检索结果-内蒙古大学图书馆

Chinese control Conference

作者： Xiangyang Dai Wei Xue Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan

Remote sensing hyperspectral imaging can obtain rich spectral information of terrestrial objects, which allows the indistinguishable matter in the traditional wideband remote sensing to be distinguished in hyperspectral remote sensing. Hyperspectral image has the characteristics of "combining image with spectrum". Making full use of spectral information and spatial information in hyperspectral image is the premise of obtaining accurate classification results. At present, most of hyperspectral data feature extraction algorithms mainly utilize local spatial information in the same channel and spectral information in the same spatial location of different channels. However, these methods require a large amount of prior knowledge, it is difficult to fully grasp the hyperspectral data of all spatial and spectral information, and the model generalization ability is poor. With the development of deep learning, convolutional neural network shows superior performance in all kinds of visual tasks, especially in the two-dimensional image classification, and could get a high classification accuracy. In this paper, an image classification method based on three-dimensional convolution neural network is proposed based on the structural properties of hyperspectral data. In the proposed method, first the stereo image blocks of hyperspectral data are intercepted, then multi-layer convolution and pooling operation of extracted blocks by convolutional neural network are implemented to obtain the essential information of hyperspectral data, finally the classification of hyperspectral data is completed. The experimental results show the proposed method could provide better feature expression and classification accuracy for hyperspectral image.

关键词： Hyperspectral imaging Image classification Convolution Feature extraction Support vector machines

来源：评论

学校读者我要写书评

暂无评论

On Event-triggered Adaptive Robust control 36

On Event-triggered Adaptive Robust Control

引用

第36届中国控制会议

作者： Yuan Huang Junzheng Wang Dawei Shi State Key Laboratory of Intelligent Control and Decision of Complex Systems

ISBN: (纸本)9781538629185

In this work,an event-triggered adaptive robust controller（ET-ARC） design is considered for a continuous-time nonlinear system combined with structural uncertainties and parameter *** the event-trigger scheme,the controller only can obtain the sampled date of the output measurement at some certain instants determined by the designed triggering condition and therefore the performance of the ET-ARC depends on the triggering condition ***,in this work,for the adaptive robust control scheme,an event-triggered transmission strategy is proposed,which relies on the output measurement of the nonlinear ***,based on this strategy,the design idea of the adaptive robust controller is presented such that the tracking performance is ***,based on a more general assumption,we provide a possible formation of control signal which satisfies the requirement proposed.

关键词： Adaptive robust control event-triggered transmission parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Forest Representation Learning with Multiscale Contour Feature Learning for Leaf Cultivar Classification

Forest Representation Learning with Multiscale Contour Featu...

引用

IEEE International Conference on Bioinformatics and Biomedicine

作者： Wenbo Zheng Chao Gou Lan Yan School of Software Engineering Xi'an Jiaotong University Chinese Academy of Sciences School of Intelligent Systems Engineering Sun Yat-sen University Chinese Academy of Sciences The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences

ISBN: (纸本)9781728118680

Automated plant species identification system could help botanists and layman in identifying plant species rapidly. Deep learning is robust for feature extraction as it is superior in providing deeper information of images. However, deep neural networks based leaf cultivar classification model can not deeply mine the contour features of leaf images. Besides, the deep neural networks are very data-hungry due to the large complexity of the models, which means that the model's performance can decrease significantly when the size of the training data decreases. In this paper, we propose the leaf cultivar classification model based on forest representation learning and multiscale contour feature learning. Firstly, we build the multiscale contour feature learning to extract the contour features of leaf images. Then, the original input features are transformed by the data augmentation method to enhance the ability of feature expression, and the autoencoder by forest performs the data of dimensionality reduction on the features. Finally, we use the improved deep forest algorithm and autoencoder by forest to build forest representation learning for classification. The experimental results show that the proposed algorithm has higher performance than the original deep forest (gcForest) algorithm and other existing start-of-art algorithms, and has higher performance and efficiency than other deep learning algorithms.

关键词： Leaf Cultivar Classification Deep Learning Deep Forest AutoEncoder by Forest Data Augmentation contour Forest Learning plant species foliage Botanists Taxonomy dimensionality reduction algorithms cultivars HIGH-PERFORMANCE

来源：评论

学校读者我要写书评

暂无评论

Adaptive robust control for four-motor driving servo system with uncertain nonlinearities

引用

control Theory and Technology 2017年第1期15卷 45-57页

作者： Wei ZHAO Xuemei REN Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing 100081 China

A novel adaptive robust control （ARC） is presented for the four-motor driving servo systems with the uncertain nonlinearities and actuation failures, such that the load tracking control is achieved with the proximate optimal-time. By applying the proposed scheme, several control objectives are achieved. First, the nonlinear synchronization algorithm is presented to maintain the velocity synchronization of each motor, which provides fast convergence without chatting. Moreover, the time-varying bias torque is applied to eliminate the effect of backlash and reduce the waste of energy. Then, the ARC is designed to achieve the proximate optimal-time output tracking with the transient performance in L2 norm, where the friction and actuation failures are addressed by the adaptive scheme based on the norm estimation of unknown parameter vector. Finally, the extensive simulated and experimental results validate the effectiveness of the proposed method.

关键词： Four-motor driving servo systems adaptive robust control velocity synchronization control friction backlash,actuation failures

来源：评论

学校读者我要写书评

暂无评论

An Electrocommunication System Using FSK Modulation and Deep Learning Based Demodulation for Underwater Robots

arXiv

引用

arXiv 2020年

作者： Wang, Qinghao Liu, Ruijun Wang, Wei Xie, Guangming State Key Laboratory of Turbulence and Complex Systems Intelligent Biomimetic Design Lab College of Engineering Peking University Beijing100871 China College of Electrical and Information Engineering Guangxi University of Science and Technology Liuzhou545006 China Department of Urban Studies and Planning Massachusetts Institute of Technology CambridgeMA02139 United States Massachusetts Institute of Technology CambridgeMA02139 United States Institute of Ocean Research Peking University Beijing100871 China Peng Cheng Laboratory Shenzhen518055 China

Underwater communication is extremely challenging for small underwater robots which typically have stringent power and size constraints. In our previous work, we developed an artificial electrocommunication system which could be an alternative for the communication of small underwater robots. This paper further presents a new electrocommunication system that utilizes Binary Frequency Shift keying (2FSK) modulation and deep-learning-based demodulation for underwater robots. We first derive an underwater electrocommunication model that covers both the near-field area and a large transition area outside of the near-field area. 2FSK modulation is adopted to improve the anti-interference ability of the electric signal. A deep learning algorithm is used to demodulate the electric signal by the receiver. Simulations and experiments show that with the same testing condition, the new communication system outperforms the previous system in both the communication distance and the data transmitting rate. In specific, the newly developed communication system achieves stable communication within the distance of 10 m at a data transfer rate of 5 Kbps with a power consumption of less than 0.1 W. The substantial increase in communication distance further improves the possibility of electrocommunication in underwater robotics. Copyright © 2020, The Authors. All rights reserved.

关键词： Demodulation

来源：评论

学校读者我要写书评

暂无评论

From AR to AI: Augmentation Technology for intelligent Surgery and Medical Treatments

引用

IFAC-PapersOnLine 2020年第5期53卷 792-796页

作者： Mei Zhang Zhicheng Zhang Xiao Wang Hui Yu Yifan Xia Kanran Tan Fei-Yue Wang The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China and also with the Qingdao Academy of Intelligent Industries Qingdao 266109 China The Department of the 7th Medical Center of PLA General Hospital Beijing 100700 China The Department of Computer Science Purdue University West Lafayette Indiana 47906 USA The School of Creative Technologies University of Portsmouth UK The Department of Computer Science Johns Hopkins University Baltimore Maryland USA

With the development of augmented reality (AR) technologies, more and more approaches are proposed for medical applications. With the help of AR technology, the doctor can highly improve the spatial perception and obtain more information beneath the displayed image. Generally, 3D reconstruction, registration, tracking and depth visualization are all important for an AR system, which directly determine the accuracy of the system. However, none of recent systems have achieved a perfect 3D vision for doctors. It is particularly challenging for the AR system to perform well for operation on highly deformable body tissues. Therefore, there is an urgent need to improve the 3D vision and intelligence of AR systems. In this paper, we provide a review of the recent development of augmentation technologies for surgery and medical treatment. And then, we introduce the parallel intelligence theory into AR systems, which can provide a feasible approach to enhance the efficiency.

关键词： Potential impact of automation open problems Augmented reality Medical treatment Parallel theory 3D technology

来源：评论

学校读者我要写书评

暂无评论

Distributed auction-based coverage motion planning for multiple cooperative robots 8

Distributed auction-based coverage motion planning for multi...

引用

8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and control Applications, ISCIIA and ITCA 2018

作者： Gao, Guanqiang Xin, Bin School of Automation Beijing Institute of Technology Beijing100081 China Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing100081 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing100081 China

The multi-robot coverage motion planning (MCMP) problem refers to a typical task where every point of the target area must be covered by robots at least once. This paper designs a novel efficient offline algorithm to solve the MCMP problem, which is extended from the spiral-spanning tree coverage algorithm. A distributed auction mechanism is designed for the cooperative task allocation in the proposed algorithm. In this mechanism, each robot will be an auctioneer which chooses a suitable cell as an auction item form its neighbor vertexes and determines a winner robot. According to the connectedness and the balance of each robot’s graph, bidders will submit proper biddings to the auctioneer. After the auction processes, acceptable coverage trajectories can be planned rapidly. Computational experiments validate the effectiveness of the proposed MCMP algorithm. Meanwhile, the proposed algorithm is compared with the state-of-the-art algorithm named DARP. The comparative results show that the auction-based MCMP algorithm has apparent advantages in the running time and the makespans for large crowded configuration spaces. © ISCIIA and ITCA 2018 - 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and control Application.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Differential-Evolution-Based Generative Adversarial Networks for Edge Detection

Differential-Evolution-Based Generative Adversarial Networks...

引用

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Wenbo Zheng Chao Gou Lan Yan Fei-Yue Wang School of Software Engineering Xi'an Jiaotong University The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences School of Intelligent Systems Engineering Sun Yat-sen University School of Artificial Intelligence University of Chinese Academy of Sciences

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

Since objects in natural scenarios possess various scales and aspect ratios, learning the rich edge information is very critical for vision-based tasks. Conventional generative adversarial networks (GANs) based methods for edge detection don't perform so well due to model collapse. In order to capture rich edge information and avoid model collapse as much as possible, we consider the learning of GANs as an evolutionary optimization and propose a novel method termed as differential-evolution-based generative adversarial networks (DEGAN) for richer edge detection. In particular, built upon GANs structure, we introduce an improved differential evolutionary algorithm to refine the input of generator, with fitness function evaluated by the discriminator. Experimental results on the well-known BSDS500 and NYUD benchmarks indicate our proposed DEGAN can achieve state-of-the-art performance while retaining a fast speed and validate its simplicity, effectiveness, and efficiency. The high quality of our results on edge detection with proposed DEGAN may promise to make other vision-based tasks work better.

关键词： Image edge detection Generators Gallium nitride Training Generative adversarial networks Evolutionary computation Evolution (biology)

来源：评论

学校读者我要写书评

暂无评论

Chaotic Oscillator Based on a Modified Voltage-controlled HP Memristor Model

Chaotic Oscillator Based on a Modified Voltage-Controlled HP...

引用

IEEE Advanced Information Management,Communicates,Electronic and Automation control Conference (IMCEC)

作者： Zhen Wang Chao Sun Fang Jin Wenqin Mo Junlei Song Kaifeng Dong Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

Different from previous studies on memristive chaotic oscillators which tended to adopt common mathematical models but lacked practical consideration, in this paper, a novel memristive chaotic oscillator based on a modified voltage-controlled HP memristor model was proposed for the first time. By replacing Chua's diode with this model in a canonical Chua's circuit, we derived an oscillator characterized by rich dynamics such as special-shaped attractors, a wide range of chaos and insensitivity to the initial value of the memristor. These features were systematically investigated in terms of bifurcation diagrams, Poincaré map, time series, Lyapunov exponents, etc.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Multi-robot distributed cooperative monitoring of mobile targets 3rd

Multi-robot distributed cooperative monitoring of mobile tar...

引用

3rd International Conference on Intelligence Science, ICIS 2018

作者： Jiang, J.Q. Xin, B. Dou, L.H. Ding, Y.L. School of Automation Beijing Institute of Technology Beijing100081 China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing100081 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9783030013127

Cooperative monitoring targets of mobile robots is of great importance in military, civil, and medical applications. In order to achieve multi-robot coordinated monitoring, this paper proposes a new distributed path planning algorithm. In this algorithm, a method of dynamic sequential decision making is used firstly to determine which robots should be moved to the neighbourhoods of the target path. A distributed cooperative path planning algorithm is then proposed in which the robots can only utilize their local information to make the joint monitoring areas of robots cover the target path. To reduce the chance of detection and ensure enough time to implement monitoring handover, our distributed algorithm can guarantee enough overlapped monitoring areas between adjacent robots. The effectiveness of the algorithm was verified by simulation experiments and a comparison experiment in typical scenarios. © IFIP International Federation for Information Processing 2018.

关键词： Monitoring

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：