检索结果-内蒙古大学图书馆

IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI

作者： Polash Kumar Das Bin Hu Chang Liu Kaixin Cui Prabhat Ranjan Gang Xiong School of Electronic and Information Engineering South China University of Technology Guangzhou China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Science Beijing China College of Computer Science Sichuan University Chengdu China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China The Cloud Computing Center Chinese Academy of Science Dongguan China

In biometrics, face recognition methods are achieving momentum with recent progress in the computer vision(CV). Face recognition is widely used in the identification of an individual's identity. Unfortunately, in recent research work has revealed this face biometrics system is unprotected to spoofing attacks using by very low price instrument such as printed 2D photos attack, 3D masking attack and taking videos using smart devices (reply attack). Therefore, a Liveness Attack Detection (LAD) approach is needed to improve the high-quality security of face recognition system. Most of the earlier worked LAD methods for face anti-spoofing methods have highlight on using the handcrafted features, which are developed by expert knowledge of researcher. As example Gabor filter, Histogram of Oriented Gradients, local ternary pattern, and the Local Binary Pattern. Because of that, the extracted features consider limited factors of the problem, yielding a capture accuracy that is very low and changes with the point of presentation in attack face images. The deep learning method has developed in the computer vision research community, which is proven to be suitable for automatically training. In this article, we approach to mix or combine the handcrafted features and deep neural network features to design the discriminant face spoofing detection. The handcrafted features were based on LBP analysis. We examine the features information from the brightness and the chrominance channels using LBP descriptor. In deep features, we present an approach based on pre-trained convolutional neural network VGG-16 model using static features to recognize video and printed(2D) photo attacks. By attaching this two types of image features on our dataset and public databases, we get good results to identify real and attack images feature, called hybrid features, which has better discrimination ability to understand spoofing image feature.

关键词： Face Videos Feature extraction Databases Face recognition Password

来源：评论

学校读者我要写书评

暂无评论

Analysis and Maximum Efficiency Design for Wireless Power Transfer systems

Analysis and Maximum Efficiency Design for Wireless Power Tr...

引用

Chinese control Conference

作者： Bing Cao Hongbin Wang Qingyi Wang Min Ding Quan Yin Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China State Grid Corporation of China Wuhan China School of Automation Huazhong University of science and technology Wuhan China

How to stabilize the output voltage while ensuring the maximum charging efficiency of the system is a problem faced by the development of wireless power transfer(WPT). Especially in the dynamic environment, the change of system coupling coefficient or load resistance will have a huge impact on the system. In this paper, a two-stage DC-DC converter control mode is used to control the system with the goal of dynamic charging demand. Among them, the system achieves impedance matching through the receiver DC-DC converter to ensure the transmission efficiency of the system, and in order to match the impedance, the voltage and current information in the coil is used to calculate the coupling coefficient, then, the coupling coefficient can be used to achieve maximum efficiency. The system output voltage is stabilized by using the transmitter DC-DC converter. The simulation experiment shows that the control mode can stabilize the output voltage well, and is more efficient than the single receiver closed loop control(SRCLP) system.

关键词： Resistance Couplings DC-DC power converters control systems Voltage control Receivers Frequency control

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

Chinese control Conference

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

With the increased number of traffic accidents, the research and development of smart cars have been promoted. The 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： Object detection Computer vision Training Proposals Machine learning Automobiles Convolution

来源：评论

学校读者我要写书评

暂无评论

Massive MIMO Channel Modeling Using Map-based Ray Tracing Method

Massive MIMO Channel Modeling Using Map-based Ray Tracing Me...

引用

2017 7th IEEE International Symposium on Microwave, Antenna, Propagation, and EMC Technologies

作者： Junliang Yao Haipeng Ren Qing Liu Shaanxi Key Laboratory Complex System Control and Intelligent Information Processing Xi'an University of Technology

Massive multiple-input multiple-output(MIMO), with giant array size and multi-dimension array structure, has been widely considered as a key physical layer technique in future wireless communications. With regarding the large number of antenna elements, some new challenges and issues are arising, e.g. modeling the near-field effects in MIMO channel and the high computational complexity. To solve these problems, a statistical channel model is proposed based on the cluster delay line(CDL) framework. The proposed model focuses on the spherical wavefront theory, thus can be applied to the massive MIMO system. Furthermore, the map-based ray tracing algorithm with low complexity is used to compute the statistical parameters, such as pathloss, delay spread, etc., The numerical analysis results show that the proposed channel model is enable to describe the main characteristics of massive MIMO channel.

关键词： large scale MIMO wireless channel modeling ray tracing algorithm path loss delay spread

来源：评论

学校读者我要写书评

暂无评论

Optimal switching integrity attacks in cyber-physical systems

Optimal switching integrity attacks in cyber-physical system...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Guangyu Wu Jian Sun The Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing China

ISBN: (纸本)9781538629024

In this paper, an optimal switching data integrity attack schedule method is presented. It is assumed that an attacker is able to inject false data to partial actuators of a healthy system at each instant. Optimal switching attack represents a growing class of cyber-physical attacks that aim to damage a target system via a controlled switching of attacked units. A feedback attack law is proposed to maximize a weighted quadratic performance. Two switching conditions are designed to obtain the optimal sequence of the attacked actuators via the Maximum Principle. Finally, numerical results are provided to illustrate the effectiveness of the proposed method.

关键词： Switches Actuators Cyber-physical systems Jamming Optimal control system performance

来源：评论

学校读者我要写书评

暂无评论

Analysis of Influencing Factors on Carbon Monoxide Utilization Rate of Blast Furnace Based on Multi-Timescale Characteristics 36

Analysis of Influencing Factors on Carbon Monoxide Utilizati...

引用

第36届中国控制会议

作者： Jianqi An Yuwan Yang Min Wu Takao Terano School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Department of Computer Science School of ComputingTokyo Institute of Technology

ISBN: (纸本)9781538629185

In the blast furnace,due to the different changing frequency of different operations,and the different reaction time of gas,liquid and solid materials,there exists multi-timescale characteristics in the iron-making ***,not enough attention has been paid to this characteristic,most of the analyses on the blast furnace state before are under a fixed time ***,this paper makes a analysis of influencing factors on carbon monoxide utilization rate of blast furnace based on multi-timescale ***,the factors that affect the carbon monoxide utilization rate are analyzed from different time ***,in the short time scale,the individual influencing time scale of the permeability index,total pressure difference and top temperature is found by the support vector machine（SVM） *** in the long time scale,the influencing time scale of burdening is *** the validity of each model is verified by the field data of the blast furnace.

关键词： Multi-time scales Carbon monoxide utilization Support vector machine Blast furnace

来源：评论

学校读者我要写书评

暂无评论

A method of power grid partition based on influence law of component reliability

引用

IOP Conference Series: Earth and Environmental Science 2019年第5期233卷

作者： Wenzhu Zhang Yong Wang Ying Ding Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education (Shandong University) Jinan China State Grid of China Technology College Jinan China

In view of the increasing scale of power network and the complexity of reliability calculation, how to divide large power grid to reduce computational complexity is an urgent problem to be solved. In this paper, a partition method based on the rule of reliability influence between components is proposed to judge the area division of power network. By calculating the influence of component outage on the reliability index of other components, we can analyse the strength of the system regional relation, and partition the power system at the weakly connected nodes to reduce the computational complexity of reliability. At the end of the paper, we use the IEEE-RTS79 system model to simulate and calculate. By analysing the data and comparing with the partition results of other algorithms, we can verify the rationality of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Iterative Learning control for Alloy Batch Weighing Process in Refining Furnace 36

Robust Iterative Learning Control for Alloy Batch Weighing P...

引用

第36届中国控制会议

作者： Yibo Huang Jianqi An Yong He Min Wu Takao Terano School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Department of Computer Science School of ComputingTokyo Institute of Technology

ISBN: (纸本)9781538629185

This paper proposes a robust iterative learning control method for the refining furnace alloy weighing process to solve the problem of the poor control accuracy and stability caused by the changing of alloy properties and the frequency of the vibration feeder. First, a two dimensional（2D） weighing model was established based on the analysis of the dynamic characteristics of alloy weighing process. Second, a control scheme is proposed for the 2D model of alloy weighing ***, a robust iterative learning controller is developed and a stability condition of the 2D system is derived through linear matrix inequality（LMI） obtained by a 2D Lyapunov-Krasovskii function. Finally, the simulation results show that the proposed method can sufficiently improve the control precision of the alloy weighing process.

关键词： Iterative learning control 2D weighing model Batch process Alloy weighing process Robust control

来源：评论

学校读者我要写书评

暂无评论

Current controller Based on Recurrent Neural Network for Grid-Connected Converter

Current Controller Based on Recurrent Neural Network for Gri...

引用

Chinese control Conference (CCC)

作者： Xuefen Wang Hongbin Wang Qingyi Wang Min Ding Quan Yin Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China State Grid Corporation of China Wuhan China School of Automation Huazhong University of science and technology Wuhan China

Three-phase grid-connected converters are widely used in renewable and electric power system applications. Due to system nonlinearity and time-variant characteristic, there are limitations in standard decoupled d-q vector control mechanism. To mitigate these limitations, a RNN vector controller trained with Levenberg-Marquardt and FATT(Forward accumulation through time) algorithm is designed. The simulation is researched by using MATLAB software, and the results show that training neural-network algorithm is effective and the system using RNN vector control method outperforms the system using conventional PI control method under low sampling rate conditions.

关键词： Mathematical model Training Artificial neural networks Recurrent neural networks Voltage control Convergence

来源：评论

学校读者我要写书评

暂无评论

The Ball Mill Load Measuring algorithm though Grinding tone signal based on GA

The Ball Mill Load Measuring algorithm though Grinding tone ...

引用

2017 International Seminar on Artificial Intelligence, Networking and Information Technology

作者： Yingmin Yi Haichuan Yang Lu Sun Xiaoli Liu Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology

For a high energy loss and complex system of ball mill,this paper provide a ball mill load detection method based on genetic algorithm optimizing BP neural *** effective frequency range of mill sound signal is *** soft measurement model of mill load based on mill sound signal is *** order to solve the problem which converge slowly and easily reach minimal value,the global optimization of GA(genetic algorithm) local optimization of BP neural network will be combined to improve the BP neural *** with the detected mill load error generated from existing BP neural network and RBF neural network based on *** experiments results show that the proposed algorithm has better precision.

关键词： Ball mill load Grinding tone signal Genetic algorithm RBF neural network

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：