检索结果-内蒙古大学图书馆

第41届中国控制会议

作者： Yuting Ge Yi Liu Chi Xu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Particle Detection plays important roles in industrial and medical image ***-learning based methods can only deal with the particle images with simple backgrounds and sparse *** most neural network based methods can also hardly to deal with overlapping objects and small particles,besides,the huge amount of parameters of these methods also has a great demand for annotated data,which is difficult to ***,we use bright pixels to represent the spatial position of particles,and artificially divid the sizes of particles into multiple intervals.A feature representation called Light-spots Maps is proposed to replace the bounding box and pixel classifications in our detection *** Light-weight networks based on ResNets is used to transform the particle images into Light-spots maps to detect the particle *** experiments,we prove the effectiveness of our method.

关键词： Objects Detection Particles Detection Convolutional Neural Network

来源：评论

学校读者我要写书评

暂无评论

Design and control of a Virtual Teacher with Individual Motor Signature 41

Design and Control of a Virtual Teacher with Individual Moto...

引用

第41届中国控制会议

作者： Siyuan Li Chao Zhai School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this work,a virtual teacher is designed to play the mirror game with human *** individual motor signature is taken into account,which allows to produce diverse teaching *** teaching effect of virtual teacher is assessed by comparing and analyzing the original movement characteristics of human players and the movement characteristics after going through the teaching ***,stability analysis of the teaching model is ***,the feasibility of the model is verified by comparing the data of several groups of samples.

关键词： Virtual teacher Joint action Motor coordination Motor signature control design

来源：评论

学校读者我要写书评

暂无评论

Multi-modal fusion for robust hand gesture recognition based on heterogeneous networks

引用

Science China(Technological Sciences) 2023年第11期66卷 3219-3230页

作者： ZOU YongXiang CHENG Long HAN LiJun LI ZhengWei School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Hand gesture recognition has become a vital subject in the fields of human-computer interaction and rehabilitation *** paper presents a multi-modal fusion for hand gesture recognition(MFHG)model,which uses two heterogeneous networks to extract and fuse the features of the vision-based motion signals and the surface electromyography(s EMG)signals,*** extract the features of the vision-based motion signals,a graph neural network,named the cumulation graph attention(CGAT)model,is first proposed to characterize the prior knowledge of motion coupling between finger *** CGAT model uses the cumulation mechanism to combine the early and late extracted features to improve motion-based hand gesture *** the s EMG signals,a time-frequency convolutional neural network model,named TF-CNN,is proposed to extract both the signals'time-domain and frequency-domain *** improve the performance of hand gesture recognition,the deep features from multiple modes are merged with an average layer,and then the regularization items containing center loss and the mutual information loss are employed to enhance the robustness of this multi-modal ***,a data set containing the multi-modal signals from seven subjects on different days is built to verify the performance of the multi-modal *** experimental results indicate that the MFHG can reach 99.96%and 92.46%accuracy on hand gesture recognition in the cases of within-session and cross-day,respectively.

关键词： leap motion s EMG multi-modal graph neural network hand gesture recognition

来源：评论

学校读者我要写书评

暂无评论

A Security Defense Method Against Eavesdroppers in the Communication-Based Train control System

引用

Chinese Journal of Electronics 2023年第5期32卷 992-1001页

作者： YANG Li WEI Xiukun WEN Chenglin School of Cyberspace College Hangzhou Dianzi University State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University School of Automation Guangdong University of Petrochemical Technology

The communication-based train control system is the safety guarantee for automatic train *** communication brings network security risks to the communication-based train control system. The eavesdropping of the transmitted information by unauthorized third-party personnel will lead to the leakage of the estimated value of the system state, which will lead to major accidents. This paper focuses on solving the problem of defense against eavesdropping threats and proposes an eavesdropping defense architecture. This defense architecture includes a coding mechanism based on punishing eavesdroppers, an information upload trigger mechanism based on contribution, and a random information transmission strategy, and provides a guarantee for the privacy protection of information. This research makes three contributions. First, it is the first attempt to construct an information encoding mechanism with punishing eavesdroppers as the objective function; Second, for the first time, an information upload trigger mechanism based on contribution is proposed; Third, the strategy of random transmission of information is proposed. The proposed method in this paper is verified by taking the medium and low-speed maglev train as the object. The experimental results show that, compared with Gaussian noise and non-Gaussian noise mechanisms, the coding mechanism proposed in this paper can not only protect the security of information but also make the estimation error of eavesdroppers tend to be infinite. Using the state estimation error as a metric, the average growth rate of the state estimation error of the system using the trigger mechanism in this paper is less than 2% while improving the security of the system. The transmission strategy in this paper does not increase the system state estimation error while improving the security of the system.

关键词： Wireless communication Magnetic levitation vehicles Transmitters Information processing control systems Encoding Safety

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Asynchronous Fault Detection for Stochastically Switched Systems With Sojourn Probabilities 41

Event-Triggered Asynchronous Fault Detection for Stochastica...

引用

第41届中国控制会议

作者： Xingyu Tang Xiongbo Wan School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper investigates the event-triggered asynchronous fault detection（FD） problem for discrete-time switched systems with sojourn *** propose a novel asynchronous FD filter（FDF）,of which the sojourn probability is related to the mode of the switched system.A hybrid adjusting variables-dependent event-triggered mechanism（ETM） is devised to reduce the waste of network *** construct a new Lyapunov function that contains the mode of the switched system and a flexible variable in the ETM.A sufficient condition in terms of matrix inequalities is obtained under which the error dynamics is stochastically stable with a prescribed H *** parameters of the FDF are explicitly given based on the feasible solutions to these matrix inequalities.A numerical example is provided to demonstrate the effectiveness of the proposed event-triggered asynchronous FD method.

关键词： Asynchronous fault detection event-triggered switched systems sojourn probabilities

来源：评论

学校读者我要写书评

暂无评论

A Co-regularization Facial Emotion Recognition Based on Multi-Task Facial Action Unit Recognition 41

A Co-regularization Facial Emotion Recognition Based on Mult...

引用

第41届中国控制会议

作者： Chinonso Paschal Udeh Luefeng Chen Sheng Du Min Li Min Wu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex System Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Facial emotion recognition helps feed the growth of the future artificial intelligence with the development of emotion recognition,learning,and analysis of different angles of a human face and head *** worlds recent pandemic gave rise to the rapid installment of facial recognition for fewer applications,while emotion recognition is still within the experimental *** current challenges encountered with facial emotion recognition(FER) are the difference between background *** todays world shows us that humans soon need robotics in the most significant role of human perception,attention,memory,decision-making,and human-robot interaction(HRI) needs *** merging the head pose as a combination towards the FER to boost the robustness in understanding emotions using the convolutional neural networks(CNN).The stochastic gradient descent with a comprehensive model is adopted by applying multi-task learning capable of implicit parallelism,inherent and better global optimizer in finding better network *** executing a multi-task learning model using two independent datasets,the experiment with the FER and head pose learning multi-views co-regularization frameworks were subsequently merged with validation accuracy.

关键词： head pose facial expression convolution neural network deep learning emotion recognition

来源：评论

学校读者我要写书评

暂无评论

Forward and inverse calculation method for shape and depth of seepage channel of embankment 41

Forward and inverse calculation method for shape and depth o...

引用

第41届中国控制会议

作者： Yue-Cheng Zhai Jun-Lei Song Kai-Feng Dong Fang jin Wen-qin Mo Ya-juan Hui School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Seepage diseases in embankments are very common,and if they cannot be treated in time,they will bring serious safety hazards and even cause embankment break *** the location and depth of a seepage channel is the prerequisite and basis for the treatment of seepage *** present,there are several methods are used to detect seepage in embankments,but none of them can accurately calculate or explain the depth of seepage *** magnetic gradient tensor method,which is widely used in the depth calculation of magnetic sources,is only suitable for the magnetic dipole model,and not suitable for the tubular model similar to the seepage *** view of this,this paper draws on the idea of magnetic exploration,and proposes a forward and inverse calculation method for the depth of the seepage *** method first builds a variety of basic seepage channel models based on certain constraints,and calculates the magnetic field value of each model at each measuring point on the ground *** compare the actual measured magnetic field value with the model magnetic field value to find the closest seepage channel ***,by continuously optimizing the closest model,the real seepage channel is gradually *** model calculated by this method can better reflect the depth information of the real seepage channel,and the depth error is less than lm.

关键词： seepage depth magnetic gradient tensor forward and inversion calculation

来源：评论

学校读者我要写书评

暂无评论

Guided Transformative GAN: Joint Face Image Super-Resolution and Frontalization 10

Guided Transformative GAN: Joint Face Image Super-Resolution...

引用

10th International Conference on Systems and Informatics, ICSAI 2024

作者： Mu, Minghao Wang, Wei Lu, Xiaobo School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

ISBN: (纸本)9798331510138

Joint face super-resolution and frontalization of non-frontal low-resolution faces is of significant importance for many face analysis applications. However, at the same time, it is a challenging task. In this paper, a novel Guided Transformative Generative Adversarial Network (GT-GAN) is proposed to address the challenge of generating frontal high-resolution face images from non-frontal low-resolution face images. Existing methods usually treat super-resolution and frontalization as two separate tasks, leading to unsatisfactory processing results. GTG AN innovatively achieves both goals within a unified frame-work. Specifically, we propose Profile Attention Guidance (PAG) to generate landmark heatmaps that provide a priori pose information to the generative network and direct its attention to critical facial regions. In addition, an Attention Fusion Transformation Module (AFTM) is proposed to significantly improve the hallucination performance of the network by utilizing the attention mechanism and STNs, combined with sequential feature enhancement strategies. The experimental results show that GT-GAN exhibits superior performance in the joint face super-resolution and frontalization task on the public face dataset Multi-PIE, which provides new ideas and references for this challenging topic. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Design of intelligent Monitoring System for Blast Furnace Hearth Erosion 41

Design of Intelligent Monitoring System for Blast Furnace He...

引用

第41届中国控制会议

作者： Shuqiao Wang Yan Yuan Jingjie Liang Zhuofu Zhang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper takes the iron-making blast furnace in operation of a steel plant as the specific object,analyzes the erosion status and characteristics of different parts of the furnace hearth and bottom combined with iron-making process and erosion mechanism of the blast furnace,designs an intelligent monitoring system for erosion of the furnace hearth lining,visualizes the temperature measurement *** erosion calculation model is established by using the heat transfer mechanism to quickly solve the erosion boundary for the area with low erosion degree and rate,and performs a fast solution of the erosion *** areas with high erosion degree and rate,the particle swarm optimization algorithm is selected by using its adaptive *** solves the erosion boundary accurately from the rough solution of the mechanism model,and the residual thickness of furnace lining is output and displayed,which helps ironmakers optimize the blast furnace production operation,maintenance strategy,improve production efficiency and reduce energy consumption.

关键词： Blast furnace lining erosion Particle swarm optimization algorithm intelligent monitoring system

来源：评论

学校读者我要写书评

暂无评论

A Soft Grasping Device with the Modularization and Bi-directional Bending Properties 41

A Soft Grasping Device with the Modularization and Bi-direct...

引用

第41届中国控制会议

作者： Ling-Jie Gai Jie Huang Xiaofeng Zong School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This work proposes a fully soft grasping device to perform complex tasks,which consists of the modularized soft grippers and the bi-directional bending soft *** the modularized soft gripper part,we adopt caps to seal both ends of the gripper and connect the adjacent knuckles by *** modularized design not only makes the soft grippers like human fingers to achieve segmental bending,but also reduces the waste caused by local *** the soft holder part,we present a bidirectional bending method to automatically adjust the grasping space,and we also establish a mathematical model to describle the relationship between the soft holder's bending angle and the air ***,in order to evaluate the dynamic response and position accuracy of the grasping device,a PID controller is designed for the soft grasping device to track the step,sine,and square wave ***,the great grasping performance of the fully soft grasping device is verified by experiments.

关键词： Modularized soft gripper Soft holder Adjust grasping range automatically PID controller

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：