检索结果-内蒙古大学图书馆

Explore human parsing modality for action recognition

CAAI Transactions on Intelligence technology 2024年第6期9卷 1623-1633页

作者： Jinfu Liu Runwei Ding Yuhang Wen Nan Dai Fanyang Meng Fang-Lue Zhang Shen Zhao Mengyuan Liu School of Intelligent Systems Engineering Sun Yat-sen UniversityShenzhenChina Peng Cheng Laboratory ShenzhenChina State Key Laboratory of General Artificial Intelligence Peking UniversityShenzhen Graduate SchoolShenzhenChina Changchun University of Science and Technology ChangchunChina Victoria University of Wellington WellingtonNew Zealand

Multimodal-based action recognition methods have achieved high success using pose and RGB ***,skeletons sequences lack appearance depiction and RGB images suffer irrelevant noise due to modality *** address this,the authors introduce human parsing feature map as a novel modality,since it can selectively retain effective semantic features of the body parts while filtering out most irrelevant *** authors propose a new dual-branch framework called ensemble human parsing and pose network(EPP-Net),which is the first to leverage both skeletons and human parsing modalities for action *** first human pose branch feeds robust skeletons in the graph convolutional network to model pose features,while the second human parsing branch also leverages depictive parsing feature maps to model parsing features via convolutional *** two high-level features will be effectively combined through a late fusion strategy for better action *** experiments on NTU RGB t D and NTU RGB t D 120 benchmarks consistently verify the effectiveness of our proposed EPP-Net,which outperforms the existing action recognition *** code is available at https://***/liujf69/EPP-Net-Action.

关键词： action recognition human parsing human skeletons

来源：评论

学校读者我要写书评

暂无评论

An interpretable graph convolutional neural network based fault diagnosis method for building energy systems

引用

Building Simulation 2024年第7期17卷 1113-1136页

作者： Guannan Li Zhanpeng Yao Liang Chen Tao Li Chengliang Xu School of Urban Construction Wuhan University of Science and TechnologyWuhan 430065China Anhui Province Key Laboratory of Intelligent Building and Building Energy-saving Anhui Jianzhu UniversityHefei 230601China State Key Laboratory of Green Building in Western China Xi'an University of Architecture&TechnologyXi'an 710055China Key Laboratory of Low-grade Energy Utilization Technologies and Systems(Chongqing University) Ministry of Education of ChinaChongqing UniversityChongqing 400044China Hubei Provincial Engineering Research Centre of Urban Regeneration Wuhan University of Science and TechnologyWuhan 430081China

Due to the fast-modeling speed and high accuracy,deep learning has attracted great interest in the field of fault diagnosis in building energy systems in recent ***,the black-box nature makes deep learning models generally difficult to *** order to compensate for the poor interpretability of deep learning models,this study proposed a fault diagnosis method based on interpretable graph neural network(GNN)suitable for building energy *** method is developed by following three main steps:(1)selecting NC-GNN as a fault diagnosis model for building energy systems and proposing a graph generation method applicable to the model,(2)developing an interpretation method based on InputXGradient for the NC-GNN,which is capable of outputting the importance of the node features and automatically locating the fault related features,(3)visualizing the results of model interpretation and validating by matching with expert knowledge and maintenance *** was performed using the public ASHRAE RP-1043 chiller fault *** diagnosis results show that the proposed method has a diagnosis accuracy of over 96%.The interpretation results show that the method is capable of explaining the decision-making process of the model by identifying fault-discriminative *** almost all seven faults,their fault-discriminative features were correctly identified.

关键词： fault diagnosis graph neural network building energy system InputXGradient feature interpretation

来源：评论

学校读者我要写书评

暂无评论

Fog Images Generation About Unmanned Surface Vessels with Improved Generative Adversarial Network 42

Fog Images Generation About Unmanned Surface Vessels with Im...

引用

42nd Chinese Control Conference, CCC 2023

作者： Tang, Yifeng Huang, Zhihui Tang, Chuancong Luo, Chuanshang Xu, Yifan Liu, Bin Zhang, Hai-Tao School of Artificial Intelligence and Automation The Engineering Research Center of Autonomous Intelligent Unmanned Systems The Key Laboratory of Image Processing and Intelligent Control Wuhan430074 China The State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789887581543

This paper proposes a fog weather data augmentation method for the unmanned surface vessels (USVs) via improved Generative Adversarial Network(GAN) model. First, a generator scheme for GAN is proposed with the guided generation of the atmospheric scattering model in this paper. A Laplacian Pyramid Based Depth Residuals model is added to the generator which reduces the difficulty of generating fog images caused by the degradation of water surface image and improves the quality of generated images. Finally, fog images are generated from sunny weather images collected with HUST-12C by LPBDR-GAN model and experiments show that generated images are very close to real fog images. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Small-size temperature/high-pressure integrated sensor via flip-chip method

引用

Microsystems & Nanoengineering 2024年第4期10卷 153-162页

作者： Mimi Huang Xiaoyu Wu Libo Zhao Xiangguang Han Yong Xia Yi Gao Zeyu Cui Cheng Zhang Xiaokai Yang Zhixia Qiao Zhikang Li Feng Han Ping Yang Zhuangde Jiang State Key Laboratory for Manufacturing Systems Engineering International Joint Laboratory for Micro/Nano Manufacturing and Measurement TechnologiesXi’an Jiaotong UniversityXi’an 710049China Xi’an Jiaotong University(Yantai)Research Institute for Intelligent Sensing Technology and System Xi’an Jiaotong UniversityXi’an 710049China Shandong Laboratory of Yantai Advanced Materials and Green Manufacturing Yantai 265503China School of Mechanical Engineering Xi’an Jiaotong University710049 Xi’anChina School of Instrument Science and Technology Xi’an Jiaotong University710049 Xi’anChina Chongqing Key Laboratory of Micro-Nano Systems and Intelligent Sensing Chongqing Academician WorkstationChongqing 2011 Collaborative Innovation Center of Micro/Nano Sensing and Intelligent Ecological Internet of ThingsChongqing Technology and Business UniversityNan’an DistrictChongqing 400067China Xi’an Aerospace Yuanzheng Fluid Control Co.Ltd. Xi’an 710049China

Hydraulic technology with smaller sizes and higher reliability trends,including fault prediction and intelligent control,requires high-performance temperature and pressure-integrated *** designs rely on planar wafer-or chip-level integration,which is limited by pressure range,chip size,and low *** propose a small-size temperature/high-pressure integrated sensor via the flip-chip *** pressure and temperature units are arranged vertically,and the sensing signals of the two units are integrated into one plane through silicon vias and gold–gold bonding,reducing the lateral size and improving the efficiency of signal *** flip-chip technique ensures a reliable electrical connection.A square diaphragm with rounded corners is designed and optimised with simulation to sense high pressure based on the piezoresistive *** temperature sensing unit with a thin-film platinum resistor measures temperature and provides back-end high-precision compensation,which will improve the precision of the pressure *** integrated chip is fabricated by MEMS technology and packaged to fabricate the extremely small integrated *** integrated sensor is characterised,and the pressure sensor exhibits a sensitivity and sensitivity drift of 7.97mV/MPa and−0.19%FS in the range of 0–20 MPa and−40 to 120℃.The linearity,hysteresis,repeatability,accuracy,basic error,and zero-time drift are 0.16%FS,0.04%FS,0.06%FS,0.18%FS,±0.23%FS and 0.04%FS,*** measurement error of the temperature sensor and temperature coefficient of resistance is less than±1°C and 3142.997 ppm/℃,*** integrated sensor has broad applicability in fault diagnosis and safety monitoring of high-end equipment such as automobile detection,industrial equipment,and oil drilling platforms.

关键词： size corners sizes

来源：评论

学校读者我要写书评

暂无评论

Time-synchronous-averaging-spectrum based on super-resolution analysis and application in bearing fault signal identification

引用

Journal of Zhejiang University-Science A(Applied Physics & Engineering) 2024年第7期25卷 573-585页

作者： Zengle REN Yuan WANG Huiyue TANG Xin'an CHEN Wei FENG Guangdong Provincial Key Laboratory of Construction Robotics and Intelligent Construction Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen518055China Shenzhen EBORAIL Technology Co. Ltd.Shenzhen518038China National Supercomputing Center in Shenzhen Shenzhen518055China State Key Lab of Rail Traffic Control and Safety Beijing Jiaotong UniversityBeijing100044China University of Chinese Academy of Sciences Beijing100190China Shenzhen University of Advanced Technology Shenzhen518107China

Time-synchronous-averaging(TSA)is based on the idea of denoising by averaging,and it extracts the periodic components of a quasiperiodic signal and keeps the extracted waveform *** paper studies the mathematical properties of TSA,where three propositions are given to reveal the nature of *** paper also proposes a TSA-spectrum based on super-resolution analysis and it decomposes a signal without using any base *** contrast to discrete Fourier transform spectrum(DFT-spectrum),which is a spectrum in frequency domain,TSA-spectrum is a period-based spectrum,which can present more details of the cross effects between different periodic components of a quasiperiodic ***,a case study is carried out using bearing fault analysis to illustrate the performance of TSA-spectrum,where the rotation speed fluctuation of the shaft is estimated,which is about 0.12 ms *** extracted fault signals are presented and some insights are *** believe that this paper can provide new motivation for TSA-spectrum to be widely used in applications involving quasiperiodic signal processing(QSP).

关键词： Time-synchronous-averaging(TSA) Spectrum Quasiperiodic signal processing(QSP) Super-resolution analysis Bearingfaultdetection

来源：评论

学校读者我要写书评

暂无评论

Distributed Minimum-time Consensus Prediction for High-order Multi-agent systems

引用

IEEE Transactions on Automatic Control 2025年第6期70卷 4186-4193页

作者： Hu, Fulong Zhang, Hai-Tao Xu, Bowen Hu, Zhe School of Artificial Intelligence and Automation The Institute of Artificial Intelligence The Engineering Research Center of Autonomous Intelligent Unmanned Systems State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China Guangdong Hust Industrial Technology Research Institute Huazhong University of Science and Technology Dongguan523808 China Guangdong Provincial Key Laboratory of Manufacturing Equipment Digitization Dongguan523808 China School of Artificial Intelligence Optics and Electronics Northwestern Polytechnical University Xi'an710072 China

In this note, a detective matrix-based distributed algorithm is proposed to address a distributed minimum-time consensus prediction problem for discrete-time high-order multi-agent systems (MASs). Therein, each agent predicts the consensus value merely using the minimum length of individual and/or neighboring successive position time series. Compared to most existing algorithms that could only predict constant consensus values for first-order linear MASs, the present method could predict consensus manifolds for high-order linear MASs as well, which could be time-varying. Finally, both the effectiveness and superiority of the proposed distributed minimum-time consensus algorithm are substantiated by numerical simulations. © 2025 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Zero-Inflated Negative Binomial Graph Neural Network-Powered Multi-Port Vessel Traffic Flow Prediction

Spatial-Temporal Zero-Inflated Negative Binomial Graph Neura...

引用

International Conference on Artificial Intelligence and Autonomous Transportation, AIAT 2024

作者： Cao, Jining Zhu, Man Wen, Yuanqiao Liu, Yihao Zheng, Xinyi Sanya Science and Education Innovation Park of Wuhan University of Technology Wuhan University of Technology Sanya572000 China State Key Laboratory of Maritime Technology and Safety Wuhan University of Technology Wuhan430070 China Intelligent Transportation Systems Research Center Wuhan University of Technology Wuhan430070 China

ISBN: (纸本)9789819639564

High-precision prediction of vessel traffic flow is crucial for managing traffic during adverse weather conditions and enhancing navigation efficiency. Aiming to eliminate the deficiencies of traditional prediction methods and improve prediction precision and adaptability, this paper proposed a vessel traffic flow prediction method based on an origin-destination (O-D) matrix and a Spatio-Temporal Zero-Inflated Negative Binomial Graph Neural Network (STZINB-GNN) for port cluster navigational networks. To understand the internal coupling relationships within the traffic network from a macro perspective, a port cluster navigational network was constructed based on vessel origin-destination (O-D) data. Traditional prediction methods often overlook the Euclidean spatial characteristics between network nodes and face challenges due to the sparsity of vessel traffic flow. To address these issues, a spatial-temporal graph neural network prediction method incorporating a sparsity parameter π was proposed. A case study with the Qiongzhou Strait port group demonstrated that the STZINB-GNN achieved the highest prediction accuracy across three temporal resolutions compared to four established methods: STNB-GNN, STG-GNN, STGCN, and HA. Specifically, the STZINB-GNN attained superior accuracy when the temporal resolution was extended to one day. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Decentralized Game-based Auction Algorithm for Scheduling Robotic Chargers to Service EVs with Uncertain Demands

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on intelligent Vehicles 2024年 1-14页

作者： Fang, Qiuyang Zhang, Jianlei Wang, Chen Xie, Guangming Zhang, Chunyan Department of Automation College of Computer and Control Engineering Nankai University Tianjin China National Engineering Research Center of Software Engineering Peking University Beijing China State Key Laboratory for Turbulence and Complex Systems Intelligent Biomimetic Design Lab College of Engineering Peking University Beijing China

In this study, we introduce a novel auction-based algorithm modeled as a decentralized coalition formation game, designed for the complex requirements of large-scale multi-robot task allocation under uncertain demand. This context is particularly illustrative in scenarios where robots are tasked to charge electric vehicles. The algorithm begins by partitioning a composite task sequence into distinct subsets based on spatial similarity principles. Subsequently, we employ a coalition formation game paradigm to coordinate the assembly of robots into cooperative coalitions focused on these distinct subsets. To mitigate the impact of unpredictable task demands on allocations, our approach utilizes the conditional value-at-risk to assess the risk associated with task execution, along with computing the potential revenue of the coalition with an emphasis on risk-related outcomes. Additionally, integrating consensus auctions into the coalition formation framework allows our approach to accommodate assignments for individual robot-task pairings, thus preserving the stability of individual robotic decision autonomy within the coalition structure and assignment distribution. Simulative analyses on a prototypical parking facility layout confirm that our algorithm achieves Nash equilibrium within the coalition structure in polynomial time and demonstrates significant scalability. Compared to competing algorithms, our proposal exhibits superior performance in resilience, task execution efficiency, and reduced overall task completion times. The results demonstrate that our approach is an effective strategy for solving the scheduling challenges encountered by multi-robot systems operating in complex environments. IEEE

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

High-Speed 2 μm Silicon Photonic Mach-Zehnder Modulator with 30 GHz Bandwidth

High-Speed 2 μm Silicon Photonic Mach-Zehnder Modulator wit...

引用

2024 Asia Communications and Photonics Conference, ACP 2024 and International Conference on Information Photonics and Optical Communications, IPOC 2024

作者： Wang, Jianing Zhang, Xuelin Wang, Xi Yang, Yanfu Du, Jiangbing Xu, Ke Guangdong Provincial Key Laboratory of Semiconductor Optoelectronic Materials and Intelligent Photonic Systems Department of Integrated Circuits Harbin Institute of Technology Shenzhen China State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Jiao Tong University Shanghai China Department of Integrated Circuits Harbin Institute of Technology Shenzhen China

ISBN: (纸本)9798350379266

关键词： Silicon photonics

来源：评论

学校读者我要写书评

暂无评论

Design and Experimental Evaluation of WLR-III

Design and Experimental Evaluation of WLR-III

引用

2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

作者： Li, Xu Fu, Yili Zhejiang University State Key Laboratory of Robotics and System Harbin Institute of Technology State Key Laboratory of Fluid Power and Mechatronic Systems China Harbin Institute of Technology Intelligent Robot Research Center Zhejiang Laboratory State Key Laboratory of Robotics and System Heilongjiang Province Harbin150001 China

ISBN: (纸本)9798350325706

This paper introduces the design and experimental evaluation of WLR-III, which stands for the third-generation hydraulic wheel-legged robot. WLR-III is expected to be applied to disaster scenarios where the mobility, adaptability and manipulation capability are required. Based on the development of the previous two generations of wheel-legged robots, this work continuously optimizes the design to achieve higher mobility and stronger adaptability by reducing weight & inertia. The hydraulic power transmission system adopts a hose-less design method to ensure the robustness of the system. What's more prominent is that the successful development of hydraulic power unit (HPU) enables WLR-III to realize hydraulic power autonomy. In addition, to accomplish all kinds of operational tasks in the rescue scene, the electro-hydraulic hybrid drives anthropomorphic arms with heavy load grippers were developed. Finally, the effectiveness and reliability of design optimization have been evaluated through a series of experiments, including grassland movement, load bearing, obstacle-stepping and tool-operating. To the authors' best knowledge, this is the first time that a hydraulic powered autonomous wheel-legged humanoid robot with the ability to operate simple tools has been developed. © 2023 IEEE.

关键词：

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：