检索结果-内蒙古大学图书馆

第40届中国控制会议

作者： Qian Liu Lijun Long Engineering Research Center of Intelligence Perception and Autonomous Control Ministry of Education Beijing Institute of Artificial Intelligence Faculty of Information TechnologyBeijing University of Technology College of Information Science and Engineering Northeastern University China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University

This paper provides some sufficient conditions to achieve asymptotic stability of switched systems under spatiotemporal specifications via a state-dependent switching law. A common finite-time barrier function, multiple barrier functions and multiple Lyapunov functions are merged as a tool for analyzing the asymptotic stability of a switched nonlinear system under spatio-temporal specifications. Finally, a numerical example is presented to demonstrate the effectiveness of our proposed method.

关键词： Switched systems Common finite-time barrier function Multiple barrier functions Multiple Lyapunov functions State-dependent switching law

来源：评论

学校读者我要写书评

暂无评论

A Multi-Object Grasping Detection Based on the Improvement of YOLOv3 Algorithm

A Multi-Object Grasping Detection Based on the Improvement o...

引用

第32届中国控制与决策会议

作者： Kun Du Jilai Song Xiaofeng Wang Xiang Li Jie Lin Faculty of Robot Science and Engineering Northeastern University Shenyang SIASUN Robot & Automation Co. LTD. State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of Sciences

YOLOv3 has achieved good results in the field of object *** order to achieve multi-object grasping detection,the network structure has been *** improved YOLOv3 algorithm is applied to the object position and pose detection in robotic grasping,and a deep learning model is proposed to predict the robot’s grasping position,which can detect the occurrence of multiple objects in real time and grasp them in order according to the semantic *** the specific application scenario,the corresponding dataset is made,and a corner detection method based on YOLOv3 is proposed to grasping position and pose *** with the traditional corner detection method,this method has semantic information in its detected *** the scene,we first classify and locate the object,then detect the corner of the object,and filter the corner of the false detection through the positioning of the object,and design the corresponding algorithm to complete the corner of the missed detection,so that the accuracy of the corner detection is greatly improved,reaching 99% in the self-made ***,the position information of the corner is used to calculate the centroid position of the object,that is,the grasping point of the *** point cloud information is obtained by depth camera,and the grasping pose of the object is *** method can greatly improve the accuracy of grasping detection in specific scenes.

关键词： YOLOv3 robotic grasping Deep learning Corner detection Grasping position and pose detection

来源：评论

学校读者我要写书评

暂无评论

Hamiltonian-Differential Flatness Control Laws for Battery/Ultracapacitor for Hybrid Electric Vehicle Applications

Hamiltonian-Differential Flatness Control Laws for Battery/U...

引用

2023 IEEE Transportation Electrification Conference and Expo, Asia-Pacific, ITEC Asia-Pacific 2023

作者： Mungporn, Pongsiri Khomfoi, Surin Inteeworn, Ridtee Gonmanee, Apinun Pierfederici, Serge Nahid-Mobarakeh, Babak Takorabet, Noureddine Bizon, Nicu Yodwong, Burin Thounthong, Phatiphat School of Engineering King Mongkut's Institute of Technology Ladkrabang Bangkok Thailand Provincial Electricity Authority Nakhonnayok Nakhonnayok Thailand Khon Kaen Technical College Institute of Vocational Education Department of Electronics Technology Northeastern Region 3 Khon Kaen40000 Thailand University of Lorraine Laboratoire d'Energetique et de Mecanique Théorique et Appliquée Umr 7563 Cnrs Vandœuvre-lès-Nancy54500 France McMaster University Electrical and Computer Engineering HamiltonONL8S 4L8 Canada Université de Lorraine ENSEM-GREEN Nancy54052 France The National University of Science and Technology Politehnica Bucharest Piteşti University Centre Pitesti110040 Romania Thai French Innovation Institute King Mongkut's University of Technology North Bangkok Bangkok Thailand King Mongkut's University of Technology North Bangkok Renewable Energy Research Centre Bangkok Thailand King Mongkut's University of Technology North Bangkok Faculty of Technical Education Department of Teacher Training in Electrical Engineering Bangkok Thailand

ISBN: (纸本)9798350314274

This paper introduces the Hamiltonian-differential flatness control laws specifically designed for battery and ultracapacitor (UC) hybrid vehicle systems. The main goal of these control laws is to effectively manage power flow and optimize energy utilization in hybrid systems combining batteries and UC. The proposed control laws use Hamiltonian control and differential flatness techniques to dynamically regulate the energy distribution between the battery and UC, particularly in the context of constant power load (CPL) challenges within DC Microgrid applications, including vehicle systems. To confirm the efficiency of the proposed control strategy, the experimental test bench has been set up with a Li-ion battery module (LFeLi-48100TB, 48 Vdc, 100 Ah) and a UC module with a capacitance of (188.88 F, 51.3 V.) Finally, the experimental results confirm the exceptional performance of the studied control law throughout the load-drive cycles. © 2023 IEEE.

关键词： Supercapacitor

来源：评论

学校读者我要写书评

暂无评论

Deep Residual Network Based Medical Image Reconstruction

Deep Residual Network Based Medical Image Reconstruction

引用

第三十八届中国控制会议

作者： Yifei Zhang Jianning Chi Chengdong Wu Xiaosheng Yu A College of Information Science and Engineering Northeastern University Faculty of Robot Science and Engineering Northeastern University

Recent years have witnessed the development of medical imaging technology. However, the process of imaging, storage and transmission often makes the image quality reduced and affects the visual and post-processing effect. The degradation of medical image often leads to the interference of noise and the decrease of resolution. In order to reconstruct the degraded medical image, a deep residual network combined with perceptual loss and mean square error(MSE) loss is proposed to enhance image quality. As a result, a single network can handle de-noising and super-resolution in same time. By using the residual network, the number of network layers can be deepen while the gradient dispersion problem can be avoided. More image edges and details can be reconstructed with the joint loss. Experiments on one medical image data set TCIA show that the proposed method can jointly perform de-noising and super-resolution to restore more medical image texture details and get better visual effect, especially for restraining noise in the low-dose CT image.

关键词： Deep residual network medical image reconstruction de-noise super-resolution joint loss

来源：评论

学校读者我要写书评

暂无评论

Person Re-identification Algorithm Based on the Fusion of Deep Feature and LOMO Feature

Person Re-identification Algorithm Based on the Fusion of De...

引用

2019第十一届数字图像处理国际会议

作者： Zi Liang Jianning Chi Ruzhao Hua Yue Zhang Wenhao Wang College of Information Science and Engineering Northeastern University Faculty of Robot Science and Engineering Northeastern University

Person Re-identification is a sub-problem of image retrieval,using computer vision techniques to judge whether a certain identical pedestrian exists among different images or video sequences,which has attracted more and more attention of *** this paper,regarding the fact that under non-overlapping multi-camera,traditional handcrafted features have a limited presentation power in re-identifying the pedestrians and that deep features have complicated parameters while training.A re-identification method based on the deep fusion of handcrafted features and deep features was proposed,which cut down the number of parameters but still guaranteed the accuracy,achieving the advancement of both precision and *** our model,the LOMO algorithm is used to extract the handcrafted features from the images ***,the dimensionality of those features are reduced by Guassian Pooling for *** that,they are connected to the deep fusion network with the deep features extracted from the same images by a modification of ***,the fused features are sent to the classifier for the *** the training process,we proposed a training strategy called Gradient Freezing after studying the training details in the application of transfer learning on neural *** have proved that the accuracy of applying the deep fusion network that fused with deep features and handcrafted features is 30% higher than that of the ResNet50 alone,and that the time it consumes is reduced by 10 epoches through the gradient freezing ***,several experiments carried out on dataset Marketl501 indicate that under Single Query on Marketl501,Rankl（the probability of matching successfully for the first time） can reach a high number of 81.74% and mAP（mean average Precision） of 68.75%.

关键词： Person search LOMO algorithm Residual neural network Feature fusion network

来源：评论

学校读者我要写书评

暂无评论

Asymmetry Total Variation and Framelet Regularized Nonconvex Low-Rank Tensor Completion

SSRN

引用

SSRN 2022年

作者： Chen, Yongyong Zhao, Xiaojia Xu, Tingting Zeng, Haijin Xu, Yanhui Chen, Junxing The School of Computer Science and Technology Harbin Institute of Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Shenzhen518055 China Image Processing and Interpretation Imec Research Group Ghent University Belgium Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau China The College of Medicine and Biological Information Engineering Northeastern University Shenyang110004 China

The low-rank tensor representation has shown enormous potential and advantages in diverse applications. However, (1) due to the inherent limitations of the low-rank tensor model, the tensor nuclear norm is utilized yet as a biased estimate of the tensor rank, which limits the image recovery performance. (2) most current low-rank approximation-based methods focus on the preservation of global information, while ignoring the local details preservation such as the spatial piece-wise smoothness and sharp edges. To overcome he above obstacles, we propose a novel asymmetry three-dimensional total variation and framelet regularized nonconvex low-rank tensor completion (ATV-FNTC) model, which integrates the nonconvex penalty function and asymmetric three-dimensional total variation into one unified model. Specifically, ATV-FNTC introduces one nonconvex penalty function as a tighter regularizer to approximate the tensor rank. Different from existing methods, the asymmetric three-dimensional total variation regularization is developed to achieve more accurate recovery of detailed information and flexibly control the smoothing strength of different dimensions of tensor data. Furthermore, we design an iterative algorithm to solve the nonconvex ATV-FNTC model by the alternating direction methods of multipliers. Experimental results reveal the superiority of the proposed method compared with several state-of-the-art methods when handling different completion tasks. © 2022, The Authors. All rights reserved.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

A Practical Method to Improve Absolute Positioning Accuracy of Industrial robot 2

A Practical Method to Improve Absolute Positioning Accuracy ...

引用

2019 2nd International Conference on Computer Information science and Artificial Intelligence, CISAI 2019

作者： Shi, Guosong Zhao, Shuying Hu, Baolong College of Information Science and Engineering Northeastern University Shenyang110819 China Quality and R and D Center Yuanda Intelligent Robot Co.Ltd Economic and Technological Development Zone No.27 Kaifa Road Shenyang110144 China

Industrial robots had been wildly used in modern factory. While the high repeatability of industrial robots can address most of need of process, their low absolute positioning ability cannot reach the demands of some high precision tasks. An example is if the action of the robot relies on the real-Time sampled data rather than the simulated data. The low absolute positioning ability of the robot will cause working performance far different away from expectation. For improving the absolute positioning accuracy as long as compile with the programs of automation integration projects, a practical general compensation method has been advanced. Our method also can be a compensation frame which can absorb new better model in the future. One application of this method in a project verifies the achievement of this method. © Published under licence by IOP Publishing Ltd.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Gaits generation from a mimetic word based on sound symbolism

引用

Transactions of the Japanese Society for Artificial Intelligence 2021年第5期36卷

作者： Kato, Hirotaka Hirayama, Takatsugu Doman, Keisuke Ide, Ichiro Kawanishi, Yasutomo Deguchi, Daisuke Murase, Hiroshi Graduate School of Informatics Nagoya University Japan Faculty of Human Environment University of Human Environments Japan School of Engineering Chukyo University Japan Mathematical and Data Science Center Japan Guardian Robot Project R-IH RIKEN Japan

The Japanese language is known to have a rich vocabulary of mimetic words, which have the property of sound symbolism;Phonemes that compose the mimetic words are strongly related to the impression of various phenomena. Especially, human gait is one of the most commonly represented phenomena by mimetic words expressing its visually dynamic state. Sound symbolism is useful for modeling the relation between gaits and mimetic words intuitively, but there has been no study on their intuitive generation. Most previous gait generation methods set specific class labels such as "elderly" but have not considered the intuitiveness of the generation model. Thus, in this paper, we propose a framework to generate gaits from a mimetic word based on sound symbolism. This framework enables us to generate gaits from one or more mimetic words. It leads to the construction of a generation model represented in a continuous feature space, which is similar to human intuition. Concretely, we train an encoder-decoder model conditioned by a "phonetic vector", a quantitive representation of mimetic words, with an adaptive instance normalization module inspired by style transfer. The phonetic vector is a dense description of the intuitive impression of a corresponding gait and is calculated from many mimetic words in the HOYO dataset, which includes gait motion data and corresponding mimetic word annotations. Through experiments, we confirmed the effectiveness of the proposed framework. © 2021, Japanese Society for Artificial Intelligence. All rights reserved.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

Synergistic chelating agents for in-situ synthesis of Mg-Al LDH films on PEO treated Mg alloy

引用

Journal of Magnesium and Alloys 2024年

作者： Chen, Qianqian Lu, Xiaopeng Serdechnova, Maria Wu, Ting Wieland, D.C. Florian Kasneryk, Valeryia Shulha, Tatsiana Liu, Huanye Blawert, Carsten Zheludkevich, Mikhail L. Wang, Fuhui Corrosion and Protection Center Northeastern University 3-11 Wenhua Road Shenyang110819 China Institute of Surface Science Helmholtz-Zentrum Hereon Max-Planck Straβe 1 Geesthacht21502 Germany Institute of Metallic Biomaterials Helmholtz-Zentrum Hereon Max-Planck Straβe 1 Geesthacht21502 Germany Liaoning Provincial Key Laboratory of Oral Diseases School and Hospital of Stomatology China Medical University Shenyang110001 China Faculty of Engineering University of Kiel Institute of Materials Research Kaiserstraβe 2 Kiel24143 Germany

In-situ growth of layered double hydroxide (LDH) has been considered a feasible method to further improve the corrosion protection of PEO coated Mg alloys, but the process is basically carried out in an autoclave. In this study, LDH was in-situ synthesized on PEO treated AM50 Mg by hydrothermal treatment at ambient pressure in the presence of chelating agents. Results indicated that the synergistic effect of sulfosalicylic acid (SSA) and ethylenediaminetetraacetic acid tetrasodium salt (EDTA) chelating agents is appropriate for Mg-Al LDH formation due to the sufficient quantity of highly stable Mg and Al complexes in the treatment bath. An appropriate hydrothermal treatment time was also revealed in this work, which can efficiently seal the pores and defects of PEO coating with a uniform LDH film. As a result, the corrosion protection of the coating was improved dramatically. The prolonged hydrothermal treatment is detrimental to the integrity of PEO layers. The influence of chelating agents on the LDH formation processes is supported by thermodynamic calculation of the equilibrium composition, and the formation mechanism of LDH film is discussed in depth. © 2024

关键词： Corrosion resistance

来源：评论

学校读者我要写书评

暂无评论

Localization of mobile robot based on multi-sensor fusion

Localization of mobile robot based on multi-sensor fusion

引用

Chinese Control and Decision Conference, CCDC

作者： Yu Gao Fei Wang Jinghong Li Yuqiang Liu College of Information Science and Engineering Northeast University Shenyang China Faculty of Robot Science and Engineering Northeast University Shenyang China

ISBN: (数字)9781728158556

ISBN: (纸本)9781728158563

In order to realize the precise positioning of mobile robot, the data information of multiple sensors needs to be collected by the localization system to enhance the state estimation ability of robot. Due to the need for accurate calibration and initialization of sensor groups, as well as the processing of measurement errors with different rates and delays, multi-sensor fusion still needs to solve many problems and faces many challenges. A method of multi-sensor fusion, which can analyze and screen the signal quality of sensors is proposed in this paper. Based on the extended Kalman filter, UWB data, IMU data and Lidar data are fused. By filtering and processing the sensor information, the impact of noise can be reduced. At the same time, the results of various sensor information fusion are closer to the actual results, and the mobile robot can be located.

关键词： Mobile robots Laser radar robot sensing systems Sensor systems Mathematical model

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：