao Tian, Yonglin Wang, Yutong Niu, Jinglong Kwan, Oliver Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Anhui Univ Sch Artificial Intelligence State Key Lab Management & Control Complex Syst Hefei 230031 Peoples R China Chinese Acad Sci Qingdao Acad Intelligent Ind State Key Lab Management & Control Complex Syst Qingdao 266109 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Acad Intelligent Ind Qingdao 266109 Peoples R China China North Ind North Automatic Control Technol Re Taiyuan 030006 Peoples R China Motion G Inc Singapore 068898 Singapore

The traffic environment and driving behaviors are of great complexity and uncertainty in our physical world. Therefore, training in the digital world with low cost and diverse complexities become popular for autonomous driving in recent years. However, the current training methods tend to be limited to static data sets and deterministic models that do not sufficiently take into account the uncertainty and diversity prevalent in real traffic scenarios. These approaches also limit more possibilities for the comprehensive development and optimization of vision systems. In this paper, we develop a parallel training method based on artificial systems, computational experiments, and parallel execution (ACP) for the intelligent optimization and learning of the aforementioned agents in uncertain driving spaces. Parallel training creates a virtual driving space following the instruction of the ACP approach and conducts large-scale rehearsal experiments for possible scenarios. By enhancing the diversity of virtual scenarios, intelligent vehicles are trained to respond and adapt to the diverse uncertainties in the physical real-world driving space. Specifically, parallel training first proposes a standard operating procedure for intelligent driving systems, namely the projection-emergence-convergence-operation (PECO) loop. Digital quadruplets for parallel training, i.e., physical, descriptive, predictive, and prescriptive coaches, are also proposed. With the guidance of parallel training, virtual and real-world driving spaces are set up in parallel and interact frequently. They are closely linked and unified in opposition to each other, ultimately building a parallel driving system that fulfills safety, security, sustainability, sensitivity, service, and smartness (6S).

关键词： Training Digital twins Testing Task analysis Intelligent agents complex systems Uncertainty Parallel intelligence parallel driving digital quadruplets parallel learning digital twins metaverses automated driving knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

Vision-based control in the open racing car simulator with deep and reinforcement learning

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第12期14卷 15673-15685页

作者： Zhu, Yuanheng Zhao, Dongbin State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

With decades of development, computer intelligence has now reached a really high level. Especially deep learning (DL) and reinforcement learning (RL) endow computers the perception and decision abilities. This paper aims to design a vision-based system that is able to play The Open Racing Car Simulator (TORCS) like a human player that uses images. With the DL-trained perception module, useful and low-dimensional information is extracted from first-person images. Based on that, the RL-trained module further manipulates the simulated car in the middle of the lane. The two modules are separately trained, and both DL and RL advantages are maximally utilized. Experiments on different tracks show the promising performance of the method. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Line Feature Based Visual Servo control with TDE for Underwater Vehicle Manipulator Systems Target Grasping

Line Feature Based Visual Servo Control with TDE for Underwa...

引用

2024 IEEE International Conference on Unmanned Systems, ICUS 2024

作者： Zhang, Yunfei Bian, Xinyu Sun, Yize Zhang, Zongyu Huang, Hai Yang, Xu National Key Laboratory of Autonomous Marine Vehicle Technology Harbin Engineering University Harbin China State Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350384185

Underwater vehicle manipulator systems (UVMSs) is becoming a research hotspot in the field of marine intelligent equipment. Introducing visual feedback equipped with cameras in the loop to guide UVMS to complete the grasping has comprehensive advantages of response speed, work efficiency and intelligence. In this paper, mapping between the feature error and the motion of the UVMS generalized degrees of freedom is established to realize the suspended grasping under the coordinated motion of the vehicle body and the manipulator. Then, a UVMS motion control algorithm based on time delay estimation (TDE) is constructed for visual servo autonomous grasping process, the TDE of which is used to estimate and compensate the lumped interference in real time. The Lyapunov theory is applied to analyze its stability and its control performance is verified through simulation experiments. The simulation results shew the effectiveness of the proposed visual servo control with TED method based on line features. © 2024 IEEE.

关键词： Visual servoing

来源：评论

学校读者我要写书评

暂无评论

AI4S Based on DeSci: Reference Model and Research Issues

AI4S Based on DeSci: Reference Model and Research Issues

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Ding, Wenwen Li, Juanjuan Qin, Rui Guan, Sangtian Wang, Fei-Yue Institute of Automation Chinese Academy of Sciences The State Key Laboratory for Management and Control of Complex Systems The State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Macau University of Science and Technology Faculty of Innovation Engineering Macau China Institute of Automation The State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350337020

The rise of Artificial Intelligence for Science (AI4S) has highlighted the importance and urgency of ensuring open-ness, fairness, impartiality, diversity, and sustainability in scientific systems. Existing scientific systems, referred to as Centralized Science (CeSci), are built on centralized organizational structures and top-down institutional frameworks, which are lagging behind the development and practical requirements of AI4S. To address these limitations, AI4S needs to embrace a new scientific organizational and operational paradigm, namely Decentralized Science (DeSci). It can provide strong support to AI4S via effectively addressing issues such as information silos, biases, unfair distribution, and monopolies and promoting multidisciplinary, interdisciplinary, and trans disciplinary cooperation in science. Based on these considerations, this paper presents the framework of AI4S based on DeSci and explores its potential application scenarios and research issues. The research can provide effective guidance for the development of scientific systems. © 2023 IEEE.

关键词： Artificial Intelligence for Science (AI4S) ChatGPT Decentralized Autonomous Organizations and Operations (DAOs) Decentralized Science (De-Sci) Generative Artificial Intelligence (GAI) Intelligent Science

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Macroscopic Regulation for High-Speed Railway Timetable Rescheduling

引用

IEEE/CAA Journal of Automatica Sinica 2023年第9期10卷 1822-1833页

作者： Wei Xu Chen Zhao Jie Cheng Yin Wang Yiqing Tang Tao Zhang Zhiming Yuan Yisheng Lv Fei-Yue Wang Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China Signal&Communication Research Institute China Academy Railway SciencesBeijing 100081China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049 State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China IEEE State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190 Macao Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China

Unexpected delays in train operations can cause a cascade of negative consequences in a high-speed railway *** such cases,train timetables need to be ***,timely and efficient train timetable rescheduling is still a challenging problem due to its modeling difficulties and low optimization *** paper presents a Transformer-based macroscopic regulation approach which consists of two stages including Transformer-based modeling and policy-based ***,the relationship between various train schedules and operations is described by creating a macroscopic model with the Transformer,providing the better understanding of overall operation in the high-speed railway ***,a policy-based approach is used to solve a continuous decision problem after macro-modeling for fast *** experiments on various delay scenarios are *** results demonstrate the effectiveness of the proposed method in comparison to other popular methods.

关键词： High-speed railway reinforcement learning train timetable rescheduling Transformer

来源：评论

学校读者我要写书评

暂无评论

The Increasing Role of Synergistic Effects in Carbon Mitigation and Air Quality Improvement, and Its Associated Health Benefits in China

引用

Engineering 2023年第1期20卷 103-111页

作者： Jie Wang Xi Lu Pengfei Du Haotian Zheng Zhaoxin Dong Zihua Yin Jia Xing Shuxiao Wang Jiming Hao State Key Joint Laboratory of Environment Simulation and Pollution Control School of the EnvironmentTsinghua UniversityBeijing 100084China Institute for Carbon Neutrality Tsinghua UniversityBeijing 100084China Beijing Laboratory of Environmental Frontier Technologies Tsinghua UniversityBeijing 100084China State Environmental Protection Key Laboratory of the Sources and Control of Air Pollution Complex Beijing 100084China

A synergistic pathway is regarded as a critical measure for tackling the intertwined challenges of climate change and air pollution in China. However, there is as yet no indicator that can comprehensively reflect such synergistic effects;hence, existing studies lack a consistent framework for comparison. Here, we introduce a new synergistic indicator defined as the pollutant generation per gross domestic product (GDP) and adopt an integrated analysis framework by linking the logarithmic mean Divisia index (LMDI) method, response surface model (RSM), and global exposure mortality model (GEMM) to evaluate the synergistic effects of carbon mitigation on both air pollutant reduction and public health in China. The results show that synergistic effects played an increasingly important role in the emissions mitigation of SO_(2), NOx, and primary particulate matter with an aerodynamic diameter no greater than 2.5 μm (PM2.5), and the synergistic mitigation of pollutants respectively increase from 3.1, 1.4, and 0.3 Mt during the 11th Five-Year Plan (FYP) (2006–2010) to 5.6, 3.7, and 1.9 Mt during the 12th FYP (2011–2015). Against the non-control scenario, synergistic effects alone contributed to a 15% reduction in annual mean PM2.5 concentration, resulting in the prevention of 0.29 million (95% confidential interval: 0.28–0.30) PM2.5-attributable excess deaths in 2015. Synergistic benefits to air quality improvement and public health were remarkable in the developed and population-dense eastern provinces and municipalities. With the processes of urbanization and carbon neutrality in the future, synergistic effects are expected to continue to increase. Realizing climate targets in advance in developed regions would concurrently bring strong synergistic effects to air quality and public health.

关键词： Synergistic effects Indicator Carbon mitigation Air pollution control Spatial and temporal disparities

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：