检索结果-内蒙古大学图书馆

Axial Assembled Correspondence Network for Few-Shot Semantic Segmentation

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 711-721页

作者： Yu Liu Bin Jiang Jiaming Xu School of Automation Science and Engineering South China University of TechnologyGuangzhou 510640 R&D Center of Precision Electronic Manufacturing Technology Guangzhou Institute of Modern Industrial Technologyand also with the High Performance Motor and Intelligent Control Engineering Technology Research Center of Guangdong ProvinceGuangzhou 511458China School of Automation Science and Engineering South China University of TechnologyGuangzhou 510640China IEEE

Few-shot semantic segmentation aims at training a model that can segment novel classes in a query image with only a few densely annotated support *** remains a challenge because of large intra-class variations between the support and query *** approaches utilize 4d convolutions to mine semantic correspondence between the support and query ***,they still suffer from heavy computation,sparse correspondence,and large *** propose axial assembled correspondence network(AACNet)to alleviate these *** key point of AACNet is the proposed axial assembled 4d kernel,which constructs the basic block for semantic correspondence encoder(SCE).Furthermore,we propose the deblurring equations to provide more robust correspondence for the aforementioned SCE and design a novel fusion module to mix correspondences in a learnable *** on PASCAL-5~i reveal that our AACNet achieves a mean intersection-over-union score of 65.9%for 1-shot segmentation and 70.6%for 5-shot segmentation,surpassing the state-of-the-art method by 5.8%and 5.0%respectively.

关键词： Artificial intelligence computer vision deep convolutional neural network few-shot semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Low-Frequency Structure-Borne Noise Identification Based on FastICA-WPA Algorithm 8

Low-Frequency Structure-Borne Noise Identification Based on ...

引用

8th IEEE International Conference on advanced robotics and Mechatronics, ICArM 2023

作者： Liu, Qiang Zhu, Jianxin Sunward Intelligent Equipment Co. Ltd. National Enterprise R&D Center Hunan Research Center of Geotechnical Construction Equipment and Control Engineering Changsha410100 China Central South University State Key Laboratory for High Performance Complex Manufacturing Changsha410100 China

ISBN: (纸本)9798350300178

Low-frequency structure-borne noise in enclosed space is easy to produce booming sensation, which seriously affects the auditory comfort. But its sources are complex and the transmission path is strongly coupled, meanwhile it is difficult to be directly measured by experiments, so making identification difficult. To address the problem of decoupling multi-source mixed signals, this paper proposes a low-frequency structure-borne noise identification method based on FastICA-WPA algorithm. Using FastICA (Fast algorithm of Independent Component Analysis) algorithm to identify the structure-borne noise components in single-channel noise, then WPA (Wavelet Packet Analysis) method is applied to identify the low-frequency components of structure-borne noise. Finally decouple the contribution of low-frequency structure-borne noise. This method is applied to an intelligent excavator cab. The correctness of the method is verified by applying vibration signal correlation analysis. The identification algorithm lays the foundation for developing a low-frequency structure-borne noise control strategy. © 2023 IEEE.

关键词： Independent component analysis

来源：评论

学校读者我要写书评

暂无评论

Pressures monitored by 3d printed capacitive pressure sensor embedded on prosthetic upper-limb socket;a case study

引用

Journal of Biomechanical Science and Engineering 2021年第3期16卷 1-9页

作者： Lee, Sunkon Kwon, Hyeonjung Jung, Sung-Yoon Shin, Hyun-Jun Kwon, Chil-Yong Kim, Joo-Hyung Lab. of Intelligent Devices and Thermal Control Department of Mechanical Engineering Inha University 100 Inha-ro Michuhol-gu Incheon22212 Korea Republic of Advanced Prosthesis R&D Team Korea Orthopedics & Rehabilitation Engineering Center 10 Beon-gilGyeongin-ro Bupyeong-gu Incheon21417 Korea Republic of

The comfort fit of a limb prosthetic socket is one of the most important considerations for developing the socket for an amputee. The pressure at the touchpoint, which is the interface between the residual limb with natural skin and the prosthetic limb socket with a polymeric material, should be monitored precisely when fabricating the comfort fit. Even a small volume or shape discrepancy between the residual limb and prosthetic limb sock causes several problems in the residual limb, such as skin breakage, tissue irritation, and associated pain. Volume variations of the residual limb due to squeezing by a prosthetic limb sock result in pressure changes that can be detected using a pressure sensor. In this study, the interface pressures between the residual limb and prosthetic upper-limb socket were obtained using a 3d printed capacitive pressure sensor. An upper-limb prosthetic socket and capacitive pressure sensor were fabricated using a dual nozzle 3d Fused deposition Modelling technique. Polylactic acid, polylactic acid-carbon black compound, and polyurethane were used as the personalized upperlimb socket and sensing electrode, and substrate material, respectively. The as-fabricated sensors were embedded into the sock wall, and their sensing properties were characterized. For a case study, the sensor-embedded sockets were worn on an amputee's residual upper-limb to characterize empirically the contact pressure occurring at the interfaces. A weight was attached to the end of the limb socket to examine the effects of weight on the local pressures acting on the residual upper limb. The observed interface pressures and pressure distribution at the interface can provide valuable information to clinicians and developers that can guide fit improvements. © 2021. All rights reserved.

关键词： Pressure sensors

来源：评论

学校读者我要写书评

暂无评论

Low-Frequency Structure-Borne Noise Identification Based on FastICA-WPA Algorithm

Low-Frequency Structure-Borne Noise Identification Based on ...

引用

International Conference on advanced robotics and Mechatronics (ICArM)

作者： Qiang Liu Jianxin Zhu National Enterprise R&D Center Hunan Research Center of Geotechnical Construction Equipment and Control Engineering Sunward Intelligent Equipment Co. Ltd. Changsha China State Key Laboratory for High Performance Complex Manufacturing Central South University Changsha China

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Improvement for the Cmos rail-to-rail Amplifier Via Apso-Based design and Snn's Training

SSRN

引用

SSrN 2023年

作者： Liu, Xianming Wu, Shihong Xiao, Wenrun Zhao, Chenhui Guo, donghui School of Electronic Science and Engineering R&D Center of Integrated Circuit Xiamen University Fujian Xiamen361005 China School of Physics Electronics and Intelligent Manufacturing Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua University Hunan Huaihua418000 China Ningbo Institute of Artificial Intelligence Industry Zhejiang Ningbo315100 China

In this paper, a Spiking Neural Network optimization assisted design method for analogintegrated circuits is proposed. The optimization procedure includes adaptive particle swarmoptimization(APSO) search program and SNN Training. The application of APSO algorithmachieves global optimization, and the sample practical user-defined specifications are simulatedby SPICE parallelly. Then, the sampled practical data and the optimal result is used for traininga spiking neural network(SNN) model, and the optimal fitness value is calculated and ranked byAPSO algorithm. The SNN model is used to capture the relation between the inputs (transistorsize, currents) and outputs (frequency characteristic) of the circuit module. The optimizationframework for performance improvement is applied in a rail-to-rail amplifier with constant gmtechnology. Simulation results show that the performance is enhanced obviously by the proposedoptimization algorithms. Compared with traditional approaches, the proposed method providesabout one times speed enhancement and the accuracy of SNN model is up to 99.73%. © 2023, The Authors. All rights reserved.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

research on Obstacle Avoidance Technology for Unmanned Aerial Vehicles Based on Panoramic Visual Perception

引用

Journal of Computers (Taiwan) 2024年第3期35卷 345-361页

作者： Jiang, Xiao-Yan Han, Mei Zhang, Jun-Kai Wu, Xiao-Fei Zhang, Xiao-Yang Hebei Institute of Mechanical and Electrical Technology Hebei Province Xingtai City054000 China Hebei Province Mechanical and Electrical Equipment Intelligent Sensing and Advanced Control R&D Center Hebei Province Xingtai City054000 China

With the continuous increase of market demand, the application of low altitude rotary wing unmanned aerial vehicles is becoming increasingly widespread, and the requirements for active obstacle avoidance ability and endurance time are also increasing. This article focuses on the active obstacle avoidance technology of drones. The panoramic camera is installed on the drone. For the collected multi camera images, the first step is to perform stitching processing. The improved SUrF algorithm is used to process the overlapping defects after image stitching. Then, the image is weighted and fused using the arc function weighted fusion image stitching algorithm to remove the stitching gaps. The fused image is used as input, and the improved YOLOv8 model is used as the target recognition model. After analyzing the basic performance of the model, in order to improve the algorithm’s lightweight level, the LAd calculation rule is integrated into the algorithm. Then, the EMA attention mechanism is added to improve the model’s recognition ability for specific obstacles, and depth separable convolution is added to enhance the algorithm’s ability to extract target features. Finally, an experimental environment was established, and through simulation experiments, the method proposed in this article improved the average recognition accuracy of obstacles by 2.3% while ensuring the endurance of the drone. © 2024 Codon Publications. All rights reserved.

关键词： drones

来源：评论

学校读者我要写书评

暂无评论

Applications of MXenes in human-like sensors and actuators

引用

Nano research 2023年第4期16卷 5767-5795页

作者： Jinbo Pang Songang Peng Chongyang Hou Xiao Wang Ting Wang Yu Cao Weijia Zhou ding Sun Kai Wang Mark H.rümmeli Gianaurelio Cuniberti Hong Liu Institute for Advanced Interdisciplinary Research(iAIR) Collaborative Innovation Center of Technology and Equipment for Biological Diagnosis and Therapy in Universities of ShandongUniversity of JinanJinan 250022China Institute for Materials Science and Max Bergmann Center of Biomaterials Technische Universität DresdenDresden 01069Germany Center for Advancing Electronics Dresden Technische Universität DresdenDresden 01069Germany Dresden Center for Computational Materials Science Technische Universität DresdenDresden 01062Germany Dresden Center for Intelligent Materials(GCL DCIM) Technische Universität DresdenDresden 01062Germany High-Frequency High-Voltage Device and Integrated Circuits R&D Center Institute of MicroelectronicsChinese Academy of SciencesBeijing 100029China Key Laboratory of Microelectronic Devices&Integrated Technology Institute of MicroelectronicsChinese Academy of SciencesBeijing 100029China Shenzhen Key Laboratory of Nanobiomechanics Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China State Key Laboratory of Biobased Material and Green Papermaking Qilu University of TechnologyShandong Academy of SciencesJinan 250353China School of Bioengineering Qilu University of TechnologyShandong Academy of ScienceJinan 250353China Key Laboratory of Modern Power System Simulation and Control&Renewable Energy Technology(Ministry of Education) Northeast Electric Power UniversityJilin 132012China School of Electrical Engineering Northeast Electric Power UniversityJilin 132012China School of Electrical Engineering Weihai Innovation Research InstituteQingdao UniversityQingdao 266000China School of Electrical and Computer Engineering Jilin Jianzhu UniversityChangchun 130118China Institute for Complex Materials Leibniz Institute for Solid State and Materials Research Dresden(IFW Dresden)20 Helmholtz StrasseDresden 01069Germany College of Energy Soochow Institute for Energy and Materials Innovations Soochow UniversitySuzhou 215006China Key L

Human beings perceive the world through the senses of sight,hearing,smell,taste,touch,space,and *** first five senses are prerequisites for people to *** sensing organs upload information to the nervous systems,including the brain,for interpreting the surrounding ***,the brain sends commands to muscles reflexively to react to stimuli,including light,gas,chemicals,sound,and ***,as an emerging two-dimensional material,has been intensively adopted in the applications of various sensors and *** this review,we update the sensors to mimic five primary senses and actuators for stimulating muscles,which employ MXene-based film,membrane,and composite with other functional ***,a brief introduction is delivered for the structure,properties,and synthesis methods of ***,we feed the readers the recent reports on the MXene-derived image sensors as artificial retinas,gas sensors,chemical biosensors,acoustic devices,and tactile sensors for electronic ***,the actuators of MXene-based composite are ***,future opportunities are given to MXene research based on the requirements of artificial intelligence and humanoid robot,which may induce prospects in accompanying healthcare and biomedical engineering applications.

关键词： MXenes sensors actuators gas sensors biosensors tactile sensors sound sensors artificial retina

来源：评论

学校读者我要写书评

暂无评论

Plastic Shavings by Laser: Peeling Porous Graphene Springs for Multifunctional All-Carbon Applications

引用

advanced Science 2023年第21期10卷 e2301208页

作者： Kim, Chanwoo Hwang, Eunseung Kwon, Jinhyeong Jang, Tae Hwan Lee, Won Chul Kim, Shi Hyeong Park, Jongmin Lee, Ming-Tsang Kim, Hyun Hong, Sukjoon Lee, Habeom School of Mechanical Engineering Pusan National University Busan46241 Korea Republic of Optical Nanoprocessing Lab Department of Mechanical Engineering BK21 FOUR ERICA ACE Center Hanyang University Gyeonggi-do Ansan15588 Korea Republic of Intelligent Manufacturing System R&D Department Korea Institute of Industrial Technology Chungcheongnam-do Cheonan31056 Korea Republic of Division of Electrical Engineering Hanyang University ERICA Gyeonggi-do Ansan15588 Korea Republic of Department of Mechanical Engineering BK21 FOUR ERICA ACE Center Hanyang University Gyeonggi-do Ansan15588 Korea Republic of Department of Advanced Textile R&D Korea Institute of Industrial Technology Gyeonggi-do Ansan15588 Korea Republic of HYU-KITECH Joint Department Hanyang University Seoul04763 Korea Republic of Advanced Materials Division Korea Research Institute of Chemical Technology Daejeon34114 Korea Republic of Department of Power Mechanical Engineering National Tsing Hua University Hsinchu30013 Taiwan

manufacturing strategies to create three-dimensional (3d) structures with multifunctional nanomaterials are of intense interest for fabricating building blocks in many electromechanical applications. A coil spring composed of graphene provides an important step toward the realization of all-carbon devices, as it is one of the essential elements for a wide range of systems. In this connection, here an unprecedented fabrication strategy to create a new type of 3d coil spring composed of laser-induced graphene springs (LIG-S) which is spontaneously produced via the pyrolytic jetting technique, is presented. Similar to wood or metal shavings observed in traditional machining processes, a pair of LIG-S with two opposite chiralities and controllable macroscopic dimensions is produced by a single scanning of a focused continuous-wave (CW) laser on a polyimide (PI) substrate. The resulting LIG-S, plastic shavings by laser, exhibits sufficient mechanical and electrical properties to enable many applications including strain-tolerant spring electrodes, antennas, supercapacitors, gas sensors, and luminescent filaments under extreme conditions. Without using any conventional fabrication techniques or other labor-intensive, time-consuming, and expensive processes, this novel approach enables a high-throughput mass production of macro-, micro-, and nanoscale featured LIG-S that can be manufactured within seconds to realize many open opportunities in all-carbon electromechanical systems. © 2023 The Authors. advanced Science published by Wiley-VCH GmbH.

关键词： Fabrication

来源：评论

学校读者我要写书评

暂无评论

depth-Map-Based Augmented reality Holographic Stereogram: Method and Verification

SSRN

引用

SSrN 2022年

作者： Liu, Yunpeng Jing, Tao Lei, Ming Hu, Hairong Chen, Zhuo Lin, Min Li, Pei Jiang, Xiaoyu Yan, Xingpeng Department of Information Communication Army Academy of Armored Forces Beijing100072 China China Defense Science and Technology Information Center Beijing100037 China Department of Basic Education Army Academy of Armored Forces Beijing100072 China R & D Center for Intelligent Control and Advanced Manufacturing Research Institute of Tsinghua University in Shen Zhen Shen Zhen518057 China Department of Artificial Intelligence College of Information Systems Engineering Strategic Support Force Information Engineering University Zhengzhou450001 China

In this paper, a perspective image fusion algorithm of real-world and artificial scenes based on depth maps is proposed and applied to holographic printing to realize augmented reality display of holographic stereograms. The basic principle of the fusion algorithm is introduced, and the perspective image fusion with correct occlusion relation is implemented theoretically. Under the condition of sampling only once, an image generation algorithm with adjustable depth of artificial scenes is proposed and implemented. We use effective perspective image segmentation and mosaicking method for optical experiments, and verify the effectiveness of the proposed method. © 2022, The Authors. All rights reserved.

关键词： Three dimensional displays

来源：评论

学校读者我要写书评

暂无评论

In-depth mechanism analysis for negative differential resistance coupled resistance switching behavior in multiple factors regulated MoO x /MoO y -stacked memristor

引用

Materials research Bulletin 2025年 192卷

作者： Jiajia Qin Bai Sun Shuangsuo Mao Mingnan Liu Zhaowei rao Wei Lin Yulong Yang Yong Zhao Fujian Provincial Collaborative Innovation Center for Advanced High-Field Superconducting Materials and Engineering College of Physics and Energy Fujian Normal University Fuzhou 350117 China Frontier Institute of Science and Technology (FIST) Xi’an Jiaotong University Xi'an Shanxi 710049 China School of Intelligent Manufacturing Sichuan University of Arts and Science Dazhou 635000 China Superconductivity and New Energy R&D Center Southwest Jiaotong University Chengdu Sichuan 610031 China

It is well known that memristors have low-power parallel brain-like computing capabilities and fast data/information/image processing efficiency. It will have application prospects if devices with multiple physical characteristics can be developed, especially playing an important role in the next generation of artificial intelligence (AI). In this work, a double-layer stacked memristor with the structure of Ag/MoO x /MoO y /fluorine doped tin oxide (FTO) was synthesized by magnetron sputtering (MS). The memristor presents the evolution of resistance switching (rS) behavior and negative differential resistance (Ndr) coupled rS (NrS) behavior by adjusting the operating voltage. It was also observed that rS behavior of the memristor was obviously enhanced with the increase of oxygen content, and even the Ag/MoO x /MoO y /FTO device still exhibit excellent rS behavior at high temperature. More importantly, the temperature coefficient of the Ag/MoO x /MoO y /FTO device in low resistance state (LrS) was calculated to demonstrate that the formation and fracture of Ag conductive filaments (CFs) have an important impact on the rS behavior of memristor. Therefore, this work not only provides theoretical proof for a deeper understanding of the physical mechanism of rS behavior, but also it expands the path for developing high-capacity memristor with high temperature resistance and multi-level storage.

关键词： Artificial intelligence Conductive filament Mechanism analysis Memristor resistive switching

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：