检索结果-内蒙古大学图书馆

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Keun-Chang Kwak Witold Pedrycz Department of Control Instrumentation and Robot Engineering Chosun University Gwangju South Korea Department of Electrical and Computer Engineering University of Alberta Edmonton Canada

In this paper, the fundamental idea of Linguistic Models (LM) introduced by Pedrycz is followed and their genetically oriented design framework is developed. The LM is designed by the use of fuzzy granulation realized via Context-based Fuzzy C-Means (CFCM) clustering. This clustering technique builds information granules in the form of fuzzy sets and develops clusters by preserving the homogeneity of the clustered patterns associated with the input and output space. However, it is difficult to optimize the number of linguistic context produced in the output space, the number of cluster generated by each context, and fuzzification factor related to fuzzy clustering. Thus, we perform simultaneous optimization of design parameters linking information granules in the input and output spaces based on Genetic Algorithm (GA). The experimental results on coagulant dosing process in a water purification plant reveal that the proposed method shows a good performance in comparison with Linear Regression (LR), Neural Networks (NN), Radial Basis Function Networks (RBFN), and LM itself.

关键词： Context Pragmatics Data models Context modeling Artificial neural networks Fuzzy sets Purification

来源：评论

学校读者我要写书评

暂无评论

Classification of EEG signals based on CNN-Transformer model 20

Classification of EEG signals based on CNN-Transformer model

引用

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

作者： Liu, Jianwei Dong, Enzeng Tong, Jigang Yang, Sen Du, Shengzhi Tianjin University of Technology Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Intelligent Robot Laboratory 391 Binshui West Road Tianjin China Tshwane University of Technology Department of Electrical Engineering Pretoria0001 South Africa

ISBN: (纸本)9798350320831

Brain-computer interfaces (BCI) based on EEG have attracted extensive research and attention worldwide, while motor imagery (MI), mental arithmetic (MA), and P300 event-related potentials are a few of the more commonly used *** Transformer(ViT) is a new Transformer model that has superior global processing power compared to Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN).In this study, we propose a hybrid CNN-Transformer based model that uses CNN to convolve EEG signals in time and space, followed by ViT for global processing, and finally optimizes the model using 10-run × 10-fold cross-validation and validates it on a publicly available dataset of 29 subjects. Final accuracies of 87.23% and 90.79% were achieved on the MI and MA tasks, respectively. Compared to other literature, the model achieved higher classification accuracies. © 2023 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Fatigue Driving Detection of EEG Signals by LSTM Deep Neural Network with LPSD and DE 20

Fatigue Driving Detection of EEG Signals by LSTM Deep Neural...

引用

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

作者： Zhang, Hao Dong, Enzeng Tong, Jigang Yang, Sen Du, Shengzhi Tianjin University of Technology Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Intelligent Robot Laboratory 391 Binshui West Road Tianjin China Tshwane University of Technology Department of Electrical Engineering Pretoria0001 South Africa

ISBN: (纸本)9798350320831

Fatigue driving detection has always been an urgent social problem to be solved, and many complex factors increase the difficulty of detection. Nowadays, more scholars choose to use multi-channel EEG signals for fatigue detection, which is accompanied by the development of deep learning networks. Here, we propose the deep Long Short Term Memory (LSTM) neural network with the Differential Entropy (DE) and Logarithm Power Spectrum Density (LPSD). We first divide the EEG signal into 8-s Hanning windows with 50% overlap, and then use the Short Time Fourier Transform(STFT) on the extracted time window to obtain 50 frequency sub-bands. Finally, LPSD and DE features are extracted from the frequency offspring obtained from the STFT and input into the deep LSTM neural network. The network can choose to learn more task related information by adding soft attention and extract effective time information from EEG signals,thereby improving the model's performance in detecting driving fatigue. In addition, we also collected EEG signals from 8 subjects in both awake and fatigued states,and used the PERCLOS index to judge the degree of fatigue. Using the collected dataset, we compared the effectiveness of the deep LSTM neural network with five other methods. The results indicate that the deep LSTM neural network has a better classification accuracy of 93.12%. It proves that the network has good performance in fatigue detection of EEG signals. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Modeling and control Design for Quadrotor Transporting System With a Cable-Suspended Rigid Payload 20

Modeling and Control Design for Quadrotor Transporting Syste...

引用

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

作者： Xia, Tianqi Dong, Enzeng Yang, Sen Tong, Jigang Du, Shengzhi Tianjin University of Technology Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Intelligent Robot Laboratory 391 Binshui West Road Tianjin China Tshwane University of Technology Department of Electrical Engineering Pretoria0001 South Africa

ISBN: (纸本)9798350320831

In this paper, facing the aerial transportation task with a large volume cargo, the system of quadrotor with a cable-suspended rigid payload is investigated. The dynamic model of proposed system is built with Lagrange d'Alembert principle. The dynamic model is linearized to design the feedback control method. Finally, two groups of numerical simulation with proposed feedback controller are designed to demonstrate the effectiveness of system model and the results of simulation illustrate satisfactory performance. © 2023 IEEE.

关键词： Dynamic models

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Classification of Riemannian Tangent Spaces Based on MI-BCI 20

Machine Learning Classification of Riemannian Tangent Spaces...

引用

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

作者： Zhao, Chunli Dong, Enzeng Tong, Jigang Yang, Sen Du, Shengzhi Tianjin University of Technology Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Intelligent Robot Laboratory 391 Binshui West Road Tianjin China Tshwane University of Technology Department of Electrical Engineering Pretoria0001 South Africa

ISBN: (纸本)9798350320831

Motor imagery brain-computer interfaces (BCIs) have been extensively used in stroke rehabilitation, particularly in China where stroke incidence is high. The application of BCI to control prostheses and robotic arms has shown promising results in improving the quality of life for stroke patients. However, a major challenge in this field is improving the accuracy of motor imagery (MI) classification. Several previous studies have reported that stroke patients exhibit atypical patterns of even-trelated desynchronization (ERD) and event-related synchronization (ERS) activation during motor imagery (MI) tasks. It has been suggested that the brain regions affected by stroke may show reduced excitability and relative insensitivity to external interference compared to those of healthy individuals. Therefore, this study proposes that the classification accuracy of stroke patients in the same MI task would be higher compared to that of healthy volunteers. In this study, we employed a feature extraction algorithm that combines the Filter Bank Common Spatial Pattern (FBCSP) and Riemann geometric mean distance methods to compare the classification accuracy of five different classifiers, with the objective of identifying the most suitable classifier for our analysis. The obtained results revealed that the K-Nearest Neighbors (KNN) classifier yielded the highest accuracy, reaching 87.5% for stroke patients and 85% for healthy volunteers, respectively. In addition to accuracy, we also utilized Kappa values as evaluation metrics, which yielded Kappa results of 0.619 and 0.613 for stroke patients and healthy volunteers, respectively. © 2023 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of spring for the vehicle suspension system using the nonlinear finite element method 4

Performance evaluation of spring for the vehicle suspension ...

引用

4th International Conference on Advanced Design and Manufacturing engineering, ADME 2014

作者： Kim, Byeong Soo Moon, Byung Young Kim, Sung Kwan School of Mechanical and Automotive Engineering High Safety Vehicle Core Technology Research Center Inje University 607 Obang-dong Gimhae Korea Republic of Department of Naval Architecture Kunsan National University 1170 Daehagro Gunsan Korea Republic of Department of Control and Robot Engineering Graduate School Kunsan National University Korea Republic of

ISBN: (纸本)9783038352570

Air spring is used for the suspension system and it affects the vehicle stability and riding comfort by improving the impact-relief, braking, and cornering performance. Air Spring is comprised of the upper plate, lower plate, and rubber sleeve. Rubber sleeve is the composite material, which is made up of combination of rubber and Nylon, and the characteristics are changed according to the shape of rubber-sleeve, the angle of reinforcement cord. In this study, the distribution of internal stresses and the deformation of rubber composite material are analyzed through the nonlinear finite element method. The result showed that the internal maximum stresses and deformations about the changes of cord angle caused the more the Young's modulus decrease, the more maximum stress reduced. © (2014) Trans Tech Publications, Switzerland.

关键词： Rubber

来源：评论

学校读者我要写书评

暂无评论

Design of wireless mobile environment monitoring system based on spherical amphibious robots 15

Design of wireless mobile environment monitoring system base...

引用

15th IEEE International Conference on Mechatronics and Automation, ICMA 2018

作者： Guo, Shuxiang Yang, Xujie Guo, Jian Li, Chunying Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems and Biomedical Robot Laboratory Tianjin University of Technology Binshui Xidao Tianjin391 China Intelligent Mechanical Systems Engineering Department Faculty of Engineering Kagawa University 2217-20 Hayashi-cho Takamatsu761-0396 Japan

ISBN: (纸本)9781538660720

A wireless mobile environmental monitoring system based on spherical amphibious robots is proposed in this paper, which is used to monitor environmental data in *** control interface is designed by using labVIEW to display the collected environmental *** XBee module is used to realize the wireless communication between robot and PC. The robot is equipped with temperature and humidity sensors, pressure sensors and high-definition cameras to collect environmental information. An adaptive weighted fusion algorithm is proposed for deal with the multi source data collected by multiple robots and improve the accuracy of *** this paper, the underwater kinematic model of amphibious robot is established, and the proportional-integral-derivative(PID) controller is designed to control the depth of spherical amphibious robot. The simulation and experimental results verified the effectiveness of the system. © 2018 IEEE.

关键词： robots

来源：评论

学校读者我要写书评

暂无评论

Some aspects of the modular walking robot MERO's new architecture

引用

IFAC Proceedings Volumes 2012年第6期45卷 900-905页

作者： Ion Ion Simionescu Ion Curaj Adrian Aurelian Vasile Dinu Cornel Manufacturing Technology Department POLITEHNICA University of Bucharest Romania Mechanism and Robot Theory Department POLITEHNICA University of Bucharest Automatic Control and System Engineering Department POLITEHNICA University of Bucharest Romania

The new modular walking robots MERO by reconfiguring their architecture are built to displace the heavy loads on the unaligned terrain. The main characteristic of the modular walking robots is that they are able to move away on unarranged, horizontal and rough terrain The modular walking system protects much better the environment when its contact with the soil is discrete, a fact that limits appreciately the area that is crushed. The new modular walking robots may have a lower or higher autonomy degree. This autonomy has in view the power source's supply capability but also orientation and perception capabilities as regards the terrain configuration the robot is running upon and its decision making and the motion manner towards a target. Architecture of the reference structure of the walking robot has three two-legged modules. Every leg has three degrees of freedom (RRP), a slip sensor and tactile sensor to measure the contact which consists of lower and upper levels. The body of the MERO (MEchanism robot) walking robot carries a gyroscopic bearing sensor to measure the pitch and roll angles of the platform. The legs are powered by hydraulic drives and are equipped with transducers and sensors. They are used to control the walking robot in the adaptability to a natural ground. In this paper presents some aspects of the new modular walking robot

关键词： autonomous mobile robot walking robot mechanism gait stability level control

来源：评论

学校读者我要写书评

暂无评论

Wireless remote control for an electromagnet-type moving microrobot (fabrication of prototype microrobot and experimental results)

Wireless remote control for an electromagnet-type moving mic...

引用

IEEE/SICE International Symposium on System Integration

作者： Masahiro Isogai Yoshiteru Nishiura Department of Electronic Control and Robot Engineering Aichi University of Technology Gamagori Japan Aichi University of Technology Japan

In recent years, a large number of studies have focused on micro-robots. Moreover, yearly contests have been held in order to develop micro-robot technologies. As a result of these activities, various types of microrobot have been proposed, including motor-type, piezoelectric-element-type, and electromagnet-type micro-robots. To date, the authors' research group has been studying a locomotion mechanism and control method for an electromagnet-type microrobot, which has a volume of 1[cm 3 ]. The proposed microrobot has a feature of being able to turn with single electromagnet coil using the difference of the vibration characteristics of the legs. In this paper, we propose a wireless remote control method for the microrobot, using the feature of the locomotion mechanism and control method. We report on some experimental results to confirm the fundamental function of the wireless remote control method proposed.

关键词： Vibrations Batteries Receivers robots Acceleration Wheels Brushes

来源：评论

学校读者我要写书评

暂无评论

Research on and education for navigation control of an exploration rover with microwave Doppler sensors

Research on and education for navigation control of an explo...

引用

International Symposium on Micro-NanoMechatronics and Human Science, MHS 2015

作者： Isogai, Masahiro Nawa, Yasuhiko Iijima, Toru Department of Electronic Control and Robot Engineering Aichi University of Technology 50-2 Manori Nishihazamacho Gamagori Aichi443-0047 Japan College of Environmental Technology Graduate School of Engineering Muroran Institute of Technology 27-1 Mizumoto-cho Muroran-shi Hokkaido050-8585 Japan

ISBN: (纸本)9781479966783

Microwave Doppler sensors commonly used in automatic-door systems have been used in a rover navigation system. A collimated microwave beam with an angular width of and plusmn;3 and deg;at a frequency of 24 GHz was emitted from a sensor (A) on a dish antenna 30 cm in diameter. Another sensor (B), which works as a detector, was installed on the rover. The rover was programmed to make a right turn when the microwave signal was above a specified level and to make a left turn when the signal was below that level. In this study, we fabricated the third prototype rover. To confirm the effectiveness of the proposed method, we performed the experiments on the strength distribution of the microwave beam and on the navigation control with the fabricated rover. Finally, we had a questionnaire for the student who collaborated with this study to investigate how the education effects for the student were. © 2015 IEEE.

关键词： Microwave antennas

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：