检索结果-内蒙古大学图书馆

第33届中国控制与决策会议

作者： Wei Fu Liping Qian Xiaohui Zhu School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture

In view of the lack of intrusion detection data and the slow update of mainstream detection methods,an intrusion detection data generation method based on a generative adversarial network is ***,the overall data is digitized and normalized to maintain the integrity of the data;Then use the ACGAN model to learn the hidden features of the data and generate new data;Finally,evaluate the similarity and validity of the generated data from multiple *** results show that the data generated by this method has similar characteristics to the original data,and can be used to enhance the original data set to meet the needs of intrusion detection systems.

关键词： Smart City Cyber Security Intrusion Detection data Generative Adversarial Network

来源：评论

学校读者我要写书评

暂无评论

Research on Accurate Model of Lithium Battery

Research on Accurate Model of Lithium Battery

引用

第32届中国控制与决策会议

作者： Yongxue Ye Hongyan Ma Jingjian Yang Beijing University of Civil Engineering and Architecture Beijing Key Laboratory of Intelligent Processing for Building Big Data College of Electrical and Information EngineeringBeijing University of Civil Engineering and Architecture

In order to build accurately the external characteristic curve of lithium-ion batteries,this paper improve existing lithium-ion battery models,and verify the improved lithium-ion battery model in *** this paper,for reflecting the accuracy of the improved external characteristics of the lithium-ion battery model,the external characteristic curves of lithium-ion battery model simulation before and after improvement are compared under different temperature and discharge current *** comparison results show that under different operating conditions,the improved model can more accurately reflect the experimental conditions of lithium battery discharge in the concave function discharge area than before the improvement.

关键词： lithium battery mathematical model research Simulink modeling data comparison

来源：评论

学校读者我要写书评

暂无评论

Research on Energy Saving Control of Lighting Systems in Public Buildings

Research on Energy Saving Control of Lighting Systems in Pub...

引用

第33届中国控制与决策会议

作者： Shengyan Li Hongyan Ma Yongxue Ye Jiaming Dou Jingjian Yang Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture National Virtual Simulation Experimental Center for Smart City Education Institute of Distributed Energy Storage Safety Big Data

Most indoor users are unwilling to adjust the lighting equipment and shutters in daily life,resulting in increasing energy consumption of *** this paper,in order to reduce the energy consumption,using fuzzy control to solve this *** using fuzzy control,it could control the opening of indoor lamps,and let the shutters could determine the opening degree of the shutters according to the difference between the set illuminance values and the actual illuminance values on the working *** results show that the fuzzy control of classroom lighting system can reasonably control the running status of lamps according to the actual situation of the environment and reduce the energy consumption of the lighting *** with the single fuzzy controller,the double fuzzy controller of the shutter can make the difference between the illuminance value of indoor working surface,and the set illuminance value smaller,control the light sources in different areas of the room,and improve the uniformity of natural light in the *** method proposed in this paper can solve the energy consumption problem.

关键词： Lighting System Shutter Double Fuzzy Control System Fuzzy Control

来源：评论

学校读者我要写书评

暂无评论

On-line modification of T-S fuzzy models based on gradient descent algorithm

On-line modification of T-S fuzzy models based on gradient d...

引用

第33届中国控制与决策会议

作者： FENG Haodong WEI Dong JIAO Huanyan School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing Municipal Science and Technology Commission

The gradient descent algorithm is applied to the model parameter correction algorithm in view of the shortcoming that T-S fuzzy model cannot be used for real-time adaptive parameter *** this paper,an online model correction method combining T-S fuzzy model with gradient descent algorithm is proposed,and the operation data of a subway air-conditioning system in Wuhan is used for *** experimental results show that the T-S fuzzy model modified by gradient descent algorithm has better accuracy and higher operational efficiency.

关键词： T-S fuzzy model Gradient descent algorithm Air conditioning system model

来源：评论

学校读者我要写书评

暂无评论

Research on Human Pose Classification Based on Improved SVM

Research on Human Pose Classification Based on Improved SVM

引用

第33届中国控制与决策会议

作者： Yingda Zhang Hongyan Ma Yongxue Ye Jiaming Dou Jingjian Yang Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture National Virtual Simulation Experimental Center for Smart City Education Institute of Distributed Energy Storage Safety Big Data

With the development of intelligent buildings and aging of population,designing a high-accuracy alarm system is essential to prevent the elderly from accidentally falling *** address the problems of poor generalization and low accuracy of the SVM in the application of indoor elderly fall alarm systems,in this paper,the human keypoints detection algorithm,which increases the discrimination of the dataset,is proposed to pre-process the *** on this,the features of images are extracted from the histogram of the oriented gradient and the gray-level co-occurrence matrix,and the improved SVM algorithm is then used again for image *** simulation results show that the classification accuracy of using SVM to detect the dataset is around 91%,while the accuracy of the dataset classified as using improved SVM is around 97%.The method proposed in this paper is effective in increasing the accuracy of computer recognition of accidental falls by the elderly.

关键词： SVM Human keypoints Detection Image Classification Accidental Indoor Falls Aging of Population

来源：评论

学校读者我要写书评

暂无评论

Research on STF-DBSCAN based personal semantic location acquisition

Research on STF-DBSCAN based personal semantic location acqu...

引用

第33届中国控制与决策会议

作者： Zixuan Yao Dong Wei Yibing Ran School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing Municipal Science and Technology Commission

With the development of technology and economy,the planning and construction of smart cities have generated new demands and *** intelligence-led technologies and applications are changing people's lives where location-based services are one of the most important technical *** recent years,the popularity of portable devices with GPS(Global Positioning System) function and the development of positioning technology make a large amount of individual track data ***,collecting personal semantic location by mining these tracklogs would be the application direction and research focus of location-based *** semantic location is a practical significant location that users will visit frequently,stay for a long time such as a home address,workplace,etc.).The acquisition of personal semantic location involves two steps,which are acquiring location and matching ***,most of the relevant research use density clustering-based algorithms to collect location *** the original DBSCAN algorithm is used to acquire location,all the trajectory points in the raw dataset need to be included in the clustering samples,which increases calculation and reduces the program *** paper addresses this problem and proposes an advanced density-based clustering algorithm ***,the trajectory points in the raw dataset are filtered to obtain the dwell ***,the dwell points are clustered and analyzed to achieve the purpose of improving the running *** the semantic recognition issue,this paper pre-defines the daily behavior pattern of individual and analyzes the temporal features of the trajectory points in each *** using the same trajectory data samples for location acquisition,the running time of the proposed algorithm in this paper is one-fifteenth of the original algorithm.

关键词： Personal Semantic Location DBSCAN Spatio-temporal Features

来源：评论

学校读者我要写书评

暂无评论

Harmonic detection and filtering of distributed photovoltaic grid-connected system under instantaneous reactive power theory

Harmonic detection and filtering of distributed photovoltaic...

引用

第34届中国控制与决策会议

作者： Wen Haoyu Ma Hongyan Li Shengyan Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture National Virtual Simulation Experimental Center for Smart City Education

To solve the environmental pollution and resources shortage problems of traditional fossil fuels,distributed photovoltaic（PV） grid-connected system are used *** power quality problems caused by harmonics generated during the operation of the system have also received widespread *** and accurate detection and filtering of system harmonics is particularly *** this paper,a brief description of the i-i harmonic detection method based on the instantaneous reactive power（IRP） theory is provided and used to detect the harmonics generated during the operation of the ***,a new LCL-type filter is designed innovatively to filter out the detected harmonics of the ***,the above process is simulated and analyzed by MATLAB/Simulink *** experimental results show that the designed LCL-type filter can reduce the harmonic content of voltage and current on the grid side and effectively improve the power quality of the grid.

关键词： distributed photovoltaic grid-connected system IRP theory harmonic detection LCL-type filter

来源：评论

学校读者我要写书评

暂无评论

RECC: A Relationship-Enhanced Content Caching Algorithm Using Deep Reinforcement Learning

RECC: A Relationship-Enhanced Content Caching Algorithm Usin...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Jiarui Ren Haiyan Zhang Xiaoping Zhou Menghan Zhu School of Information Engineering Ningxia University Yinchuan China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture Beijing China

Mobile edge caching (MEC) is a promising technology to alleviate traffic congestion in the network. Current studies explored deep reinforcement learning (DRL)-based MEC methods. These methods consider the dynamics of the request size to maximize the cache hit rate. However, they usually ignored the potential request relationships among contents. Two contents with a strong relationship are usually requested sequentially. Inspired by this assumption, this paper proposes a relationship-enhanced content caching algorithm using DRL, named RECC. Our RECC infers user preferences by mining the request relationships among contents. In this work, the relationships are modeled as request sequences, and the request features are learned by using graph embedding. These features will be used as input of state in our DRL-based algorithm. We utilize the Wolpertinger architecture to solve the limitation of large discrete action space. The simulation results indicate that our RECC outperformed the traditional cache policies and state-of-the-art DRL-based method in cache hit rate. Furthermore, the proposed RECC has advantages in long-term stability in the environment where content popularity changes dynamically, and also has a higher cache hit rate when handling the requests with number changes dynamically.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Holographic capture and projection system of real object based on tunable zoom lens

引用

PhotoniX 2020年第1期1卷 271-285页

作者： Di Wang Chao Liu Chuan Shen Yan Xing Qiong-Hua Wang School of Instrumentation and Optoelectronic Engineering Beihang UniversityBeijing 100191China Beijing Advanced Innovation Center for Big Data-based Precision Medicine Beihang UniversityBeijing 100191China Key Laboratory of Intelligent Computing&Signal Processing Ministry of EducationAnhui UniversityHefei 230039China.

In this paper, we propose a holographic capture and projection system of real objectsbased on tunable zoom lenses. Different from the traditional holographic system, aliquid lens-based zoom camera and a digital conical lens are used as key parts to reachthe functions of holographic capture and projection, respectively. The zoom camera isproduced by combing liquid lenses and solid lenses, which has the advantages of fastresponse and light weight. By electrically controlling the curvature of the liquid-liquidsurface, the focal length of the zoom camera can be changed easily. As anothertunable zoom lens, the digital conical lens has a large focal depth and the opticalproperty is perfectly used in the holographic system for adaptive projection, especiallyfor multilayer imaging. By loading the phase of the conical lens on the spatial lightmodulator, the reconstructed image can be projected with large depths. With theproposed system, holographic zoom capture and color reproduction of real objects canbe achieved based on a simple structure. Experimental results verify the feasibility ofthe proposed system. The proposed system is expected to be applied to microprojectionand three-dimensional display technology.

关键词： Spatial light modulator Holographic system Zoom lenses Display technology

来源：评论

学校读者我要写书评

暂无评论

Contact lenses detection based on the Gaussian curvature

引用

Journal of Computers (Taiwan) 2019年第2期30卷 158-164页

作者： Wang, Junrui Tian, Qichuan School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing100044 China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing100044 China

Iris recognition is a kind of biometrics recognition with good stability, which is reliable, effective and safe. However, some attack means such as paper printed iris, iris images, simulated eyes, color contact lenses and the others are quite deceptive for iris recognition system. The recognition result of iris recognition system is meaningful only when the authenticity of the feature is guaranteed. At present, the iris anti-spoofing with contact lenses is seldom studied, and the recognition rate is not ideal. Based on the above background, aiming at the characteristics of gaussian curvature change of corneal outer surface caused by wearing contact lenses, this essay proposes a detection method of contact lenses based on depth feature. The effective depth information of cornea is obtained by depth camera, gaussian curvature of cornea is calculated, and features are extracted by sum of squared deviations. Experimental results show that this method can effectively identify whether to wear contact lenses, low error rate, high efficiency, which can meet the requirements of practical application. © 2019 Computer Society of the Republic of China. All rights reserved.

关键词： Contact lenses

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：