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

Wind farm sub-synchronous oscillation identification based on improved variational mode decomposition 8

Wind farm sub-synchronous oscillation identification based o...

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： Ma, Junjie Liu, Fang Wu, Min Ding, Min Li, Danyun School of Information Science and Engineering Central South University Changsha410083 China School of Automation China University of Geoscience Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China

Sub-synchronous oscillation (SSO), an oscillation at a frequency below the synchronous frequency, is introduced to the generator when it exchanges significant energy with series capacitor compensated system. Identifying mode of SSO from the noise-like signal, as well as small disturbance responses with high amplitude noise, can provide early warning for wind farm, and help to adjust controller parameters. For low signal-to-noise ratio of noise-like signal, normal mode identifying method cannot obtain satisfactory results. In order to solve the above problem, an improved variational mode decomposition based method is proposed in this paper to identify SSO mode information from the wind farm noise-like signal. The mode number of variational mode decomposition is adaptively obtained by fast Fourier transformation and average magnitude calculation. The simulation results show that the proposed method can accurately separate SSO of different frequency, and has high mode identification accuracy for different types of oscillations. The proposed method is also suitable for performing online mode identification. © 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： Variational mode decomposition

来源：评论

学校读者我要写书评

暂无评论

A new modified repetitive control system design based on T-S fuzzy model 8

A new modified repetitive control system design based on T-S...

引用

作者： Zhang, Manli Wu, Min Chen, Luefeng Yu, Pan School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Department of Electrical and Electronic Engineering Chiba University Chiba263-8522 Japan

— A new modified repetitive control strategy based on the Takagi-Sugeno fuzzy model is presented for an affine nonlinear system to track a periodic reference and reject a periodic disturbance. Then, a parallel distributed compensation control strategy is developed for the fuzzy repetitive system. Further, taking advantage of the control action during a period and the learning action between periods, a two-dimensional model is established for the closed-loop control system. A sufficient condition in the form of a set of linear matrix inequalities is derived to guarantee the robust asymptotic stability of the closed-loop control system. Simulation results demonstrate the validity of the method. A comparison with conventional modified repetitive control also shows the superiority of the developed method. © 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： Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

Optimization of Overhauser magnetometer based on multi-channel frequency measurement algorithm 37

Optimization of Overhauser magnetometer based on multi-chann...

引用

37th Chinese control Conference, CCC 2018

作者： Wang, Guanzhong Dong, Haobin Ge, Jian Luo, Vang Liu, Huan Yuan, Zhiwen Zhu, Jun Zhang, Haiyang School of Automation China University of Geosciences Wuhan Hubei430074 China Hubei Key Laboratory of Advance Control and Intelligent Automation for Complex Systems Hubei Wuhan430074 China Science and Technology on Near-Surface Detection Laboratory Wuxi Jiangsu214035 China

ISBN: (纸本)9789881563941

Overhauser magnetometer is a weak magnetic measuring instrument based on the dynamic nuclear polarization of free radical species. It has the characteristics of high precision, high sensitivity, low power consumption and continuous measurement. It is widely used in geophysics, aeromagnetic surveying, satellite Magnetic measuring, military and various engineering fields. Aiming at the problem that the measurement accuracy of the magnetometer prototype is low and the measurement effect is poor when the angle between the probe axis and the geomagnetic field is 0°, several optimization methods are proposed and the magnetometer is optimized by adding the frequency measurement channel on the basis of the prototype. Based on the standard deviation of GSM-19 measurement data, comparing the experimental data that use the multi -channel frequency measurement algorithm, the standard deviation of prototype data decreases from 0.397 to 0.203 when the angle between probe axial and geomagnetic field is 45°, the standard deviation of the prototype data decreases from 0.631 to 0.371 when the angle between probe axial and geomagnetic field is 0°, which provides an important reference for the follow-up optimization of the magnetometer. © 2018 Technical Committee on control Theory, Chinese Association of automation.

关键词： Magnetometers

来源：评论

学校读者我要写书评

暂无评论

A Smoothing-Type Algorithm for Solving Monotone Weighted Complementarity Problems

引用

Journal of Physics: Conference Series 2020年第1期1642卷

作者： Xiaoqin Jiang Yujin Huang Department of Public Basic Wuhan Technology And Business University Wuhan Hubei 430065 China School of Automation Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China University of Geosciences 388 Lumo Road Wuhan Hubei 430074 China

The weighted complementarity problem is an extension of the standard finite dimensional complementarity problem. It is well known that the smoothing-type algorithm is a powerful tool of solving the standard complementarity problem. In this paper, we propose a smoothing-type algorithm for solving the weighted complementarity problem with a monotone function, which needs only to solve one linear system of equations and performs one line search at each iteration. We show that the proposed method is globally convergent under the assumption that the problem is solvable. The preliminary numerical results indicate that the proposed method is effective and robust for solving the monotone weighted complementarity problem.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RBF Neural Network Based-PID control for Weight on Bit During Drilling Operation

RBF Neural Network Based-PID Control for Weight on Bit Durin...

引用

Chinese control Conference

作者： Sike Ma Min Wu Luefeng Chen Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan Hubei China

Deep drilling is a costly project and efficiency is of paramount importance. The weight on bit is one of the main operating parameters that influences the drilling efficiency and it was controlled by manual before. But after people saw the giant potential of an auto-drilling system in increasing the drilling efficiency, more and more studies on the feed back control of weight on bit have emerged. This paper mainly studied weight on bit dynamic under the variational formation based on a lumped parameter model and a self-tuning PID controller for weight on bit control. The parameters of the PID controller are tuned by using gradient descent method and RBF neural network identification.

关键词： Neural networks DC motors Feeds Suspensions Lifting equipment Torque Angular velocity

来源：评论

学校读者我要写书评

暂无评论

Parallel intelligence： toward lifelong and eternal developmental AI and learning in cyber-physical-social spaces

引用

Frontiers of Computer Science 2018年第3期12卷 401-405页

作者： Fei-Yue WANG Jun Jason ZHANG Xiao WANG The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China School of Electrical Engineering Wuhan University Wuhan 430072 China Qingdao Academy of Intelligent Industries Qingdao 266109 China

Dear editor, Fundamentally, there are only two main approaches so far in artificial intelligence （AI）： reasoning-oriented formal logic approach and function-oriented computational intelligence approach, so called Neats vs. Scuruffies, which is a reflection of the historical fight between two schools of thought for formalism and empiricism respectively in the field of AI that is continuing even today.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An efficient nondominated sorting algorithm 18

An efficient nondominated sorting algorithm

引用

2018 Genetic and Evolutionary Computation Conference, GECCO 2018

作者： Wang, Junchen Li, Changhe Diao, Yiya Zeng, Sanyou Wang, Hui School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China School of Mechanical Engineering and Electronic Information China University of Geosciences Wuhan China Nanchang Institute of Technology Nanchang China

ISBN: (纸本)9781450357647

Nondominated sorting (NS) is commonly needed in multi-objective optimization to distinguish the fitness of solutions. Since it was suggested, several NS algorithms have been proposed to reduce its time complexity. In our study, we found that their performances are closely related to properties of the distribution of a data set, especially the number of fronts. To address this issue, we propose a novel NS algorithm Filter Sort. We also propose a new benchmark data generator for evaluating the performance of a NS algorithm. Experimental results show that our algorithm is superior to several state-of-the-art NS algorithms in most cases. © 2018 Copyright held by the owner/author(s).

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Extended dissipativity analysis of delayed memristive neural networks based on a parameter-dependent lyapunov functional

Extended dissipativity analysis of delayed memristive neural...

引用

2018 Australian and New Zealand control Conference, ANZCC 2018

作者： Lu, Chengda Zhang, Xian-Ming Wu, Min Han, Qing-Long He, Yong School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China School of Software and Electrical Engineering Swinburne University of Technology MelbourneVIC3122 Australia

ISBN: (纸本)9781538666173

This paper is concerned with extended dissipativity analysis of memristive neural networks with time-varying delays. Using the characteristic function technique, a tractable model of a memristive neural network is obtained. This model is similar to a neural network with polytopic uncertain synaptic weights, enabling us to construct a parameter-dependent Lyapunov functional. By combining this functional and some integral inequalities, a novel extended dissipativity criterion is obtained in terms of linear-matrix-inequalities, where different Lyapunov matrices are used for each form of the memristive neural network. Through a numerical example, this criterion is shown to be less conservative than the one based on a common Lyapunov functional. © 2018 IEEE.

关键词： Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

Electroencephalogram Emotion Recognition Based on A Stacking Classification Model

Electroencephalogram Emotion Recognition Based on A Stacking...

引用

Chinese control Conference (CCC)

作者： Oiao Xie Zhen-Tao Liu Xue-Wen Ding Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

To improve the accuracy of Electroencephalogram (EEG) emotion recognition, a stacking emotion classification model is proposed, in which different classification models such as XGBoost, LightGBM and Random Forest are integrated to learn the features. In addition, the Renyi entropy of 32 channels' EEG signals are extracted as the feature and Linear discriminant analysis (LDA) is employed to reduce the dimension of the feature set. The proposal is tested on the DEAP dataset, and the EEG emotional states are accessed in Arousal-Valence emotion space, in which HA/LA and HV/LV are classified, respectively. The result shows that the average recognition accuracies of 77.19% for HA/LA and 79.06% for HV/LV are obtained, which demonstrates that the proposal is feasible in EEG emotion recognition.

关键词： Electroencephalography Emotion recognition Brain modeling Feature extraction Stacking Entropy Predictive models

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：