检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Jiasen Li Jianxin Zhang Qiule Sun Hengbo Zhang Jing Dong Chao Che Qiang Zhang Key Lab of Advanced Design and Intelligent Computing (Ministry of Education) Dalian University Dalian China School of Computer Science and Engineering Dalian Minzu University Dalian China School of Information and Communication Engineering Dalian University of Technology Dalian China School of Computer Science and Technology Dalian University of Technology Dalian China

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

With the breakthrough performance in a variety of computer vision and medical image analysis problems, convolutional neural networks (CNNs) have been successfully introduced for the classification task of breast cancer histopathological images in recent years. Nevertheless, existing breast cancer histopathological image classification networks mainly utilize the first-order statistic information of deep features to represent histopathological images, failing to characterize the complex global feature distribution of breast cancer histopathological images. To address the problem, this work makes a first attempt to explore global second-order statistics of deep features for the above task. More specifically, we propose a novel deep second-order pooling network (DSoPN) for breast cancer histopatho-logical image classification, in which a robust global covariance pooling module based on matrix power normalization (MPN) is embedded into a simple yet effective CNN architecture. The given DSoPN model can capture richer second-order statistical information of deep convolutional features and produce more informative global representations for breast cancer histopatho-logical images. Experimental results on the public BreakHis dataset illuminate the promising performance of the second-order pooling for breast cancer histopathological image classification. Besides, our DSoPN achieves very competitive performance compared to the state-of-the-art methods.

关键词： Breast cancer Covariance matrices Task analysis Feature extraction Computer architecture Pathology

来源：评论

学校读者我要写书评

暂无评论

Probing dynamics and ion structuring of imidazolium ionic liquid confined at charged graphene surfaces using graphene colloid probe AFM

引用

Friction 2025年第6期13卷 151-161页

作者： Muqiu Wu Zhongyang Dai Fan Zhang Faiz Ullah Shah Enrico Gnecco Yijun Shi Braham Prakash Rong An 2State Key Laboratory of Solid Lubrication Lanzhou Institute of Chemical Physics Chinese Academy of Sciences Lanzhou 730000 China 3Shandong Laboratory of Advanced Materials and Green Manufacturing at Yantai Yantai 264006 China 1School of Materials Science and Engineering/Herbert Gleiter Institute of Nanoscience Nanjing University of Science and Technology Nanjing 210094 China 4High Performance Computing Department National Supercomputing Center in Shenzhen Shenzhen 518055 China 5Department of Engineering and Design School of Engineering and Information University of Sussex Brighton BN1 9RH UK 6Chemistry of Interfaces Luleå University of Technology Luleå 97187 Sweden 7Marian Smoluchowski Institute of Physics Jagiellonian University Krakow 30-348 Poland 8Division of Machine Elements Luleå University of Technology Luleå 97187 Sweden

Driven by the potential applications of ionic liquid (IL) flow for charging graphene-based surfaces in many emerging technologies, recent research efforts have focused on understanding ion dynamics and structuring at IL–graphene interfaces. Here, graphene colloid probe (GrP) atomic force microscopy (AFM) was used to probe the dynamics and ion structuring of 1-butyl-3-methylimidazolium tetrafluoroborate at graphene surfaces under various bias voltages. In particular, the AFM-measured nanofriction provides a good measure of the dynamic properties of the ILs at graphene surfaces. Compared with the IL at the unbiased graphene surface (0 V), the charged graphene surfaces with either negative (–1, –2 V) or positive (+1, +2 V) voltages favor a reduction in the friction coefficient by the IL. A higher magnitude of the bias voltage applied on the graphene surface with either sign (–2 or +2 V) results in a smaller friction coefficient than that at –1 and +1 V. In combination with the AFM-probed contact stiffness, adhesion forces, and ion structuring force curves with an ion orientational distribution according to molecular dynamics (MD) simulations, we discovered that the unbiased graphene surface (0 V) possesses randomly structured IL ions and that the graphene colloid probe is more likely to become stuck, resulting in more energy dissipation to contribute to a larger friction coefficient. Biasing of the graphene surface under either negative or positive voltages resulted in uniformly arranged ions, which produced a more ordered ion structure and, thus, a smoother sliding plane to reduce the friction coefficient. Electrochemical impedance spectroscopy (EIS) for the IL with graphene as an electrode demonstrated a greater ionic conductivity in the IL paired with the biased graphene than in the unbiased one, implying faster ion movement at the charged graphene, which is beneficial for reducing the friction coefficient.

关键词： nanofriction graphene charge ionic liquid (IL) IL arrangement simulation

来源：评论

学校读者我要写书评

暂无评论

Distributed model predicted control of multi-agent systems with applications to multi-vehicle cooperation

arXiv

引用

arXiv 2020年

作者： Bian, Yougang Du, Changkun Hu, Manjiang Liu, Haikuo State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body College of Mechanical and Vehicle Engineering Hunan University Changsha410082 China Beijing Advanced Innovation Center for Intelligent Robots and Systems School of Mechatronical Engineering Beijing Institute of Technology Beijing100081 China School of Mechatronical Engineering Beijing Institute of Technology Beijing100081 China

This paper proposes a distributed model predicted control (DMPC) approach for consensus control of multi-agent systems (MASs) with linear agent dynamics and bounded control input constraints. Within the proposed DMPC framework, each agent exchanges assumed state trajectories with neighbors and solves a local open-loop optimization problem to obtain the optimal control input. In the optimization problem, a discrete-time consensus protocol is introduced into update law design for assumed terminal states, with which asymptotic consensus of assumed terminal states and recursive feasibility are rigorously proved. Together with the optimal cost function, an infinite series of cost-to-go functions is introduced into the design of a Lyapunov function, with which closed-loop asymptotic consensus is finally proved. Two applications including cooperation of autonomous underwater vehicles (AUVs) and connected and automated vehicles (CAVs) are used to validate the effectiveness of the proposed DMPC approach. Copyright © 2020, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Research on Feedforward Control Based on Robot Dynamics Parameters Identification

Research on Feedforward Control Based on Robot Dynamics Para...

引用

IEEE International Conference on Mechatronics and Automation

作者： Xingmao Shao Shoujun Wang Liusong Yang Nan Liu Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Tianjin China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin China CITIC Heavy Industries Company Ltd. Luoyang China

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

Accurate robot dynamics model can effectively improve the motion control performance of robot, and accurate dynamics parameters are the basis for establishing dynamics model. This paper discusses the parameter identification method of the tandem manipulator and the feedforward control scheme based on dynamics. First, we deduced the basic parameters of the first three joints of the UR5 manipulator, and identified the parameters through experimental sampling and calculation. Secondly, we established a feedforward control mechanism based on dynamics using the Simulink platform, and simulated and verified the feedforward control of the robot three-axis system. The experimental results show that the feedforward control scheme based on robot dynamics can effectively improve the error convergence performance, which proves the effectiveness of the method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Swimming Characteristics of Soft robot with Magnetoelastic Material

Swimming Characteristics of Soft robot with Magnetoelastic M...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Hongbiao Xiang Mengwei Li Tilei Zhang Shoujun Wang Xiuping Yang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin China

Cable-less micro-robots have exhibit great capabilities for remote applications in small and constrained environments, especially in biotechnology and healthcare. This paper presents a swimmer propelled by its undulatory deformation using magnetoelastic composite material. The robot can move freely on water surface driven through a function of magnetic field, such as forward, backward and steering with different velocity. The magnetic field is generated by 3D Helmholtz coils, and the locomotion of the micro swimming robot is controlled by different applied magnetic field. To understand the characteristics of the swimmer, the force balance equation is established, and the morphologies of swimmer with different magnetic field are analyzed and described through finite element analysis method. Furthermore, we discuss and analyze relationship between the parameters of magnetic field and the speed of the swimmer. The experimental results verified the speed model of the swimming robot, which is influenced by the frequency and strength of magnetic field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Based on Contextual Generative Adversarial Network

Facial Expression Recognition Based on Contextual Generative...

引用

IEEE International Conference on Cloud computing and Intelligence Systems (CCIS)

作者： Qian Chu Min Hu Xiaohua Wang Yu Gu Tian Chen Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and Information Hefei University of Technology Hefei Anhui China

ISBN: (数字)9781728138633

ISBN: (纸本)9781728138640

In recent years, deep neural networks have been widely concerned by researchers in facial expression recognition. However, insufficient facial training data of the public available database is a major challenge in deep learning, which will lead to an obvious decrease in the effectiveness of learning result; many data augmentation techniques have thus been widely used to enrich the training dataset. In this paper, we introduce a contextual loss function to construct a Contextual Generation Adversarial Network with one generator and one discriminator. The proposed method can map the neutral expression to six basic expressions to expand the database. The experimental results on CK + and KDEF databases show that the proposed method can effectively improve the ability to extract facial features and the ability to generate higher quality images. The data augmentation used the proposed method improves the recognition rate of facial expressions on KDEF and CK + datasets.

关键词： XML

来源：评论

学校读者我要写书评

暂无评论

SI-YOLO: A Deep Learning Algorithm Suitable for Surgical Instrument Detection

SSRN

引用

SSRN 2022年

作者： Liu, Zhenzhong Zhou, Yifan Sun, Qiyuan Wang, Yan Polat, Kemal Nour, Majid Alenezi, Fayadh Alhudhaif, Adi Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China Tianjin300384 China Department of Electrical and Electronics Engineering Bolu Abant Izzet Baysal University Bolu14280 Turkey Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia Department of Electrical Engineering College of Engineering Jouf University 72238 Saudi Arabia Department of Computer Science College of Computer Engineering and Sciences in Al-kharj Prince Sattam bin Abdulaziz University P.O. Box 151 Al-Kharj 11942 Saudi Arabia

Surgical instrument detection and tracking is one of the core technologies of surgical robots, which can assist clinicians in completing operations. However, existing methods need further improvement in terms of real-time performance and accuracy. We propose a deep learning algorithm, SI-YOLO, for detection of surgical instruments. SimAM attention mechanism is used to improve the feature extraction ability of YOLOv5. Replacing PANet with BiFPN in the neck network improves the feature fusion strategy. The α-IoU loss function is used to improve the regression accuracy of detection boxes. The mAP and FPS of the SI-YOLO reach 99.2% and 120 frames/sec, respectively. Aiming at the problem of ID transformation in the disappearance and occlusion of surgical instruments, the Inception-ResNet-v2 structure is added on the basis of the appearance feature extraction network Cosine of the DeepSort tracking algorithm. Combining SI-YOLO with the improved DeepSort implements the Tracking by Detection (TBD) algorithm. In the case of device disappearance or occlusion, the frequency of ID transitions is reduced by approximately 30%. Finally, we built a simulated surgery experimental platform, established our own data set, and realized the preliminary application of the proposed algorithm. © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Fused behavior recognition model based on attention mechanism

引用

Visual computing for industry, biomedicine, and art 2020年第1期3卷 7页

作者： Lei Chen Rui Liu Dongsheng Zhou Xin Yang Qiang Zhang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Dalian University Dalian 116622 China. Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Dalian University Dalian 116622 China. liurui@***. School of Computer Science and Technology Dalian University of Technology Dalian 116024 China.

With the rapid development of deep learning technology, behavior recognition based on video streams has made great progress in recent years. However, there are also some problems that must be solved: (1) In order to improve behavior recognition performance, the models have tended to become deeper, wider, and more complex. However, some new problems have been introduced also, such as that their real-time performance decreases; (2) Some actions in existing datasets are so similar that they are difficult to distinguish. To solve these problems, the ResNet34-3DRes18 model, which is a lightweight and efficient two-dimensional (2D) and three-dimensional (3D) fused model, is constructed in this study. The model used 2D convolutional neural network (2DCNN) to obtain the feature maps of input images and 3D convolutional neural network (3DCNN) to process the temporal relationships between frames, which made the model not only make use of 3DCNN's advantages on video temporal modeling but reduced model complexity. Compared with state-of-the-art models, this method has shown excellent performance at a faster speed. Furthermore, to distinguish between similar motions in the datasets, an attention gate mechanism is added, and a Res34-SE-IM-Net attention recognition model is constructed. The Res34-SE-IM-Net achieved 71.85%, 92.196%, and 36.5% top-1 accuracy (The predicting label obtained from model is the largest one in the output probability vector. If the label is the same as the target label of the motion, the classification is correct.) respectively on the test sets of the HMDB51, UCF101, and Something-Something v1 datasets.

关键词： Action recognition Attention mechanism Res34-SE-IM-net ResNet34-3DRes18

来源：评论

学校读者我要写书评

暂无评论

Simulation of Passenger Evacuation of High-speed Train Cars 9

Simulation of Passenger Evacuation of High-speed Train Cars

引用

9th International Conference on Fire Science and Fire Protection Engineering, ICFSFPE 2019

作者： Huang, Shenshi Wei, Ruichao Shi, Kai Hu, Jinxing Lu, Shouxiang Lian, Liping Institute of Advanced Computing and Digital Engineering Shenzhen Institute of Advanced Technology Chinese Academy of Science Shenzhen China Smart City Research Institute of China Electronics Technology Group Corporation Shenzhen China State Key Laboratory of Fire Science University of Science and Technology of China Hefei China School of Urban Planning and Design Peking University Shenzhen China

ISBN: (纸本)9781728153223

This study is to evaluate the passenger evacuation of the high-speed train. Geometry was built up based on current Chinese train type CRH380B, and scenarios were designed according to the current emergency response plans. Simulation runs were performed by Pathfinder and uncertainty of evacuation time was obtained. It is observed that the passenger flow rates in train coaches are generally stable. Passenger transfer time and evacuation time are approximately proportional to passenger attendance rate. However, in some complicated scenarios, it is found that the process of passenger transfer affects the evacuation results a lot. Reasonable passenger transfer scale can maximize the effectiveness of emergency plans. This study provides an evaluation method on the topic of train car evacuation, and future work can be carried out to optimize the design of emergency response. © 2019 IEEE.

关键词： Railroad cars

来源：评论

学校读者我要写书评

暂无评论

I3−/I−Redox Reaction-mediated Organic Zinc-Air Batteries with Accelerated Kinetics and Long Shelf Lives

引用

Angewandte Chemie 2023年第26期135卷

作者： Mangwei Cui Ninggui Ma Hao Lei Youfa Liu Wei Ling Sheng Chen Jiaqi Wang Prof. Hongfei Li Zhaohui Li Prof. Jun Fan Prof. Yan Huang State Key Laboratory of Advanced Welding and Joining Sauvage Laboratory for Smart Materials Shenzhen Key Laboratory of Flexible Printed Electronics Technology School of Materials Science and Engineering Harbin Institute of Technology (Shenzhen) Shenzhen 518055 China Department of Materials Science and Engineering City University of Hong Kong 83 Tat Chee Avenue Kowloon Hong Kong 999077 China Key Laboratory of Radiation Physics and Technology of Ministry of Education Institute of Nuclear Science and Technology Sichuan University Chengdu 610064 China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen 518055 China Songshan Lake Materials Laboratory Dongguan 523808 China Shenzhen China Star Optoelectronic Semiconductor Display Technology Co. Ltd. Shenzhen 518055 China

The storage time of Zn-air batteries (ZABs) for practical implementation have been neglected long-lastingly. ZABs based on organic solvents promise long shelf lives but suffer from sluggish kinetics. Here, we report a longly storable ZAB with accelerated kinetics mediated by I 3 − /I − redox. In the charge process, the electrooxidation of Zn 5 (OH) 8 Cl 2 ⋅H 2 O is accelerated by I 3 − chemical oxidation. In the discharge process, I − adsorbed on the electrocatalyst changes the energy level of oxygen reduction reaction (ORR). Benefitting from these advantages, the prepared ZAB shows remarkably improved round-trip efficiency (56.03 % vs. 30.97 % without the mediator), and long-term cycling time (>2600 h) in ambient air without replacing any components or applying any protective treatment to Zn anode and electrocatalyst. After resting for 30 days without any protection, it can still directly discharge continuously for 32.5 h and charge/discharge very stably for 2200 h (440 cycles), which is evidently superior to aqueous ZABs (only 0/0.25 h, and 50/25 h (10/5 cycles) by mild/alkaline electrolyte replenishment). This study provides a strategy to solve both storage and sluggish kinetics issues that have been plaguing ZABs for centuries, opening up a new avenue to the industrial application of ZABs.

关键词： Iodine-Containing Reaction Kinetics Redox Mediators Storage Time Zn-Air Batteries

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：