检索结果-内蒙古大学图书馆

International Conference on Computer Engineering and Applications (ICCEA)

作者： Ruifeng Zhu Caixia Sun Xiaopeng Wei Lasheng Zhao Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education (Dalian University) Dalian University Dalian China School of Computer Science and Technology Dalian University of Technology Dalian China

In order to improve the accuracy of speech emotion recognition, this paper proposes a speech emotion recognition method based on the channel attention mechanism. Firstly, Mel Frequency Ceptral Coefficient(MFCC), speech spectrograms and spectral envelopes are selected as the initial input features; then, multiple depth network models are used to extract feature maps from different angles in parallel; then, weights are assigned and fused to the feature maps output from each sub-depth network model by the channel attention mechanism; finally, the fused feature maps are used to predict emotion categories. The experimental results on CASIA, Emo-DB, and SAVEE emotion datasets show that the method achieves 88.3 % , 85.1%, and 64.5% recognition accuracy, respectively, with better recognition performance compared to recent comparative literature models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GraphSR: A Data Augmentation Algorithm for Imbalanced Node Classification

arXiv

引用

arXiv 2023年

作者： Zhou, Mengting Gong, Zhiguo State Key Laboratory of Internet of Things for Smart City University of Macau China Guangdong-Macau Joint Laboratory for Advanced and Intelligent Computing China

Graph neural networks (GNNs) have achieved great success in node classification tasks. However, existing GNNs naturally bias towards the majority classes with more labelled data and ignore those minority classes with relatively few labelled ones. The traditional techniques often resort over-sampling methods, but they may cause overfitting problem. More recently, some works propose to synthesize additional nodes for minority classes from the labelled nodes, however, there is no any guarantee if those generated nodes really stand for the corresponding minority classes. In fact, improperly synthesized nodes may result in insufficient generalization of the algorithm. To resolve the problem, in this paper we seek to automatically augment the minority classes from the massive unlabelled nodes of the graph. Specifically, we propose GraphSR, a novel self-training strategy to augment the minority classes with significant diversity of unlabelled nodes, which is based on a Similarity-based selection module and a Reinforcement Learning(RL) selection module. The first module finds a subset of unlabelled nodes which are most similar to those labelled minority nodes, and the second one further determines the representative and reliable nodes from the subset via RL technique. Furthermore, the RL-based module can adaptively determine the sampling scale according to current training data. This strategy is general and can be easily combined with different GNNs models. Our experiments demonstrate the proposed approach outperforms the state-of-the-art baselines on various class-imbalanced datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

The effect of different gravity fields on mass transfer in the rat bone lacunar-canalicular system

引用

Medicine in Novel Technology and Devices 2023年第1期17卷 141-149页

作者： Hao Wang Jiaming Wang Kangning Li Lilan Gao Aiguo Wang Shuping Wei Linwei Lyu Chunqiu Zhang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control National Demonstration Center for Experimental Mechanical and Electrical Engineering EducationSchool of Mechanical EngineeringTianjin University of TechnologyTianjin300384PR China Tianjin Academy of Traditional Chinese Medicine Affiliated Hosptial PR China

The bone lacunar-canalicular system(LCS)is an important microscopic infrastructure for signaling and solute transport in bone tissue,which guarantees normal physiological processes of the tissue,but the mass transfer laws in the LCS under different gravity fields have not yet been *** rats were injected intraperitoneally with different concentrations of sodium fluorescein tracer and subjected to mass transfer experiments in the LCS under normal gravity and *** fluorescence distribution in the osteon was observed using laser scanning confocal *** hypergravity environment was provided by a self-designed high-G loading *** fluorescence intensity of the Haversian canal in the osteon was the *** fluorescence intensity of lacunae farther away from the Haversian canal was lower,and the fitted curve was *** the increasing distance from the Haversian canal,the curve first rapidly decreased,and then the decreasing trend gradually became *** promoted mass transfer in the LCS,and the 10 G hypergravity showed varying degrees of fluorescence intensity in each layer of the osteon relative to normal gravity,with intensity enhancements in the range of 132.7–249.0%.The fluorescence intensity was also significantly increased when the tracer concentration was halved and the gravity field magnitude was increased to *** conclusion,hypergravity promoted the transport of solute molecules,nutrients,and signaling molecules within the *** effect of hypergravity on mass transfer in the LCS was greater than that of tracer *** may help to understand bone diseases from a mass transfer perspective.

关键词： Bone Lacunar-canalicular system Mass transfer Hypergravity

来源：评论

学校读者我要写书评

暂无评论

Innovative Application of Project Integration Technology in the Teaching Mode of Engineering Drawing Course 24

Innovative Application of Project Integration Technology in ...

引用

7th International Conference on Educational Technology Management, ICETM 2024

作者： Zhang, Runfeng Ming, Yankun Zhang, Guobin Liu, Zhenzhong Wu, Jianguo Tang, Yuxin National Demonstration Center for Exerimenta Mechanica and Electrica Engineering Education Lianin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin Tianjin China Tianjin Hanhailanfan Marine Technology Co. Ltd. Tianjin University of Technology Tianjin Tianjin China

ISBN: (纸本)9798400717468

Taking underwater robots project as an example, this paper discusses the innovation of the teaching mode of engineering drawing courses under the guidance of a project. The traditional engineering drawing course often lacks the link of practice and project application, which leads to the lack of students’ understanding and application ability of the course content. Therefore, this study proposes a teaching mode based on project guidance. By using underwater robots as teaching cases, theoretical knowledge and practical application are combined to promote the cultivation of students’ comprehensive abilities. This paper first reviews the research progress in related fields, then introduces the design and implementation methods of the teaching mode in detail, and analyzes the actual effect of the model through the underwater robot case. The results show that the teaching mode of engineering drawing courses under the guidance of the project has a positive impact on students’ learning interest, practical ability and teamwork ability. The results of this study will provide practical and feasible solutions for the innovation of the teaching mode of engineering drawing courses, and also provide a reference for the reform of undergraduate teaching mode in the construction of "New Engineering Education". © 2024 Copyright held by the owner/author(s).

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Modeling, Simulation, and Parameter design of Actuation Mechanisms Based on New Magnetic Control Materials 25

Modeling, Simulation, and Parameter Design of Actuation Mech...

引用

25th IEEE China Conference on System Simulation Technology and its Application, CCSSTA 2024

作者： Shen, Ruixuan Tian, He Zhao, Guanqiao Zhu, Ziliang Li, Jiangping Liang, Chao Tianjin University of Technology National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin China Tianjin Sanyuan Power Equipment Manufacturing Co. Ltd Tianjin China

ISBN: (纸本)9798350366600

With the rapid advancement of technology, the reliability and efficiency of power systems have become increasingly critical. In power systems, pole-mounted circuit breakers play a vital role. This paper presents a design scheme for an actuation mechanism of a pole-mounted circuit breaker based on new magnetic control materials. By analyzing the working principle of this actuation mechanism, a mathematical model was constructed, and a corresponding virtual prototype model was established using multi-body dynamics simulation software ADAMS and the dynamics mathematical model of this type of actuation mechanism. key performance parameters of the circuit breaker were optimized using a quantum genetic algorithm. Simulation experiments verified that the proposed parameter settings achieved a closing time of 7.6 ms, demonstrating significant improvements in circuit breaker performance. The results of this study are of great importance for the optimization design and performance enhancement of circuit breakers in power systems. © 2024 IEEE.

关键词： Software prototyping

来源：评论

学校读者我要写书评

暂无评论

An optimal design and fuzzy control method for a new flapping-wing robot 3

An optimal design and fuzzy control method for a new flappin...

引用

3rd International Conference on Electrical Engineering and Control Science, IC2ECS 2023

作者： Zhang, Chunxiao Zhao, Yansen Zhang, Ting Liu, Qi Li, Bin Ma, Yue Suo, Mengze Li, Changrui School of Mechanical Engineering Tianjin University of Technology Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin300384 China Tianjin University of Technology National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin300384 China

ISBN: (纸本)9798350382426

Bionic flapping-wing robot has the advantages of good maneuverability, low noise and strong stealth performance. It is widely used in military intelligence collection, field rescue and investigation. In this paper, an optimal design method of bionic flapping-wing robot non-phase difference driving mechanism is proposed. By setting the constraints of flapping angle amplitude, fuselage height and slider stroke, the scale parameters of the mechanism are optimized by using the minimum transmission angle;on this basis, the effectiveness of fuzzy PD control in improving the tracking accuracy of the drive system is verified by means of ADAMS and MATLAB / Simulink electromechanical coupling simulation. This research has practical value for designing new flapping-wing robot and improving its control quality. © 2023 IEEE.

关键词： flapping-wing robot fuzzy PD control kinematics scale optimization

来源：评论

学校读者我要写书评

暂无评论

Control Strategy of Permanent Magnet Synchronous Motor and Brushed DC Servo Motor Based on ADRC 20

Control Strategy of Permanent Magnet Synchronous Motor and B...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Liu, Liang Liu, Haikui Nie, Guangyin Gao, Yang Tianjin University of Technology Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin300384 China Tianjin University of Technology National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin300384 China

ISBN: (纸本)9798350320831

Adaptive disturbance rejection control (ADRC) is a rapidly evolving and promising control method that has been widely applied in various industrial fields and may yield better results than traditional method. In order to promote the controller performance, ADRC technology was employed to construct a three-loop structure for the controllers of permanent magnet synchronous motor (PMSM) and brushed DC Servo Motor (BDSM). Firstly, the mathematical models of the both kinds of motors were presented and combined with the ADRC, respectively. Secondly, the simulation models based on ADRC were constructed in MATLAB/SIMULINK, respectively. Finally, comparative experiments were carried out by ADRC and Proportional-Integral (PI) methods. The simulation results showed that ADRC outperforms PI control in terms of response speed, overshoot reduction, and anti-interference capability, which verified the proposed method can exhibit superior dynamic properties in the induction motor control. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

A Control Method of Robotic Arm Based on Improved Deep Deterministic Policy Gradient 20

A Control Method of Robotic Arm Based on Improved Deep Deter...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Shao, Yanpeng Zhou, Haibo Zhao, Shuaishuai Fan, Xiaoyan Jiang, Jiayi Tianjin University of Technology National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin300384 China Tianjin University of Technology Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin300384 China

ISBN: (纸本)9798350320831

With the continuous development of Machine Learning, Reinforcement Learning has achieved excellent results in many fields. An improved Deep Deterministic Policy Gradient (DDPG) algorithm is proposed in this paper to optimize Reinforcement Learning control performance, because of the issue of sparse rewards during training in continuous action spaces such as robotic arms, leading to slow convergence and low success rates. The algorithm merges the DDPG algorithm with the Hindsight Experience Relay (HER) algorithm, enabling the agent to learn from the failed experience when learning. Moreover, a double experience replay buffer is introduced, comprising a primary buffer and a secondary buffer containing high-reward experiences, which enhances the sampling probability of high-quality samples. At long last, a PyBullet simulation environment was utilized to execute a simulation experiment. The robotic arm using the improved DDPG algorithm achieved a success rate of nearly 100% in about 220 epochs of training, and the algorithm convergence speed was greatly improved. The trained robotic arm can reach any target point in the workspace. The efficacy of the improved DDPG algorithm is demonstrated by the outcomes, providing a valuable reference for further exploration into the intelligent control of robotic arms for object grasping. © 2023 IEEE.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Research on Control Strategy of Manipulator Based on Deep Reinforcement Learning 23

Research on Control Strategy of Manipulator Based on Deep Re...

引用

3rd International Conference on Artificial Intelligence, Automation and Algorithms, AI2A 2023

作者： Xu, Nuo Shao, Yanpeng Fan, Xiaoyan National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin300384 China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China

ISBN: (纸本)9798400707605

Abstract: Today, the traditional control algorithm of the manipulator is difficult to meet in the complex and changing working environment, and the development of artificial intelligence has achieved remarkable results in the field of manipulator control. As a branch of artificial intelligence, deep reinforcement learning combines the perception ability of deep learning with the decision-making ability of reinforcement learning, which can greatly improve the work efficiency and adaptability of the manipulator. This paper expounds on the principle of deep reinforcement learning, compares and analyzes the application examples of the single manipulator and multi-manipulator control algorithms based on deep reinforcement learning, and demonstrates the achievements of deep reinforcement learning in the motion control of manipulators. The intelligent control research provides a reference. © 2023 ACM.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Dimensional synthesis and static/dynamic analysis of a robot in automobile hubs polishing 20

Dimensional synthesis and static/dynamic analysis of a robot...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Chen, Long Xi, Manru Ma, Yue Li, Bin Liu, Qi Li, Changrui Tianjin University of Technology Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin300384 China Tianjin University of Technology National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin300384 China

ISBN: (纸本)9798350320831

Focusing on the polishing operation of automobile hubs, this paper proposed a polishing robot by combining a 1T2R parallel mechanism (PM) and an X-Y worktable. The dimensional synthesis and static/dynamic performance analysis of the 1T2R PM are also presented with the key points as follows. Firstly, the inverse displacement model and velocity model of the PM are built to formulate the motion/force transmissibility indices on the basis of the generalized Jacobian matrix. Secondly, the dimensional synthesis problem is formulated to determine the optimized normalized dimensional parameters by maximizing the global force/motion transmissibility of the PM subject to geometric constraints without mechanical interference. Finally, the finite element (FE) model of the 1T2R PM is built with the aid of the SAMCEF, and the static stiffness and lower-order natural frequencies of the PM are evaluated. The research results of this paper provide dimensions and mechanical structures for developing the physical prototype of the automobile hub polishing robot. © 2023 IEEE.

关键词： Finite element method

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：