检索结果-内蒙古大学图书馆

IEEE International Conference on Mechatronics and Automation

作者： Bangqiang Cheng Lei Sun School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China Tianjin Key Laboratory for Control Theory and Complicated Industry Systems Tianjin University of Technology Tianjin China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

In unstructured environments, achieving fast and accurate object detection and successful grasping presents a significant challenge. Current grasping detection networks primarily focus on reducing the network's floating point operations (FLOPs) to improve network speed. However, we found that the effectiveness of this method is not particularly significant. To address this issue, we employed partial convolution (PConv) in place of regular convolutions to significantly enhance the network's detection speed. Additionally, we implemented a parallel structure for the network to fuse low-level and high-level features, reducing the loss of detail information during the decoding process. Our proposed faster grasp detection network (FGNet) achieved a performance of 96.74% (ow) and 98.66% (iw) on the Cornell dataset, with a detection speed of only 11ms. The grasping success rate was 96.5% in single-object scenarios and 92% in cluttered grasping scenarios.

关键词： Training Accuracy Mechatronics Convolution Fuses Grasping Object detection

来源：评论

学校读者我要写书评

暂无评论

Improved Event-Triggered Sequential Fusion Filter for Cluster Sensor Networks with Deceptive Attacks

SSRN

引用

SSRN 2024年

作者： Liu, Weicheng Cheng, Guorui Ma, Xiaolei Wang, Shengli Song, Shenmin College of Marine Science and Engineering Shandong University of Science and Technology Qingdao266000 China Center for Control Theory and Guidance Technology Harbin Institute of Technology Harbin150001 China

This paper investigates cluster sensor networks that are subjected to deceptive attacks in multi-sensor systems, and proposes an improved event-triggered (IET) mechanism to reduce their impact. The threshold of the upper bound in the IET mechanism is set to intercept the attacked information to improve the accuracy of estimation of the filter, while the lower bound is set to reduce the rate of communication to reduce the loss of unnecessary energy. Sequential fusion is used in the cluster sensor network to detect the attacked information, and the Kalman sequence fusion filter (KSFF) is applied to fuse the measurements in the cluster. Once the measurements fusion filter has been applied, the states of the clusters are exchanged and fused by using the Kalman consensus fusion filter (KCFF). We then derive the optimal IET-KSFF-KCFF under the criterion of minimum linear covariance based on event-triggered conditions and perform integral calculation. It is proved by mathematical induction that the covariance of the algorithm has an upper bound. Finally, the effectiveness of the algorithm is verified through simulations. © 2024, The Authors. All rights reserved.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Spatial distribution,morphology,and risk assessment of microplastics in sediment from the Pearl River Estuary,China

引用

Emerging Contaminants 2024年第3期10卷 409-418页

作者： Kaiqiang Xu Asfandyar Shahab Jorg Rinklebe He Xiao Jieyue Li Feng Ye Yanhong Li Dunqiu Wang Michael S.Bank Gangjian Wei College of Environmental Science and Engineering Guilin University of TechnologyGuilin541004China Guangxi Key Laboratory of Environmental Pollution Control Theory and Technology Guilin541004China University of Wuppertal School of Architecture and Civil EngineeringInstitute of Foundation EngineeringWater-and Waste-ManagementLaboratory of Soil-and Groundwater-ManagementPauluskirchstraße 742285WuppertalGermany Institute of Marine Research 5817BergenNorway University of Massachusetts Amherst AmherstMA01003USA State Key Laboratory of Isotope Geochemistry Guangzhou Institute of GeochemistryChinese Academy of SciencesGuangzhou510640China

Microplastics(MPs)(64.12%)of detected MPs were<0.85 mm and primarily consisted of pellets(36.84%)and fragments(29.65%).Three polymer types of MPs were identified by Fourier Transform Infrared Spectroscopy(FT-IR)inc... 详细信息

Microplastics(MPs)(<5 mm)are a growing environmental problem and have garnered significant global interest from scientists and policy *** ecosystems are vulnerable to MP pollution,and assessing their sources,fate,and transport in the environment is imperative for marine ecosystem *** for marine sediment are still limited,particularly in the Pearl River Estuary(PRE)ecosystem in ***,we assessed the abundance,characteristics,and risks of MPs in marine sediment from *** abundance ranged from 2.05×10^(3)items·kg^(-1)to 7.75×10^(3)items·kg^(-1)(dry weight),and white and black MPs were the dominant *** majority(>64.12%)of detected MPs were<0.85 mm and primarily consisted of pellets(36.84%)and fragments(29.65%).Three polymer types of MPs were identified by Fourier Transform Infrared Spectroscopy(FT-IR)including polyethylene(PE),polyethylene terephthalate(PET),and polypropylene(PP).Polyurethane(PU)sponge was reported for the first time in this study *** of the surface morphology of typical MPs using Scanning Electron Microscopy(SEM)showed that all MPs exhibited varying degrees of erosion,characterized by cracks,folds,and bumpy *** on type and quantity of MPs and the polymers identified,we assessed and classified the risk of MP contamination in PRE sediment as category Ⅲ,indicating severe ecosystem *** results may serve as an effective model for other estuaries facing similar pollution regimes and provides valuable information for marine sediment risk assessment.

关键词： Microplastics Distributional characteristics Surface morphology Risk assessment Pearl River Estuary

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Distributed Kalman Consensus Filter with Measurement Delay and Noise Correlation for Sensor Networks

SSRN

引用

SSRN 2024年

作者： Liu, Weicheng Yang, Yuhang Wang, Shengli Song, Shenmin College of Marine Science and Engineering Shandong University of Science and Technology Qingdao266000 China Center for Control Theory and Guidance Technology Harbin Institute of Technology Harbin150001 China

This paper reports the design of a nonlinear distributed Kalman consensus filter (NDKCF) with one-step random measurement delay and noise correlation for sensor networks. Because of the correlation between system noise and observed noise in multi-sensor systems, the state cannot be predicted directly in one-step, so the correlated noise is first decoupled. When there is a delay in the transmission of local observations from a sensor node, its predictor is used as compensation. The NDKCF with measurement delay and noise correlation under the unbiased minimum covariance criterion is derived for the first time, and the numerical integration form is designed in a Bayesian framework under the assumption that the conditional density is Gaussian. A numerical implementation of the proposed algorithm is given based on the third-degree spherical-radial rule cubature Kalman filter (CKF). It is proved that the covariance of the algorithm has an upper bound by linearization approximation, which shows the stability of the algorithm. Finally, a simulation experiment verifies the effectiveness of the algorithm. © 2024, The Authors. All rights reserved.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

GIB-RRT:a gamma interpolation bidirectional RRT algorithm

GIB-RRT:a gamma interpolation bidirectional RRT algorithm

引用

第35届中国控制与决策会议

作者： Jianyun Ni Hao Li Tie Wang Helei Du Jie Wu Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems School of Electronic Engineering and Automation Tianjin University of Technology Tianjin Climate Center

In a complex environment,when B-RRT and RRT algorithms are used for path planning,there will be problems such as long planned paths,large number of iterations,low sampling efficiency and long search *** solve these problems,this paper proposes a gamma interpolation bidirectional RRT algorithm——***,the algorithm uses a bidirectional search strategy to expand two random trees simultaneously to speed up the convergence *** the expansion process,an adaptive goal biasing strategy is introduced to improve the sampling efficiency,and the probability of expansion to the respective target point is continuously changed according to the number of collision detection *** the initial path is obtained,a greedy pruning algorithm is used to simplify the path points and reduce the path *** optimisation method of Gamma interpolation is then devised for the simplified path and combined with cubic uniform B-spline curve to generate shorter and smoothly executable *** proposed algorithm is compared with B-RRT,IB-RRT and B-RRT in different complex environments in simulation experiment,and the results show that the proposed algorithm has better search efficiency and is able to obtain optimal path in the least time and with the most stable efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Accelerating Distributed Nash Equilibrium Seeking

arXiv

引用

arXiv 2023年

作者： Tatarenko, Tatiana Nedić, Angelia The Department of Control Theory and Intelligent Systems TU Darmstadt Germany School of Electrical Computer and Energy Engineering Arizona State University United States

This work proposes a novel distributed approach for computing a Nash equilibrium in convex games with restricted strongly monotone pseudo-gradients. By leveraging the idea of the centralized operator extrapolation method presented in [4] to solve variational inequalities, we develop the algorithm converging to Nash equilibria in games, where players have no access to the full information but are able to communicate with neighbors over some communication graph. The convergence rate is demonstrated to be geometric and improves the rates obtained by the previously presented procedures seeking Nash equilibria in the class of games under consideration. © 2023, CC BY.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Medical Image Fusion in the NSST Domain with AR-Improved PA-PCNN 2022

Medical Image Fusion in the NSST Domain with AR-Improved PA-...

引用

4th International Conference on Intelligent Medicine and Image Processing, IMIP 2022

作者： Pei, Gaole Shi, T.A.O. Li, Shixing College of Electrical Engineering North China University of Science and Technology China Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems School of Electrical and Electronic Engineering Tianjin University of Technology China Department of Radiology Tianjin Beichen Hospital China

ISBN: (纸本)9781450396202

To present a medical image fusion method based on the non-subsampled shearlet transform (NSST) and improved parametric adaptive pulse-coupled neural network (PA-PCNN) for CT and MRI, which makes the fused images clearer and contains more information. The matched brain CT and MR-T2 are multi-scale decomposed by NSST, and the two source images are decomposed into low-frequency sub-bands and high-frequency sub-bands. The low-frequency fusion coefficients are obtained by fusing the low-frequency sub-band coefficients using the weighted sum-modified-Laplacian (WSML) low-frequency fusion rule. Meanwhile, the high-frequency sub-band coefficients are fused using the PA-PCNN model modified by the area ratio (AR) principle to obtain the high-frequency fusion coefficients. Finally, the low-frequency fusion coefficients and the high-frequency fusion coefficients are inverse transformed by NSST to obtain the final fused image. Compared to viewing CT or MR images alone, the fused images obviously display the relationship between soft mass and hard tissues. The fused image contains both the information of CT and MR. After fusion by the NSST-PA-AR-PCNN algorithm proposed in this paper, the details of the fused images are richer and the image quality is better than that of the previous fusion algorithms. This improved medical image fusion method of CT and MR could result that the final fused images are of higher quality to help detect anatomical structures and associated lesions in the brain. © 2022 ACM.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Robust Divergence Learning for Missing-Modality Segmentation

Robust Divergence Learning for Missing-Modality Segmentation

引用

Chinese Automation Congress (CAC)

作者： Runze Cheng Zhongao Sun Ye Zhang Chun Li MSU-BIT-SMBU Joint Research Center of Applied Mathematics Shenzhen MSU-BIT University Shenzhen China Institute of Control Theory and Control Engineering School of Automation Beijing Institute of Technology Beijing China School of Mathematics and Statistics Beijing Institute of Technology Beijing China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Multimodal Magnetic Resonance Imaging (MRI) provides essential complementary information for analyzing brain tumor subregions. While methods using four common MRI modalities for automatic segmentation have shown success, they often face challenges with missing modalities due to image quality issues, inconsistent protocols, allergic reactions, or cost factors. Thus, developing a segmentation paradigm that handles missing modalities is clinically valuable. A novel single-modality parallel processing network framework based on Hölder divergence and mutual information is introduced. Each modality is independently input into a shared network backbone for parallel processing, preserving unique information. Additionally, a dynamic sharing framework is introduced that adjusts network parameters based on modality availability. A Hölder divergence and mutual information-based loss functions are used for evaluating discrepancies between predictions and labels. Extensive testing on the BraTS 2018 and BraTS 2020 datasets demonstrates that our method outperforms existing techniques in handling missing modalities and validates each component's effectiveness.

关键词： Image segmentation Three-dimensional displays Protocols Magnetic resonance imaging Brain tumors Parallel processing Brain modeling Mutual information Knowledge transfer Testing

来源：评论

学校读者我要写书评

暂无评论

The development status of ship wall-climbing robot 4

The development status of ship wall-climbing robot

引用

4th International Conference on Electron Device and Mechanical engineering, ICEDME 2021

作者： Han, Lichun Wang, Liming Zhou, Jiahua Wang, Yang Naval University of Engineering College of Electrical Engineering Wuhan China Northeast Electric Power University Advanced Control Theory and Simulation Laboratory Jilin China

ISBN: (纸本)9780738114002

The ship wall-climbing robot belongs to a branch of intelligent robots, and its application objects are large military and civilian ships. It is mainly engaged in special operations such as testing, welding, cleaning and descaling. With the rapid development of science and technology, ship wall-climbing robots have also developed from the original negative pressure adsorption wall-climbing robots to the current bionic foot-type wall-climbing robots. In practical applications, it is gradually replacing manual operations, greatly improving work efficiency. This article introduces various ship-climbing robots with adsorption, movement, and driving methods as the main categories. This article focuses on the magnetic adsorption method, combined with other adsorption methods, and analyzes the performance characteristics and existing problems of various wall-climbing robots. Finally, we summarize the current technical problems of wall-climbing robots, and then make a prospect for the future development of wall-climbing robots. © 2021 IEEE.

关键词： Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Recursive Feasibility and Stability for Stochastic MPC based on Polynomial Chaos

引用

IFAC-PapersOnLine 2023年第1期56卷 204-209页

作者： Zhiming Ma Henning Schlüter Felix Berkel Thomas Specker Frank Allgöwer Faculty for Engineering Design Production Engineering and Automotive Engineering University of Stuttgart 70550 Stuttgart Germany Corporate Research Robert Bosch GmbH 71272 Renningen Germany Institute for Systems Theory and Automatic Control University of Stuttgart 70550 Stuttgart Germany

This paper deals with stochastic model predictive control (SMPC) based on polynomial chaos expansion (PCE) for linear systems with time-invariant stochastic parametric uncertainties and time-varying stochastic additive disturbances subject to chance constraints on states and inputs. Exploiting terminal ingredients in the SMPC problem and a hybrid update strategy, a recursively feasible optimization problem is formulated. Moreover, stability of the system of PCE coefficients can be shown. Furthermore, in the paper the performance and computational complexity of SMPC based on PCEs is compared to tube-based SMPC and robust model predictive control (RMPC) is analyzed and benefits are demonstrated in simulation.

关键词： Model predictive control stochastic control polynomial chaos expansion

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：