检索结果-内蒙古大学图书馆

IEEE International Conference on Mechatronics and Automation

作者： Zhao Su Xuehui Liang Jigang Tong Sen Yang Shengzhi Du Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and Intelligent Robot Laboratory Tianjin University of Technology Tianjin China Department of Electrical Engineering Tshwane University of Technology Pretoria South Africa

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

In the point cloud 3D object detection task, the point cloud data is unevenly distributed in 3D space. Therefore, whether it is regular sparse convolution or submanifold sparse convolution, there is a significant difference in the detection performance when dealing with objects at different positions using sparse convolutional networks. Therefore, this paper proposes an improvement using focal sparse convolution to break the limitations of traditional convolution methods and enhance the representation ability of sparse convolution. Focal sparse convolution is utilized to replace the currently better-performing two-stage object detection network based on the combination of points and voxels, enhancing the end-to-end training effectiveness and achieving better detection results. And an optional detachable auxiliary network is added, which, during the training stage, combines point features to guide the backbone network in learning the structural information of the 3D point cloud, enhancing the localization accuracy of the backbone network. Extensive experiments have been conducted on the KITTI dataset to validate the proposed method, yielding promising detection results and demonstrating the effectiveness of the approach.

关键词： Point cloud compression Training Location awareness Three-dimensional displays Accuracy Mechatronics Convolution

来源：评论

学校读者我要写书评

暂无评论

Linear active disturbance rejection control of phase-shifted full-bridge converter based on improved particle swarm optimization algorithm

Linear active disturbance rejection control of phase-shifted...

引用

IEEE International Conference on Mechatronics and Automation

作者： HongSen Wang YanJuan Wu Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin University of Technology Binshui Xidao 391 Tianjin China

In order to improve the dynamic performance and disturbance suppression ability of conventional PID control phase shift full-bridge converter, LADRC based on improved particle swarm optimization is proposed. The voltage loop transfer function of phase-shifted full-bridge converter is derived based on the state space average method. Secondly, LESO and LSEF are designed to estimate and compensate the external disturbance and internal uncertainty in real time. Finally, the advantages of linear active disturbance rejection controller are verified by simulation experiments. The experimental results show that the controller has better disturbance suppression performance and dynamic performance than the traditional PID controller.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Named Entity Recognition in Chinese Medical Texts Based on RoBERTa-WWM-IDCNN-CRF

Named Entity Recognition in Chinese Medical Texts Based on R...

引用

system Simulation Technology and its Application (CCSSTA), IEEE China Conference on

作者： Lan Tang Jie Kong Liang Xu School of Computer Xi‘an Shiyou University Xi‘an China Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China

ISBN: (数字)9798350366600

ISBN: (纸本)9798350366617

Electronic medical records and doctor-patient conversations contain a wealth of useful information, such as disease symptoms, drug names, and cure cycles. Traditional deep learning approaches utilize bidirectional recurrent neural networks to encode text, which cannot effectively capture long-distance dependencies in text. In order to identify medical entity types in various texts more accurately, a named entity recognition approach based on RoBERTa-WWM-IDCNN-CRF is proposed. This approach introduces the RoBERTa-WWM pre-trained model, in order to improve the overall understanding of long Chinese texts for the first time. The model generates semantic representations containing prior knowledge. Then, the generated semantic representations are feed to the IDCNN to extract sentence level characteristics. Finally, the global optimal solution is obtained and the results of the named entity are produced through the CRF. The experiment indicates that the improvement of $F_{1}$ score, accuracy, and recall of RoBERTa-WWM-IDCNN-CRF model are 7.94%, 4.52% and 10.02% comparing with the classical BiLSTM-CRF model.

关键词： Drugs Recurrent neural networks Semantics Named entity recognition Oral communication Medical services systems simulation Feeds Electronic medical records Diseases

来源：评论

学校读者我要写书评

暂无评论

Real-time scheduling strategy for electric vehicles based on sliding window transmission optimization

Real-time scheduling strategy for electric vehicles based on...

引用

IEEE International Conference on Mechatronics and Automation

作者： Peizhi Cong Yanjuan Wu Caiwei Wang Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin University of Technology Binshui Xidao 391 Tianjin China

In order to reduce the impact of electric vehicle(EV) charging load on the power grid, a real-time optimal scheduling scheme for charging and discharging Evs is proposed. Firstly, the objective is to reduce charging costs and network loss costs, aiming to minimize the total cost of EVs at the current time. An EV dispatching model is established, the grid node acceptance capacity performance is analyzed by constructing a network loss sensitivity index, and the EV charging and discharging strategy is obtained in real time based on the time-of-use tariff of the grid load by means of a tide calculation and a sliding window variable speed optimization algorithm as well as a second-order convex optimization calculation method. Finally, the proposed strategy is verified to be effective in reducing the charging cost and network loss cost, and has good real-time flexible dispatching performance, using an improved IEEE 39-node distribution network as an example.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Based on Hybrid Densenet-121 with Support Vector Machine Algorithm for Lettuce and Chili

Based on Hybrid Densenet-121 with Support Vector Machine Alg...

引用

IEEE International Conference on Mechatronics and Automation

作者： Yuzhe He Yanjuan Wu Caiwei Wang Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin University of Technology Binshui Xidao 391 Tianjin China

In this paper, to improve the recognition accuracy of Densenet-121, we combine Densenet-121 with SVM to generate a new network Densenet-121-SVM. In this paper, the two datasets are combined to generate a new dataset named Mixed-dataset, which has four plants, namely: Lettuce, Chili, Chinee apple, and Lantana, and this dataset is used to train the network. Finally, the recognition accuracies of SVM, Densenet121 and Densenet-121-SVM are 84.144%, 96.211% and 98.181%, respectively, and it can be seen that the accuracy of Densenet-121-SVM is improved by 14% and 1.97% compared to SVM and Densenet-121, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Uncertainty Treatment of Integrated Energy system Based on Scenario Reduction Method

Uncertainty Treatment of Integrated Energy System Based on S...

引用

IEEE International Conference on Mechatronics and Automation

作者： Caiwei Wang Yanjuan Wu Peizhi Cong Yuzhe He Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin University of Technology Binshui Xidao 391 Tianjin China

In the context of high permeability of renewable energy, a large number of uncertain energy sources, such as scenery, have brought a huge impact on the security and stability of the comprehensive energy system. In order to reduce the impact of renewable energy on the new power system and improve the system stability, In this paper, a comprehensive energy system of the park is set up, which consists of three kinds of energy loads including source side electricity, heat, gas and scenery, and electric heat. On this basis, Monte Carlo method is adopted to simulate multiple sets of scenes respectively for the scenery output. On this basis, scene reduction method is adopted to reduce them to obtain the final equivalent force diagram, so as to reduce the influence of the uncertainty of scenery on the system stability. Finally, the effectiveness of the proposed method is verified by simulation analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Path Planning of Mobile Robot Based on Improved Artificial Potential Field Method

Path Planning of Mobile Robot Based on Improved Artificial P...

引用

第35届中国控制与决策会议

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

An improved artificial potential field method is proposed to address the problems of target unreachability and falling into local minima in the path planning process of the traditional artificial potential field ***,the distance factor between the robot and the target point is introduced to solve the target unreachability problem;secondly,the robot is guided out of the local minima point by setting the virtual target point through the double-circle strategy;finally,in order to satisfy the continuity of robot velocity and acceleration,the resulting path is smoothed by using three uniform B-sample *** experimental results show that the improved algorithm can effectively solve the problems of target unreachability and falling into local minima in the traditional algorithm,and the smoothness of the path after the spline treatment is better compared with the original path.

关键词： artificial potential field method target unreachable local minimum point bicircular strategy virtual target point B-sample curve

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

A Review of UAV Power Line Inspection

A Review of UAV Power Line Inspection

引用

International Conference on Guidance, Navigation and control, ICGNC 2020

作者： Wang, Zhaoyang Gao, Qiang Xu, Jianbin Li, Dahua School of Electrical & Electronic Engineering and Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin300384 China Sanyuan Electric Equipment Manufacturing Co. Ltd Tianjin300409 China

ISBN: (纸本)9789811581540

In recent years, unmanned aerial vehicles (UAVs) have begun to enter human life as a new type of tool, they have played a large role in various industries, and the power industry is no exception. The normal operation of the power system requires prudential inspection. Traditional methods such as manual inspection have nonnegligible disadvantages, so more and more power companies have begun to use UAVs instead of manual inspection. In this paper we analyzed the development history and advantages of UAV power line inspection, and showed the composition and classification of UAV power line inspection system, as well as the current circumstances. Next, according to the type of UAV, the task of power line inspection is described. Then, based on the requirements of the power line inspection task, the inspection methods and key technologies of the UAV are described. Finally, challenges such as safety, endurance time, and automation that have emerged during the development of UAV power inspections are proposed. We analyze the prospects of UAV power inspection technology from how some companies are responding to these challenges. © 2022, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

Research on Measuring Method of Self-Mixing Interference Magnetic Field Based on Faraday Effect

SSRN

引用

SSRN 2024年

作者： Zhao, Yan Sun, Wenqiang Wang, Haipeng Ma, Shihui School of Electrical Engineering and Automation Tianjin University of Technology Tianjin300384 China Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems Tianjin300384 China Institute of Functional Crystals and Tianjin Key Laboratory of Functional Crystal Materials Tianjin University of Technology Tianjin300384 China

In this paper, the magnetic field measurement method of laser self-mixing interference based on the Faraday effect is proposed. The polarization plane of the linearly polarized light is changed by the terbium gallium garnet crystal with the influence of the magnetic field. The light modulated by the magnetic field reentered into the laser cavity through the Brewster window and formed the self-mixing effect. The theoretical analysis of the self-mixing interference model based on the Faraday effect is conducted, which explains essential features of the experimental results. The magnetic field is measured by the peak-to-peak value of self-mixing interference signal. The experimental results show that the relative error of the magnetic field measurement is within ±1.6%. The measurement method has the advantage of simple and compact structure with strong anti-interference ability. © 2024, The Authors. All rights reserved.

关键词： Faraday effect

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：