检索结果-内蒙古大学图书馆

Chinese control Conference

作者： Zhongzhao Xie Yongbo Li Xinmei Wang Wendi Cai Jing Rao Zhenzhu Liu Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan P. R. China

Facial expression recognition (FER) plays an important role in human-machine interaction. An assistant robot having a close interaction with human being should be able to recognize human facial expression. FER is a non-trivial problem because each individual has his own way to reveal his emotion and the facial expressions of two different persons may not be totally identical. Hence, facial expression recognition is still a challenging problem in computer vision. In this work, we propose a simple solution for facial expression recognition that uses a combination of Convolutional Neural Network and specific image pre-processing steps. The experiments employed to evaluate our technique were carried out using two largely used public databases(CK+, JAFFE). A study of the impact of each image pre-processing operation in the accuracy rate is presented. The proposed method: achieves competitive results when compared with other facial expression recognition methods-97.85% of accuracy in the CK+ database-it is fast to train, and it allows for real time facial expression recognition with standard computers.

关键词： Training Face recognition Convolutional neural networks Neurons Convolution Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Design and Application of a Web-based Comprehensive Evaluation and Decision Support System for Tobacco Cultivation Process

Design and Application of a Web-based Comprehensive Evaluati...

引用

第37届中国控制会议

作者： Gong Chen Yonghua Xiong Wei Chen Hao Zhou School of Automation China University of Geoscience Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Guizhou Tobacco Science Institute

The evaluation and decision support system are widely used in agriculture with the development of information technology. In this paper, a Web-based comprehensive evaluation and decision support system（WCEDSS） is designed for flue-cured tobacco cultivation process. Using the artificial neural networks and some image processing methods, WCEDSS can predict various indicators of tobacco such as yield and flue-cured score, or give decisions at different stages of tobacco cultivation. As the system is developed by the Browser/Server（B/S） architecture, it is possible to make full use of the Internet resources and to facilitate users at any place with access to the Internet. Test results indicates that WCEDSS can achieve good performance. With other auxiliary functions, the system shows potential and extensive practicality in agricultural information management and guidance.

关键词： tobacco Browser/Server architecture evaluate decision support

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Prediction Model Based on BP Neural Network for Predicting CO/CO_2 in Iron Ore Sintering Process

Hierarchical Prediction Model Based on BP Neural Network for...

引用

Chinese control Conference

作者： Ben Xu Xin Chen Yang Zhou School of Automation China University of Geosciences Wuhan China Intelligent Automation for Complex Systems Hubei key Laboratory of Advanced Control Wuhan China

The sintering process is one of the most energy-consuming processes in steelmaking, its carbon fuel consumption accounts for 8% to 10% in the steel production process. To find ways of reducing the energy consumption, it is necessary to predict the carbon efficiency. The value of CO/CO_2 in the carbon emission can reflect the utilization of carbon combustion in sintering process. In this study, the CO/CO_2 is taken to be a measure of carbon efficiency and a hierarchical model is built to predict it. Firstly, the physical and chemical reactions and the carbon flow mechanism in the sintering process are analyzed, and the process parameters that affect the CO/CO_2 are determined. Then, the gray relational analysis method is used to analyze the influence factors to determine the relationship between the parameters, and a hierarchical predictive model for CO/CO_2 is established based on the relationship between the parameters. The hierarchical predictive model is divided into two parts: the predictive models for the thermal state parameters and the predictive model for CO/CO_2. The inputs of the predictive models for the thermal state parameters are the raw material parameters and the operating parameters, and the inputs of the predictive model for CO/CO_2 are the predicted values of the predictive models for the thermal state parameters. Finally, the simulation results verify the effectiveness of the proposed modeling method. This method can provide a theoretical basis for the optimization and control of carbon efficiency in the sintering process.

关键词： Predictive models Combustion Correlation Mathematical model Carbon dioxide Chemicals Raw materials

来源：评论

学校读者我要写书评

暂无评论

Modeling and Maximizing Angle Coverage in Visual Sensor Networks

Modeling and Maximizing Angle Coverage in Visual Sensor Netw...

引用

第37届中国控制会议

作者： Yonghua Xiong Manjie Lu Wei Chen School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Guizhou Tobacco Science Institute

Maintaining the quality of network coverage is a major concern in visual sensor networks. In this paper, we study the angle coverage problem in visual sensor networks, considering the target is very large, and each camera node can only monitor a portion of its perimeter. The goal of the proposed work is to schedule camera nodes to achieve maximum angle coverage in different period. Firstly, we establish a novel coverage model and formally prove that the problem is NP-hard in ***, we present a scheduling scheme based on greedy algorithm, to schedule camera nodes into disjoint cover sets working in ***, we conclude that the approximate ratio of the proposed algorithm is k, theoretically, and the time complexity of the algorithm is O（n）. Finally, extensive simulations have been conducted to evaluate the performance of the proposed algorithm.

关键词： Visual sensor network angle coverage camera node scheduling greedy algorithm

来源：评论

学校读者我要写书评

暂无评论

Street Object Detection Based on Faster R-CNN

Street Object Detection Based on Faster R-CNN

引用

第37届中国控制会议

作者： Wendi Cai Jiadie Li Zhongzhao Xie Tao Zhao Kang Lu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems The Library of Wuhan University of Technology

With the increased number of traffic accidents, the research and development of smart cars have been *** detection of street objects has become one of the important research topics. Generic Model detection algorithm based on Convolution Neural Network(CNN) need to design the training model, while the training and testing of the model will take a lot of time. Transfer Learning is used to fine-tune the pre-trained models, using the Image task datasets of COCO, transferring a generic deep learning model to specific one with different weights and outputs. Furthermore, the CNN structure is adjusted to improve overall performance, and the street environment is trained to the special scene. We compare the results of experiments,and the results showed that the network which is fine-tuned is effective.

关键词： Transfer Learning Faster R-CNN Inception-ResNet-v2 Object Detection

来源：评论

学校读者我要写书评

暂无评论

Optimal Consensus control of Unknown Nonlinear Multi-Agent Systems Using Adaptive Dynamic Programming via MRAC

Optimal Consensus Control of Unknown Nonlinear Multi-Agent S...

引用

第37届中国控制会议

作者： Hao Fu Xin Chen Wei Wang Jinbin Li Yaodong Zhang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems State Grid Hubei Electric Power Research Institute

This paper introduces an optimal consensus control scheme for nonlinear multi-agent systems with completely unknown dynamics. In general, it is difficult to solve the coupled Hamilton-Jacobi-Bellman（HJB） equations, which the optimal consensus control relies on in multi-agent systems, especially unknown nonlinear systems. For the purpose of solving the problem, we propose an optimal consensus control approach based on the model reference adaptive control（MRAC） and adaptive dynamic programming（ADP）. Using the structure of the diagonal recurrent neural network, the identifier and controller are devised to achieve MRAC for every plant of the unknown nonlinear systems, i.e. the reference model serves as a dynamic model of each individual agent. Then, according to reference models of distributed agents, an adaptive dynamic programming（ADP）is introduced to approximate the solution of the coupled HJB equations.

关键词： Multi-agent systems optimal consensus model reference adaptive control adaptive dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Hexagon-Shaped Screw Recognition and Positioning System Based on Binocular Vision

Hexagon-Shaped Screw Recognition and Positioning System Base...

引用

第37届中国控制会议

作者： Fang Wang Xin Chen Chang Tan Jinbin Li Yaodong Zhang School of Automation China University of Geoscience Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems State Grid Hubei Electric Power Research Institute

Traditional artificial live work asks for a high standard with operator’s mental state and technical level in high-voltage and strong-magnetic environment,which not only reduces the efficiency of modern production and living but also causes potential threats to the safety of ***,developing robot live work has great significance for both academic research and industrial applications.A key problem of the live work for an industrial robot is recognition and positioning of the hexagonshaped screw in substation with high *** solve this problem,this article designs a hexagon-shaped screw recognition and positioning system based on binocular vision in transformer substation.A method for stereo matching including 3 steps is proposed:edge noise of the target is reduced by median filter at the beginning;then the target can be obtained through the image segmentation method of adjusting threshold;further moments are used to express the centers of hexagons in 2 images which work as stereo matching *** depth information can be obtained due to visual geometric relationships based on stereo model and camera calibration parameters based on camera *** experiment results show that the binocular system designed in this article can accurately identify the target with good stability,and the measurement error is controlled in 4%.

关键词： Binocular stereo vision Image segmentation Stereo matching Depth information

来源：评论

学校读者我要写书评

暂无评论

Development of electric cart for improving walking ability — application of control theory to assistive technology

引用

Science China(Information Sciences) 2017年第12期60卷 262-270页

作者： Jinhua SHE Yasuhiro OHYAMA Min WU Hiroshi HASHIMOTO School of Engineering Tokyo University of Technology School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Master Program of Innovation for Design & Engineering Advanced Institute of Industrial Technology

This paper explains the development of an electric cart that helps the elderly maintain or improve their physical strength. Unlike commercially available ones, it has a pedal unit that provides some exercise for a user in training his lower limbs. An impedance model describes the feeling of pushing the pedals. The largest pedal load is determined based on a pedaling experiment. An H∞ controller is designed for each of the largest pedal load and virtually no load. A control law, which is based on the concept of dynamic parallel distributed compensation, is designed using the rating of perceived exertion of a driver as a criterion to choose a pedal load between the largest and almost zero. Five university students and twelve elderly people participated experiments to verify the system design and the validity of the system.

关键词： aging Borg’s scale dynamic parallel distributed compensation electrical cart H_∞ control Karvonen formula lower limbs pedaling rating of perceived exertion

来源：评论

学校读者我要写书评

暂无评论

Multi-Convolution Neural Networks-Based Deep Learning Model for Emotion Understanding

Multi-Convolution Neural Networks-Based Deep Learning Model ...

引用

Chinese control Conference

作者： Luefeng Chen Min Wu Wanjuan Su Kaoru Hirota Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Tokyo Institute of Technology Yokohama Japan

Multi-convolution neural networks-based deep learning model in combination with multimodal data for emotion understanding is proposed, in which facial expression and body gesture are used to achieve emotional states recognition for emotion understanding. It aims to understand coexistence multimodal information in human-robot interaction by using multi-convolution neural networks, where multilayer convolutions are connected in series and multiple networks are executed in parallel. Moreover, when optimizing the weights of deep neural network by traditional method, it is easy to fall into poor local optimal. To address this problem, a hybrid genetic algorithm with stochastic gradient descent is developed, which has the capacity of inherent implicit parallelism and better global optimization of genetic algorithm so that it can adaptively find the better weights of the network. And in order to speed up the convergence of the proposal, the weights optimized by stochastic gradient descent will be taken as a chromosome of genetic algorithms initial population, and it also can be used as a priori knowledge. To verify the effectiveness of the proposal, experiments on benchmark database of spontaneous emotion expressions are developed, and experimental results show that the proposal outperforms the state-of-the-art methods. Meanwhile, the preliminary application experiments are also carried out and the results indicate that the proposal can be extended to human-robot interaction.

关键词： Feature extraction Genetic algorithms Biological cells Machine learning Sociology Statistics Neural networks

来源：评论

学校读者我要写书评

暂无评论

Calculation Method of Load Distribution for Two-crane Cooperative Lift

Calculation Method of Load Distribution for Two-crane Cooper...

引用

第37届中国控制会议

作者： Xiaoling Shen Jianqi An Takao Terano School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Engineering Tokyo University of Technology

Cooperative lifting by two cranes is widely used in the current construction site. Since the influence of changeable load in the cooperative lifting process, it is essential to take the load distribution into consideration while planning the lifting path to ensure the safety of the whole lifting process. However, most researches did not consider the reasonable actual load distribution or just used a certain load in the lift process. This paper analyzes the relationship between crane operations and the pose of the lifted object. Then based on this relationship, this paper gives the method calculating the distribution of actual load over each crane that the planning approach is based. This paper also gives calculation methods and constraints for the skew angle of each lifting rope. The results of simulation show the effectiveness of this calculation method.

关键词： Cooperative Lifting Actual Load Calculation

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：