检索结果-内蒙古大学图书馆

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

作者： Zhou, Lei Liu, Yang Li, Qiang School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China College of Computer Science and Technology Zhejiang University Hangzhou China Institute of Automation Chinese Academy of Sciences State Key Laboratory for Management and Control of Complex Systems Beijing China

ISBN: (纸本)9798350337020

Zero-shot learning (ZSL) is an important but challenging task in computer vision that aims to identify unseen classes without matching training samples. Current cutting-edge ZSL methods based on locality focus on acquiring the explicit locality of distinguishing characteristics, which could face a lack of adequate supervision at the class attribute level. This paper introduces a novel approach called IAC, which aims to learn Implicit Attribute Composition for ZSL. This method is more comprehensive compared to attribute localization that solely focuses on class-level attribute supervision. IAC utilizes subspace representations that efficiently capture the inherent structure of high-dimensional image features. Then, we learn implicit attribute composition through subspace representation learning. The superiority of the proposed IAC compared to the state-of-the-art is demonstrated through sufficient experiments conducted on three commonly used ZSL datasets, CUB, SUN, and AwA2. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Continuous-Time Linear Parallel Output Regulation

Continuous-Time Linear Parallel Output Regulation

引用

2021 China Automation Congress, CAC 2021

作者： Li, Hongyang Wei, Qinglai Wang, Fei-Yue The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665426473

A novel parallel output regulation method is presented in this paper. The framework of the parallel output regulation problem is first introduced. Then, the existence of parallel controller is analyzed detailly in the situation that only the measurable information is obtained. Finally, the simulation example is given to show the performance of the presented method. © 2021 IEEE

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Exploring painting synthesis with diffusion models 1

Exploring painting synthesis with diffusion models

引用

1st IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2021

作者： Yi, Da Guo, Chao Bai, Tianxiang Institute of Automation Chinese Academy of Sciences The State Key Laboratory for Management and Control of Complex Systems Beijing China

ISBN: (纸本)9781665433372

As a significant composition of art, fine art painting is becoming a research hotspot in machine learning community. With unique aesthetic value, paintings have quite different representations from natural images, making them irreplaceable. Meanwhile, the lack of training data is common in painting-related machine learning tasks. Therefore, the synthesis of fine art painting is meaningful and challenging work. There are two main types of generative models for image synthesis: generative adversarial networks (GANs) and likelihood-based models. GAN-based models can obtain high-quality samples but usually sacrifice diversity and training stability. Diffusion models are a class of likelihood-based models and have recently been shown to achieve state-of-the-art quality on the image synthesis tasks. In this paper, we explore generating fine art paintings by using diffusion models. We carried out the experiments on the partial impression paintings from the Wikiart dataset. The results demonstrate that the diffusion model can generate high-quality samples, and it is easy to train to cover more target distribution than the GAN-based methods. © 2021 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

TASF: Terrestrial-Aerial Synergistic Framework for a New Generation of Intelligent Transportation 27

TASF: Terrestrial-Aerial Synergistic Framework for a New Gen...

引用

27th IEEE International Conference on Intelligent Transportation systems, ITSC 2024

作者： Wang, Cong Nie, Dujun Zhang, Ruijun Teng, Siyu Chen, Long Institute of Automation Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Hong Kong Baptist University Kowloon Hong Kong Waytous Inc. Beijing China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems The State Key Laboratory of Management and Control for Complex Systems Beijing100190 China Shenzhen518107 China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an710049 China

ISBN: (纸本)9798331505929

Terrestrial-Aerial Synergistic Framework (TASF) represents a novel approach to intelligent transportation, integrating terrestrial and aerial vehicles to enhance urban transportation efficiency and capacity. In this paper, we offer an in-depth analysis of TASF, emphasizing its innovative applications in urban transportation, parcel delivery, and emergency response services. TASF incorporates a five-layer architecture comprising perception, communication, planning, control, and interaction. With the five-layer architecture, TASF can achieve effective collaboration among terrestrial and aerial vehicles, encompassing two principal features: terrestrial-aerial synergistic parallel perception and multi-agent parallel management. Parallel perception results from fusing Bird's Eye View (BEV) representations from Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs), whereas decentralized multi-agent management employs foundational models to enhance decision-making capabilities. Additionally, we consider challenges and potential solutions related to TASF, including safety, reliability, energy efficiency, management and integration. TASF marks a paradigm-shifting leap in the realm of intelligent transportation systems, providing a scalable and efficacious solution tailored to the dynamic requirements of urban mobility and emergency services. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Energy Optimization of Wireless Sensor Networks 19

Event-Triggered Energy Optimization of Wireless Sensor Netwo...

引用

19th IEEE International Conference on Networking, Sensing and control, ICNSC 2022

作者： Liu, Lu Song, Ruizhuo Wei, Qinglai School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China Institute of Automation Chinese Academy of Sciences The State Key Laboratory of Management and Control for Complex Systems Beijing China

ISBN: (纸本)9781665472432

Aiming at limited communication and energy re-sources in wireless sensor networks (WSN s), this paper proposes an energy management scheme of WSNs via adaptive dynamic programming (ADP) based on event-triggered mecha-nism (ETM). The optimal control strategy obtained by iteration can schedule the sensor nodes and make the nodes switch between working and sleeping situations, thus improving the energy utilization and extending the service life of the energy-constrained WSNs. Firstly, the mathematical model of WSNs is established, and the state is estimated by extended Kalman filter (EKF) algorithm to improve the measurement accuracy. Then, ADP solves the designed value function to achieve the scheduling plan. On the premise of system stability, ETM is applied to activate the controller on demand, which can reduce communication burden and save WSNs energy consumption. Finally, the simulation experiment reveals that the proposed algorithm can reduce the unnecessary triggering times of the controller effectively while ensuring the requirements, and avoid data congestion and interaction resource waste. © 2022 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

AUTOSIM:Automated Urban Traffic Operation Simulation via Meta-Learning

引用

IEEE/CAA Journal of Automatica Sinica 2023年第9期10卷 1871-1881页

作者： Yuanqi Qin Wen Hua Junchen Jin Jun Ge Xingyuan Dai Lingxi Li Xiao Wang Fei-Yue Wang Zhejiang Lab Hangzhou 310030China ECARX Technology Co. Ltd.Shanghai 201811China IEEE Zhejiang Supcon Information Company Ltd. Hangzhou 310052China the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Indiana University-Purdue University Indianapolis(IUPUI) IndianapolisIndiana 46202 USA School of Artificial Intelligence Anhui UniversityHefei 230039China

Online traffic simulation that feeds from online information to simulate vehicle movement in real-time has recently seen substantial advancement in the development of intelligent transportation systems and urban traffic *** has been a challenging problem due to three aspects:1)The diversity of traffic patterns due to heterogeneous layouts of urban intersections;2)The nature of complex spatiotemporal correlations;3)The requirement of dynamically adjusting the parameters of traffic models in a real-time *** cater to these challenges,this paper proposes an online traffic simulation framework called automated urban traffic operation simulation via meta-learning(AUTOSIM).In particular,simulation models with various intersection layouts are automatically generated using an open-source simulation tool based on static traffic geometry *** a meta-learning technique,AUTOSIM enables an automated learning process for dynamic model settings of traffic scenarios featured with different spatiotemporal ***,AUTOSIM is capable of adapting traffic model parameters according to dynamic traffic information in real-time by using a *** computational experiments,we demonstrate the effectiveness of the meta-learningbased framework that is capable of providing reliable supports to real-time traffic simulation and dynamic traffic operations.

关键词： Conditional generative adversarial network signalized urban networks short-term link speed prediction

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

Short-Term Wind Power Prediction Based on KNN-BiGRU

引用

Power Engineering (ICPE), International Conference on

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

ISBN: (数字)9798331531140

ISBN: (纸本)9798331531157

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 $\mathbf{8 4. 3 0 4} \%$.

关键词： Training Power engineering Accuracy Wind speed Time series analysis Nearest neighbor methods Wind power generation Predictive models Data models Optimization

来源：评论

学校读者我要写书评

暂无评论

NA-CPG: A robust and stable rhythm generator for robot motion control

引用

Biomimetic Intelligence & Robotics 2022年第4期2卷 30-38页

作者： Ru Tong Changlin Qiu Zhengxing Wu Jian Wang Min Tan Junzhi Yu State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Department of Advanced Manufacturing and Robotics College of EngineeringPeking UniversityBeijing 100871China

Central pattern generators(CPGs)have been widely applied in robot motion control for the spontaneous output of coherent periodic ***,the underlying CPG network exhibits good convergence performance only within a certain range of parameter spaces,and the coupling of oscillators affects the network output accuracy in complex topological ***,CPGs may diverge when parameters change drastically,and the divergence is irreversible,which is catastrophic for the control of robot ***,normalized asymmetric CPGs(NA-CPGs)that normalize the amplitude parameters of Hopf-based CPGs and add a constraint function and a frequency regulation mechanism are ***-CPGs can realize parameter decoupling,precise amplitude output,and stable and rapid convergence,as well as asymmetric output ***,it can effectively cope with large parameter changes to avoid network oscillations and *** optimize the parameters of the NA-CPG model,a reinforcement-learning-based online optimization method is further ***,a biomimetic robotic fish is illustrated to realize the whole optimization *** demonstrated that the designed NA-CPGs exhibit stable,secure,and accurate network outputs,and the proposed optimization method effectively improves the swimming speed and reduces the lateral swing of the multijoint robotic fish by 6.7%and 41.7%,*** proposed approach provides a significant improvement in CPG research and can be widely employed in the field of robot motion control.

关键词： Normalized asymmetric CPGs Rhythm generator Motion control Robotic fish

来源：评论

学校读者我要写书评

暂无评论

Quantitative analysis of the impact of various urban socioeconomic indicators on search-engine-based estimation of COVID-19 prevalence

引用

Infectious Disease Modelling 2022年第2期7卷 117-126页

作者： Ligui Wang Mengxuan Lin Jiaojiao Wang Hui Chen Mingjuan Yang Shaofu Qiu Tao Zheng Zhenjun Li Hongbin Song Department of Infectious Disease Prevention and Control Center for Disease Control and Prevention of Chinese People's Liberation ArmyBeijingChina Academy of Military Medical Sciences Academy of Military Science of Chinese PLABeijingChina The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijingChina State Key Laboratory for Infectious Disease Prevention and Control National Institute for Communicable Disease Control and PreventionChinese Center for Disease Control and PreventionBeijingChina

Numerous studies have proposed search engine-based estimation of COVID-19 prevalence during the COVID-19 pandemic;however,their estimation models do not consider the impact of various urban socioeconomic indicators(USIs).This study quantitatively analysed the impact of various USIs on search engine-based estimation of COVID-19 prevalence using 15 USIs(including total population,gross regional product(GRP),and population density)from 369 cities in *** results suggested that 13 USIs affected either the correlation(SC-corr)or time lag(SC-lag)between search engine query volume and new COVID-19 cases(p<0.05).Total population and GRP impacted SC-corr considerably,with their correlation coefficients r for SC-corr being 0.65 and 0.59,*** population,GRP per capita,and proportion of the population with a high school diploma or higher had simultaneous positive impacts on SC-corr and SC-lag(p<0.05);these three indicators explained 37e50%of the total variation in SC-corr and *** for different urban agglomerations revealed that the goodness of fit,R2,for search engine-based estimation was more than 0.6 only when total urban population,GRP per capita,and proportion of the population with a high school diploma or higher exceeded 11.08 million,120,700,and 38.13%,respectively.A greater urban size indicated higher accuracy of search engine-based estimation of COVID-19 ***,the accuracy and time lag for search engine-based estimation of infectious disease prevalence can be improved only when the total urban population,GRP per capita,and proportion of the population with a high school diploma or higher are greater than the aforementioned thresholds.

关键词： Urban socioeconomic indicators Search engine-based estimation Effectiveness evaluation

来源：评论

学校读者我要写书评

暂无评论

SIM: A Scenario IMagination Based Deep Reinforcement Learning Method for Outdoor Transportation Environment Exploration 11

SIM: A Scenario IMagination Based Deep Reinforcement Learnin...

引用

11th IEEE Data Driven control and Learning systems Conference, DDCLS 2022

作者： Li, Haoran Zhang, Qichao Chen, Yaran Zhao, Dongbin State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518000 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

Autonomous exploration is very important for robotics, especially for mapping, navigation, and planning in an unknown environment. In recent years, automatic exploration methods in the indoor environment have been extensively studied, but there is little research on exploration in the outdoor transportation environment. Due to the limitations of outdoor traffic rules and the scale of the environment, the methods for the indoor environment are difficult to apply to the transportation environment. Aiming at exploration in the transportation environment, this paper proposes a deep reinforcement learning algorithm based on Scenario IMagination(SIM), which has two important components: 1) a mid-level action space, which combines the classical robot control algorithm, addressing the inefficient learning and unstable navigation of deep reinforcement learning algorithms in automatic exploration. With this action space, the deep reinforcement learning algorithm achieves excellent exploration performance in both normal scale environments and large-scale branchless environments;2) a scenarios buffer, which relieves hard exploration problems of deep reinforcement learning due to serious imbalances of samples in large-scale multibranch scenarios. Compared to the map-less navigation approaches, SIM achieves excellent exploration performance in large-scale multi-branch environments. © 2022 IEEE.

关键词： Navigation

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：