检索结果-内蒙古大学图书馆

Pedestrian trajectory prediction method based on the Social-LSTM model for vehicle collision

Transportation Safety and Environment 2024年第3期6卷 140-151页

作者： Yong Han Xujie Lin Di Pan Yanting Li Liang Su Robert Thomson Koji Mizuno School of Mechanical and Automotive Engineering Xiamen University of TechnologyXiamen 361024China Fujian Province Key Laboratory of Advanced Design and Manufacturing of Buses Xiamen 361024China Engineering Research Institute of Xiamen Kinglong United Automobile Industry Co. Ltd.Xiamen 361000China Chalmers University of Technology Gothenburg 41296Sweden Department of Mechanical Systems Engineering Nagoya UniversityNagoya 464-8603Japan

Techniques for predicting the trajectory of vulnerable road users are important to the development of perception systems for autonomous vehicles to avoid *** most effective trajectory prediction methods,such as Social-LSTM,are often used to predict pedestrian trajectories in normal passage ***,they can produce unsatisfactory prediction results and data redundancy,as well as difficulties in predicting trajectories using pixel-based coordinate systems in collision avoidance *** is also a lack of validations using real vehicle-to-pedestrian *** address these issues,some insightful approaches to improve the trajectory prediction scheme of Social-LSTM were proposed,such methods included transforming pedestrian trajectory coordinates and converting image coordinates to world *** YOLOv5 detection model was introduced to reduce target loss and improve prediction *** DeepSORT algorithm was employed to reduce the number of target transformations in the tracking *** Perspective Transformation(IPT)and Direct Linear Transformation(DLT)theories were combined to transform the coordinates to world coordinates,identifying the collision location where the accident could *** performance of the proposed method was validated by training tests using MS COCO(Microsoft Common Objects in Context)and ETH/UCY *** results showed that the target detection accuracy was more than 90%and the prediction loss tends to decrease with increasing training steps,with the final loss value less than 1%.The reliability and effectiveness of the improved method were demonstrated by benchmarking system performance to two video recordings of real pedestrian accidents with different lighting conditions.

关键词： vehicle-to-pedestrian collisions pedestrian trajectory prediction YOLOvB DeepSORT Social-LSTM

来源：评论

学校读者我要写书评

暂无评论

Research on workflow recognition for liver rupture repair surgery

引用

Mathematical Biosciences and engineering 2024年第2期21卷 1844-1856页

作者： Men, Yutao Zhao, Zixian Chen, Wei Wu, Hang Zhang, Guang Luo, Feng Yu, Ming Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China Medical Support Technology Research Department Systems Engineering Institute Academy of Military Sciences People’s Liberation Army Tianjin300161 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin300384 China

Liver rupture repair surgery serves as one tool to treat liver rupture, especially beneficial for cases of mild liver rupture hemorrhage. Liver rupture can catalyze critical conditions such as hemorrhage and shock. Surgical workflow recognition in liver rupture repair surgery videos presents a significant task aimed at reducing surgical mistakes and enhancing the quality of surgeries conducted by surgeons. A liver rupture repair simulation surgical dataset is proposed in this paper which consists of 45 videos collaboratively completed by nine surgeons. Furthermore, an end-to-end SA-RLNet, a self attention-based recurrent convolutional neural network, is introduced in this paper. The self-attention mechanism is used to automatically identify the importance of input features in various instances and associate the relationships between input features. The accuracy of the surgical phase classification of the SA-RLNet approach is 90.6%. The present study demonstrates that the SA-RLNet approach shows strong generalization capabilities on the dataset. SA-RLNet has proved to be advantageous in capturing subtle variations between surgical phases. The application of surgical workflow recognition has promising feasibility in liver rupture repair surgery. ©2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Channel selection against electrode shift enables robust myoelectric control without retraining

引用

Science China(Technological Sciences) 2021年第8期64卷 1653-1662页

作者： LV Bo HE JiaYuan SHENG XinJun DING Han ZHU XiangYang State Key Laboratory of Mechanical System and Vibration School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghai200240China Department of Systems Design Engineering Faculty of EngineeringUniversity of WaterlooWaterlooN2L 3G1Canada

Myoelectric controlled interfaces driven by muscle activities have achieved good performance in ideal conditions and showed many potential medical-related and industrial ***,in practical applications,the performance could be drastically degraded due to the electrode(sensor)shift,which is inevitable in donning and doffing the *** this study,we presented a novel channel selection method against electrode shift for robust pattern-recognition based myoelectric *** proposed method was evaluated on twenty-four subjects,including twenty-two able-bodied subjects and two amputees,and compared with two traditional channel selection methods,i.e.,uniform selection(UNI)and sequential feature selection(SFS).We demonstrated that the offline error rates of the proposed method were significantly lower than those of the other two methods(P<0.05),and its online performance in shift conditions was comparable to that in ideal *** outcomes benefit the practical applications of robust myoelectric controlled interfaces.

关键词： myoelectric control high-density electrodes channel selection electrode shift surface electromyography

来源：评论

学校读者我要写书评

暂无评论

Pavement Cracks Coupled With Shadows:A New Shadow-Crack Dataset and A Shadow-Removal-Oriented Crack Detection Approach

引用

IEEE/CAA Journal of Automatica Sinica 2023年第7期10卷 1593-1607页

作者： Lili Fan Shen Li Ying Li Bai Li Dongpu Cao Fei-Yue Wang School of Information and Electronics Beijing Institute of TechnologyBeijing 100081China School of Civil Engineering Tsinghua UniversityBeijing 100084China School of Mechanical Engineering Beijing Institute of TechnologyBeijing 100081China State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body and the College of Mechanical and Vehicle Engineering Hunan UniversityChangsha 410082China School of Vehicle and Mobility Tsinghua UniversityBeijing 100084China State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Automatic pavement crack detection is a critical task for maintaining the pavement stability and driving *** task is challenging because the shadows on the pavement may have similar intensity with the crack,which interfere with the crack detection *** to the present,there still lacks efficient algorithm models and training datasets to deal with the interference brought by the *** fill in the gap,we made several contributions as ***,we proposed a new pavement shadow and crack dataset,which contains a variety of shadow and pavement pixel size *** also covers all common cracks(linear cracks and network cracks),placing higher demands on crack detection ***,we designed a two-step shadow-removal-oriented crack detection approach:SROCD,which improves the performance of the algorithm by first removing the shadow and then detecting *** addition to shadows,the method can cope with other noise ***,we explored the mechanism of how shadows affect crack *** on this mechanism,we propose a data augmentation method based on the difference in brightness values,which can adapt to brightness changes caused by seasonal and weather ***,we introduced a residual feature augmentation algorithm to detect small cracks that can predict sudden disasters,and the algorithm improves the performance of the model *** compare our method with the state-of-the-art methods on existing pavement crack datasets and the shadow-crack dataset,and the experimental results demonstrate the superiority of our method.

关键词： Automatic pavement crack detection data augmentation compensation deep learning residual feature augmentation shadow removal shadow-crack dataset

来源：评论

学校读者我要写书评

暂无评论

Surgical Gesture Recognition in Open Surgery Based on 3DCNN and SlowFast 7

Surgical Gesture Recognition in Open Surgery Based on 3DCNN ...

引用

7th IEEE Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2024

作者： Men, Yutao Luo, Jian Zhao, Zixian Wu, Hang Luo, Feng Zhang, Guang Yu, Ming Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China Tianjin300384 China Systems Engineering Institute Academy of Military Sciences People's Liberation Army Tianjin300161 China

ISBN: (纸本)9798350370782

In the field of computer-aided medicine, automated surgical gesture recognition is an important research direction. Its main applications include automated skills assessment, intraoperative guidance, and education and training systems. Current research has focused on robotic surgery, and there is less research on surgical gestures for open surgery. Therefore, in this study, a new simulated open surgery dataset was developed, and a series of surgical gestures for open surgery were defined for closure the abdomen surgery with the cooperation of professional doctors. In addition, this paper uses the classical algorithm 3DCNN and SlowFast model in the field of action recognition to perform offline recognition of surgical gestures for open surgery on the dataset. 3DCNN uses R3D and R(2+1)D models. The experimental results show that on the self-built open surgical dataset, the R3D model has the best surgical gesture recognition results, with an accuracy rate of 90.4%, a precision rate of 90.5%, and a recall rate of 90.0%. © 2024 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Nitrogen-doping assisted local chemical heterogeneity and mechanical properties in CoCrMoW alloys manufactured via laser powder bed fusion

Advanced Powder Materials

引用

advanced Powder Materials 2024年第5期3卷 46-57页

作者： Wenting Jiang Ruidi Li Junyang He Song Ni Li Wang Zibin Chen Yi Huang Caiju Li Jianhong Yi Min Song State Key Laboratory of Powder Metallurgy Central South UniversityChangsha 410083China College of Materials and Advanced Manufacturing Hunan University of TechnologyZhuzhou 412007China Research Institute for Advanced Manufacturing Department of Industrial and Systems EngineeringThe Hong Kong Polytechnic UniversityHong KongChina Department of Design and Engineering Faculty of Science and TechnologyBournemouth UniversityPooleDorsetBH125BBUK Materials Research Group Department of Mechanical EngineeringUniversity of SouthamptonSouthamptonSO171BJUK Faculty of Materials Science and Engineering Kunming University of Science and TechnologyKunming 650093China

CoCrMoW alloys with different nitrogen(N)additions(0,0.05,0.1,and 0.2 wt%)were prepared via laser powder bed fusion(LPBF).The effects of N content on the microstructure and mechanical properties were *** results indicate that the LPBFed CoCrMoW alloy with 0.1 wt%N addition(0.1 N alloy)shows the best combination of mechanical properties with a yield strength of~983 MPa and an elongation of~19%.Both the LPBF process and the N addition impose great effects on suppressing theγtoεmartensitic transformation,resulting in a decrease in the width and amount ofεlaths/stacking ***,the N addition promotes the segregation of elements Mo,W,and Si along the cellular sub-grain boundaries(CBs),forming fine and discontinuous precipitates rich in Mo,W and Si along the CBs in the 0.1 N alloy,but dense and continuous(Mo,W)5Si_(3)precipitates along the CBs in the 0.2 N ***(Mo,W)5Si_(3)precipitates with a tetragonal structure were observed and characterized for the first time in the Co-Cr based *** negative mixing enthalpy between the non-metallic elements N,Si and the metallic elements Mo,W,Cr,and the rapid solidification induced segregation of high melting point elements such as Mo and W along CBs during LPBF process,synergistically contribute to the chemical heterogeneity in the *** pure FCC matrix,the slightly increased segregation of Mo,W,Si elements and fine precipitates along the CBs contribute to the good combination of strength and elongation of the 0.1 N ***,though pure FCC phase was present in the 0.2 N alloy,the dense and continuous(Mo,W)5Si_(3)precipitates along CBs acted as nucleation sites for cracks,deteriorating the elongation of the ***,it is possible to tune the mechanical properties of the LPBFed CoCrMoW alloy by adjusting the local chemical heterogeneity.

关键词： CoCrMoW alloy Laser powder bed fusion Nitrogen addition Mechanical properties Precipitation behaviors

来源：评论

学校读者我要写书评

暂无评论

Wireless Federated Learning With Hybrid Local and Centralized Training: A Latency Minimization design

引用

IEEE Journal on Selected Topics in Signal Processing 2023年第1期17卷 248-263页

作者： Huang, Ning Dai, Minghui Wu, Yuan Quek, Tony Q. S. Shen, Xuemin State Key Lab of Internet of Things for Smart City China University of Macau Department of Computer and Information Science China University of Macau State Key Laboratory of Internet of Things for Smart City The Department of Computer and Information Science China Zhuhai Um Science and Technology Research Institute Zhuhai519031 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore National Cheng Kung University Taiwan University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

Wireless federated learning (FL) is a collaborative machine learning (ML) framework in which wireless client-devices independently train their ML models and send the locally trained models to the FL server for aggregation. In this paper, we consider the coexistence of privacy-sensitive client-devices and privacy-insensitive yet computing-resource constrained client-devices, and propose an FL framework with a hybrid centralized training and local training. Specifically, the privacy-sensitive client-devices perform local ML model training and send their local models to the FL server. Each privacy-insensitive client-device can have two options, i.e., (i) conducting a local training and then sending its local model to the FL server, and (ii) directly sending its local data to the FL server for the centralized training. The FL server, after collecting the data from the privacy-insensitive client-devices (which choose to upload the local data), conducts a centralized training with the received datasets. The global model is then generated by aggregating (i) the local models uploaded by the client-devices and (ii) the model trained by the FL server centrally. Focusing on this hybrid FL framework, we firstly analyze its convergence feature with respect to the client-devices' selections of local training or centralized training. We then formulate a joint optimization of client-devices' selections of the local training or centralized training, the FL training configuration (i.e., the number of the local iterations and the number of the global iterations), and the bandwidth allocations to the client-devices, with the objective of minimizing the overall latency for reaching the FL convergence. Despite the non-convexity of the joint optimization problem, we identify its layered structure and propose an efficient algorithm to solve it. Numerical results demonstrate the advantage of our proposed FL framework with the hybrid local and centralized training as well as our proposed alg

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Multiscale Bilateral Attention Fusion Network for Pansharpening

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5828-5843页

作者： Guo, Zhongyuan Li, Jiawei Lei, Jia Liu, Jinyuan Zhou, Shihua Wang, Bin Kasabov, Nikola K. Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian116622 China University of the Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Dalian University of Technology School of Mechanical Engineering Dalian116024 China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland1061 New Zealand University of Ulster Intelligent Systems Research Center LondonderryBT48 7JL United Kingdom Bulgarian Academy of Sciences IICT Sofia1000 Bulgaria

High-resolution multispectral (HRMS) images combine spatial and spectral information originating from panchromatic (PAN) and reduced-resolution multispectral (LRMS) images. Pansharpening performs well and is widely used to obtain HRMS images. However, most pansharpening approaches determine the ratio of PAN and LRMS images through direct interpolation, which may introduce artifacts and distort the color of the fused results. To address this issue, an unsupervised progressive pansharpening framework, MSBANet, is proposed, which adopts a multistage fusion strategy. Each stage contains an attention interactive extraction module (AIEM) and a multiscale bilateral fusion module (MBFM). The AIEM extracts spatial and spectral features from input images and captures the correlations between features. The MBFM can efficiently integrate information from the AIEM and improve MSBANet context awareness. We design a hybrid loss function that enhances the ability of the fusion network to store spectral and texture details. In qualitative and quantitative experimental studies on four datasets, MSBANet outperformed state-of-the-art pansharpening techniques. The code will be released. © 2024 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Thermal management challenges and approaches for liquid hydrogen-fueled aircraft

Thermal management challenges and approaches for liquid hydr...

引用

AIAA Aviation Forum and ASCEND, 2024

作者： Ordonez, Juan C. Sailabada, Chaianan Guo, Wei Cooley, Lance Cheetham, Peter Kim, Chul Zheng, Jim P. Gladin, Jonathan Cattafesta, Louis FAMU-FSU College of Engineering Department of Mechanical Engineering Center for Advanced Power Systems and Energy and Sustainability Center Florida State University TallahasseeFL32310 United States Electrical and Computer Engineering FAMU-FSU College of Engineering and Center for Advanced Power Systems Florida State University TallahasseeFL32310 United States Center for Advanced Power Systems FAMU-FSU College of Engineering and Center for Advanced Power Systems Florida State University TallahasseeFL32310 United States Department of Electrical Engineering The State University of New York at Buffalo BuffaloNY14260 United States School of Aerospace Engineering Aerospace Systems Design Laboratory Georgia Institute of Technology AtlantaGA30332 United States Department of Mechanical Materials and Aerospace Engineering Illinois Institute of Technology ChicagoIL60616 United States

ISBN: (数字)9781624107160

ISBN: (纸本)9781624107160

This paper presents an overview of thermal management challenges associated with aircraft that rely on liquid hydrogen as the sole fuel source. The paper discusses strategies that can enhance the overall cooling capacity and enable a larger contribution of fuel cells to the overall power. design considerations for heat exchangers to integrate cryogenic hydrogen with secondary thermal management loops, outer mold line cooling, and additional thermal management strategies are presented. Cooling requirement estimates for a blended-wing aircraft (112 passengers, 2400 nautical miles) are reported. A finite element simulation using RANS suggests a cooling capacity rate of the order of 10 kW/m2 is available through the Outer Mold Line (OML). The paper also reports on the cooling capacity available by using hydrogen as a heat sink to cool the power train. For the IZEA concept, the hydrogen stream to the fuel cell can handle close to 6% of the fuel cell heat generation. © 2024, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Hydrogen fuels

来源：评论

学校读者我要写书评

暂无评论

Realizing high thermoelectric performance via selective resonant doping in oxyselenide BiCuSeO

引用

Nano Research 2023年第1期16卷 1679-1687页

作者： Yue-Xing Chen Wenning Qin Adil Mansoor Adeel Abbas Fu Li Guang-xing Liang Ping Fan Muhammad Usman Muzaffar Bushra Jabar Zhen-hua Ge Zhuang-hao Zheng F1 Shenzhen Key Laboratory of Advanced Thin Films and Applications Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong ProvinceCollege of Physics and Optoelectronic EngineeringShenzhen UniversityShenzhen 518060China Faculty of Materials and Manufacturing Beijing University of TechnologyBeijing 100124China International Center for Quantum Design of Functional Materials(ICQD) Hefei National Laboratory for Physical Sciences at Microscale(HFNL)and CAS Center for Excellence in Quantum Information and Quantum PhysicsUniversity of Science and Technology of ChinaHefei 230026China Faculty of Materials Science and Engineering Kunming University of Science and TechnologyKunming 650093China

Tuning the charge carrier concentration is imperative to optimize the thermoelectric(TE)performance of a *** BiCuSeO based oxyselenides,doping efforts have been limited to optimizing the carrier *** the present work,dual-doping of In and Pb at Bi site is introduced for p-type BiCuSeO to realize the electric transport channels with intricate band characteristics to improve the power factor(PF).Herein,the impurity resonant state is realized via doping of resonant dopant In over Pb,where Pb comes forward to optimize the Fermi energy in the dual-doped BiCuSeO system to divulge the significance of complex electronic *** manifold roles of dual-doping are used to adjust the elevation of the PF due to the significant enhancement in electrical ***,the combined experimental and theoretical study shows that the In/Pb dual doping at Bi sites gently reduces bandgap,introduces resonant doping states with shifting down the Fermi level into valence band(VB)with a larger density of state,and thus causes to increase the carrier concentration and effective mass(m*),which are favorable to enhance the electronic transport *** a result,both improved ZTmax=0.87(at 873 K)and high ZTave=0.5(at 300–873 K)are realized for InyBi(1−x)−yPbxCuSeO(where x=0.06 and y=0.04)*** obtained results successfully demonstrate the effectiveness of the selective dual doping with resonant dopant inducing band manipulation and carrier engineering that can unlock new prospects to develop high TE materials.

关键词： thermoelectric material BiCuSeO dual-doping power factor figure of merit

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：