检索结果-内蒙古大学图书馆

Topological horseshoe analysis and field-programmable gate array implementation of a fractional-order four-wing chaotic attractor

引用

Chinese Physics B 2018年第1期27卷 300-306页

作者：董恩增王震于晓陈增强王增会 Tianjin Key Laboratory For Control Theory & Applications in Complicated Systems Tianjin University of Technology Department of Automation Nankai University Department of Electrical and Mining Engineering University of South Africa

We present a fractional-order three-dimensional chaotic system, which can generate four-wing chaotic attractor. Dy- namics of the fractional-order system is investigated by numerical simulations. To rigorously verify the chaos properties of this system, the existence of horseshoe in the four-wing attractor is presented. Firstly, a Poincar6 section is selected properly, and a first-return Poincar6 map is established. Then, a one-dimensional tensile horseshoe is discovered, which verifies the chaos existence of the system in mathematical view. Finally, the fractional-order chaotic attractor is imple- mented physically with a field-programmable gate array （FPGA） chip, which is useful in further engineering applications of information encryption and secure communications.

关键词： fractional-order chaotic system Poincar6 map topological horseshoe field-programmable gatearray （FPGA）

来源：评论

学校读者我要写书评

暂无评论

A Novel Trajectory Predicting Method of Catheter for the Vascular Interventional Surgical Robot

A Novel Trajectory Predicting Method of Catheter for the Vas...

引用

IEEE International Conference on Mechatronics and Automation

作者： Jian Guo Yue Sun Shuxiang Guo Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and Intelligent Robot Laboratory Tianjin University of Technology Binshui Xidao 391 Tianjin China Faculty of Engineering Kagawa University 2217-20 Hayashi-cho Takamatsu Japan

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

In the process of vascular interventional surgery, there are many factors that affect the movement of the catheter in the complex vascular environment. In order to avoid the collision between the catheter and the vascular wall, the real-time requirements for the path planning of the catheter are higher and higher. The trajectory prediction of the catheter can better solve the real-time problem. In this paper, a trajectory prediction algorithm based on Kalman filter is proposed. The optimal state value of the next time is predicted by the state value of the previous time. In this paper, the real-time trajectory of the catheter in the virtual environment is extracted by the vascular interventional surgery doctor training system. Then the predicted value is calculated by Kalman filter, and analysis the error between the predicted trajectory and the actual trajectory. The experimental results show that the trajectory predicted by Kalman filter is close to the real trajectory.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of a Lower Limb Exoskeleton Robot

Design and Analysis of a Lower Limb Exoskeleton Robot

引用

IEEE International Conference on Mechatronics and Automation

作者： Shuxiang Guo Yibin Ding Jian Guo Tianjin Key Laboratory for Control Theory & Applications In Complicated systems and Intelligent Robot Laboratory Tianjin University of Technology No.391 Binshui Xidao Xiqing District Tianjin China Faculty of Engineering Kagawa University Takamatsu Kagawa Japan

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

In order to help patients with hemiplegia or mobility disability recover their normal walking ability. This paper designs a lower limb exoskeleton robot. This robot can not only provide to patients with walking force to drive the movement of both legs, but also can provide patients with rehabilitation training with high repeatability and good accuracy. The use of this robot will greatly save labor costs and reduce the pressure on medical resources. More importantly, machine training has the advantages of high repetition rate and accuracy. This makes the recovery period of patients shorter. This robot brings hope for patients to recover. In this article, introduce the structure of each part of the lower limb exoskeleton robot firstly. And then, make the gait analysis of human walking. Finally, make the static stress analysis of some structures with soildworks software and gait simulation experiment with adams software. In order to provide patients with a more comfortable rehabilitation experience, a control system based on electromyography signals needs to be designed in the future. An angle prediction model is obtained through neural network training, which can predict the patient's motion intention and thus control the robot's motion. This control method improves the human-computer interaction ability and enables patients to have more initiative.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Target Recognition System for the Amphibious Robot based on Edge Computing and Neural Network

A Novel Target Recognition System for the Amphibious Robot b...

引用

IEEE International Conference on Mechatronics and Automation

作者： Shuxiang Guo Handong Cheng Jian Guo Jigang Xu Tianjin Key Laboratory for Control Theory & Applications In Complicated systems and Intelligent Robot Laboratory Tianjin University of Technology Binshui Xidao Extension 391 Tianjin China Kagawa University Takamatsu Kagawa Japan Unit68709 Haidong China

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

In the past, the accuracy of target recognition was low and the transmission efficiency was low, in this paper, a target recognition system based on Edge calculation is proposed for the platform of Amphibious robot, which is mainly used for sea rescue and marine garbage search. Because of the flexible application of Amphibious robot to sea, land and air, the platform of Amphibious robot is equipped with camera to collect image information. We train neural networks on computers, We store the weight file on the edge calculation chip. The method of Edge calculation is used to run the Convolutional neural network to rescue the victims at sea, We have carried out many experiments to verify the accuracy of target recognition. Because the judgment of Edge nodes can greatly reduce the time of communication with terminals, thus improving the efficiency of rescue.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model Reference Scheduling and Resilient control Co-design with Modulation

Model Reference Scheduling and Resilient Control Co-design w...

引用

Chinese control and Decision Conference, CCDC

作者： Shunli Zhao Yuehui Ji Tianjin Key Laboratory for Control Theory & Applications in Complicated System Tianjin University of Technology Tianjin China School of Electrical and Electronic Engineering Tianjin University of Technology Tianjin China

ISBN: (数字)9781728158556

ISBN: (纸本)9781728158563

The medium access constraint that only permits limit nodes to gain access to the network is a research focus in the field of networked control systems. A co-design of the model reference scheduling and the resilient control with the modulation is proposed in the paper. The co-design scheme can deal with several representative problems in networked control systems, such as time delays from modulation, the medium access constraint and the perturbation of the controller. Finally, the effectivity of the co-design scheme proposed is demonstrated through a numerical example.

关键词： Delay effects Modulation Perturbation methods Symmetric matrices Networked control systems Delays

来源：评论

学校读者我要写书评

暂无评论

Prediction Model of User Purchase Behavior Based on Machine Learning

Prediction Model of User Purchase Behavior Based on Machine ...

引用

IEEE International Conference on Mechatronics and Automation

作者： Xiang Zhai Peng Shi Liang Xu Yalong Wang Xi Chen Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and School of Electrical and Electronic Engineering Tianjin University of Technology Binshui Xidao 391 Tianjin China AVIC Luoyang Institute of Electro-Optical Equipment Luoyang China

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

In recent years, with the continuous popularity of the Internet, the number of online shopping users in my country has reached 639 million, which contains huge commercial value. In order to maintain the prosperity, diversity and order of merchants, and fully meet consumers' one-stop shopping needs, it is necessary to analyze and predict user purchase behaviors more accurately. This article uses the interaction between users and products within a certain period of time provided by *** to predict whether users will place orders in designated categories and shops in the next week. First of all, we aim at the problem that the original features are not strongly related, and use feature fusion to construct strong features. For high-dimensional systems that are slow to calculate and prone to overfitting, we use random forests to filter features, reducing the complexity of the model. Finally, a fusion algorithm based on XGBoost and LightGBM is proposed to predict the purchase behavior of users, and the prediction effects of random forest and GBDT algorithm are compared at the same time. The results show that the fusion model has the best prediction effect, and can help merchants more accurately conduct marketing activities to potential customers based on the prediction results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Shallow Convolutional Neural Network for Classifying MI-EEG

A Shallow Convolutional Neural Network for Classifying MI-EE...

引用

Chinese Automation Congress (CAC)

作者： Tingting Wang Enzeng Dong Shengzhi Du Chao Jia Tianjin Key Laboratory For Control Theory & Applications in Complicated Systems Tianjin University of Technology Tianjin China

Deep neural network is a hotspot in the field of Machine Learning, which can realize deep hierarchical representation of input data. In this paper, a simplified Shallow Convolutional Neural Network (SCNN) is used to classify Motor Imagery Electroencephalogram (MI-EEG). The network uses a single feature layer to mine the intrinsic features of EEG sequences, and uses the training time and accuracy to evaluate the classification effect. Different from other methods, CNN integrates feature extraction and predicted classification results to optimize the whole process, which can automatically extract features from original data. Experiments on the BCI Competition IV Dataset 2b competition dataset and the BCI Competition II Dataset III competition dataset show that the overall performance under SCNN is the best.

关键词： Training Task analysis Convolutional neural networks Electroencephalography Feature extraction Machine learning Electrodes

来源：评论

学校读者我要写书评

暂无评论

Role of strategy update rules in the spatial memory-based mixed strategy games

引用

The European Physical Journal B 2021年第1期94卷 1-11页

作者： Zhang, Fan Wang, Juan Gao, Hongyu Li, Xiaopeng Xia, Chengyi Tianjin Key Laboratory for Control Theory and Complicated Industry Systems Tianjin University of Technology Tianjin People’s Republic of China School of Electrical and Electronic Engineering Tianjin University of Technology Tianjin People’s Republic of China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin People’s Republic of China Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin People’s Republic of China

Based on a continuous mixed strategy game model considering the memory mechanism and the uncertainty of individual decision-making, we explore the influence of several different update rules on the spatial cooperation behavior. Here, we mainly investigate the role of the Moran-like process, Fermi rule and replicator dynamics in the evolution of cooperation. Meanwhile, we further compare the evolution of cooperation when the memory mechanism and individual uncertainty are taken into account. In particular, memory length M and strategy adjustment factor $$\delta $$ can promote the cooperation behavior in different ways. Extensive Monte Carlo simulations indicate that the Moran-like process can generally drive the expansion of cooperative clusters faster and finally achieve the highest frequency of cooperation although the Fermi update rule performs better under the same condition. Moreover, the replicator dynamics create the worst scenario as far as the evolution of cooperation is concerned. Therefore, the level of cooperation strongly depends on the strategy update rules; these findings may be helpful to understand and analyze the evolutionary process of cooperation in many real-world natural and social systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gesture Recognition based on BP Neural Network and Data Glove

Gesture Recognition based on BP Neural Network and Data Glov...

引用

IEEE International Conference on Mechatronics and Automation

作者： Qiang Fu Jiajun Fu Jian Guo Shuxiang Guo Xun Li Tianjin Key Laboratory for Control Theory & Application in Complicated Systems and Biomedical Robot Laboratory Tianjin University of Technology Binshui Xidao 391 Tianjin China Kagawa University Takamatsu Kagawa Japan

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

Various devices for hand data collection have been proposed for gesture recognition. In this paper, a method is proposed for gesture recognition based on data glove and BP neural network. This data glove can collect data of the hand and forearm, it gives a comprehensive description of all aspects of arm movement, and BP neural network algorithm is used to process and classify the collected data and compress the data. Experiments show that hand data can be classified effectively by BP neural network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Instance Segmentation Algorithm Based on Improved Mask R-CNN

An Instance Segmentation Algorithm Based on Improved Mask R-...

引用

Chinese Automation Congress (CAC)

作者： Qijuan Yang Enzeng Dong Lin Zhu Tianjin Key Laboratory For Control Theory & Applicationsin Complicated Systems Tianjin University of Technology Tianjin China China North Industries Group 210 Reseasrch Institute Beijing China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

Mask R-CNN has a high application value in the field of computer vision. However, the Mask R-CNN algorithm has the disadvantages of poor edge segmentation due to the blurred bounding box of the target image and poor segmentation of small targets, which greatly limits its wide application. To solve the above problems, this paper proposes a multi-scale RPN(Region Proposal Network) network structure and adopts KL loss. By building the Tensorflow deep learning framework in the Ubuntu16.04 operating system, the improved algorithm was tested in the MS-COCO data set and the autonomous driving data set Cityscapes which verifies its applicability and effectiveness.

关键词： Feature extraction Image segmentation Proposals Training Data models Classification algorithms Object detection

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：