检索结果-内蒙古大学图书馆

6th International Conference on Mechatronics and Intelligent Robotics, ICMIR 2022

作者： Song, Hao Peng, Yi Wang, Rui Zhao, Xiong Faculty of Computer Information Kunming Metallurgy College Kunming650033 China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Faculty of Information and Intelligent Engineering Yunnan University of Business Management Kunming650106 China

ISBN: (纸本)9781510656635

D2D(Device-to-device) improves communication quality by reusing cellular users' spectrum resources, becoming one of the key technologies for super-large data processing and massive devices accessing in the 5G. Due to load imbalance and co-frequency interference caused by distance change or increase in the number of users, this paper introduces interference management strategy in the 5G scenario where D2D communication and cellular communication coexist. By establishing up and down link resource model of D2D user reuse cellular communication to measure user throughput, and then control transmitting power and the distance between user and base station to reduce the influence of interference on the system. Simulation results show that compared with other traditional algorithms, the network performance of D2D communication based on interference management is significantly improved. © 2022 SPIE.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

A Critical Review of Active Distribution Network Reconfiguration:Concepts,Development,and Perspectives

引用

Energy engineering 2024年第12期121卷 3487-3547页

作者： Bo Yang Rui Zhang Jie Zhang Xianlong Cheng Jiale Li Yimin Zhou Yuanweiji Hu Bin He Gongshuai Zhang Xiuping Du Si Ji Yiyan Sang Zhengxun Guo Faculty of Electric Power Engineering Kunming University of Science and TechnologyKunming650500China China Southern Power Grid Honghe Power Supply Bureau Mengzi661100China Faculty of Science Kunming University of Science and TechnologyKunming650500China China Southern Power Grid Yuxi Power Supply Bureau Yuxi653100China Yunnan Electric Power Grid Co. Ltd.Kunming650000China College of Electrical Engineering Shanghai University of Electric PowerShanghai200090China College of Information Science and Engineering Northeastern UniversityShenyang110819China Foshan Graduate School of Innovation Northeastern UniversityFoshan528311China

In recent years,the large-scale grid connection of various distributed power sources has made the planning and operation of distribution grids increasingly ***,a large number of active distribution network reconfiguration techniques have emerged to reduce system losses,improve system safety,and enhance power quality via switching switches to change the system topology while ensuring the radial structure of the *** scholars have previously reviewed these methods,they all have obvious shortcomings,such as a lack of systematic integration of methods,vague classification,lack of constructive suggestions for future study,***,this paper attempts to provide a comprehensive and profound review of 52 methods and applications of active distribution network reconfiguration through systematic method classification and ***,these methods are classified into five categories,i.e.,traditional methods,mathematical methods,meta-heuristic algorithms,machine learning methods,and hybrid methods.A thorough comparison of the various methods is also scored in terms of their practicality,complexity,number of switching actions,performance improvement,advantages,and ***,four summaries and four future research prospects are *** summary,this paper aims to provide an up-to-date and well-rounded manual for subsequent researchers and scholars engaged in related fields.

关键词： Active distribution network reconfiguration meta-heuristic algorithm machine learning

来源：评论

学校读者我要写书评

暂无评论

Design of fixed time backstepping controller for ball and plate system 6

Design of fixed time backstepping controller for ball and pl...

引用

6th International Conference on Mechatronics and Intelligent Robotics, ICMIR 2022

作者： Xu, Peng Xiang, Fenghong Li, Jiangfeng Faculty of Information Engineering and Automation Kunming University of Science and Technology 727 Jingming South Road Kunming650504 China

ISBN: (纸本)9781510656635

Ball and plate system is a typical multiple-input and multiple-output system, which has the problems of slow response speed, large oscillation amplitude, long oscillation time and other problems of poor stability. In this paper, a fixed time backstepping controller is proposed to improve the existing problems. Firstly, the mathematical model of the ball and plate system is established under the condition of ignoring the interference, and a fixed time convergent backstepping controller is designed according to the mathematical model. Secondly, the backward step method is used to analyze the system, and the command filter is used to process the virtual control parameters for derivation. Then, Lyapunov theory proves the stability of the whole system, which indicates that the system converges in the fixed time. Finally, the simulation results show that the proposed controller not only improves the accuracy and stability of the trajectory tracking, but also ensures that the ball can track the desired trajectory in a fixed time. © 2022 SPIE.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

Research on elephant flow detection method based on information entropy and improved random forest

Research on elephant flow detection method based on informat...

引用

2022 International Conference on Algorithms, Microchips and Network Applications

作者： Hu, Xiaohong Miao, Xianghua Yuan, Meiyu Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Computer Technology Application Kunming University of Science and Technology Kunming650500 China

ISBN: (纸本)9781510653290

In the increasingly complex network environment, various attacks emerge one after another. Being able to accurately detect elephant flow and mouse flow plays an extremely important role in defending against large-scale network attacks. Aiming at some shortcomings of current methods for detecting elephant flow and mouse flow, this paper proposes a detection method based on information entropy and improved random forest. After preprocessing the data, first calculate the data feature score with information entropy, screen out the truly valuable features according to the score, then put them into the improved random forest classifier, and finally get the detection results. In this paper, the grid search algorithm is used to optimize the tree and depth of random forest tree, so that the detection results can be obtained quickly and accurately. Experiments show that due to the significant difference between the data characteristics of elephant flow and mouse flow, this method can effectively identify elephant flow and mouse flow. The accuracy rate is 97.93%, the precision rate is 99.99%, the recall rate is 97.91%, and the F1-score is 98.94%, which is improved compared with other algorithms. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Pseudo-label Estimation Based on EDA for Semi-supervised Soft Sensor Development 11

Pseudo-label Estimation Based on EDA for Semi-supervised Sof...

引用

11th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2022

作者： Rao, Feihong Jin, Huaiping Liu, Haipeng Yang, Biao Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Kunming650500 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

Data-driven soft sensor is widely used in the process industry to realize online prediction of difficult-to-measure variables. However, the lack of labeled data and the abundance of unlabeled data in the process industry restrict the development of semi-supervised soft sensor. Assigning high-quality pseudo-labels to expand labeled data is an effective method for improving the semi-supervised model. In this respect, this paper proposes a method based on the estimation of distribution algorithm (EDA), known as EDA-based pseudo label estimation (EDPLE), which combines traditional pseudo-label generation and confidence evaluation into an optimal estimation problem of label probability distribution. The error accumulation in traditional iterative learning is alleviated considerably via this method. In the EDPLE method, the optimization objective consists of prediction accuracy, prediction uncertainty and manifold learning, and a multivariable probability model is designed. Subsequently, the EDA is used to solve the optimization problem to obtain high-confidence pseudo-labels. Therefore, a semi-supervised soft-sensor model based on labeled and pseudo-labeled data is established in this study. In real-world industrial cases, the proposed method outperforms the existing pseudo-label-based semi-supervised soft-sensor method. © 2022 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Analysis of Influencing Factors of Middle School Students' Learning Based on C5.0 Decision Tree 4

Analysis of Influencing Factors of Middle School Students' L...

引用

4th International Conference on Computer science and Educational Informatization, CSEI 2022

作者： Kong, Chen Zhang, Xiaoli Li, Xia Wang, Mingdan Feng, Yong Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China First Primary School in Chenggong District Kunming China

ISBN: (数字)9781839537882

ISBN: (纸本)9781839537882

Middle school is a critical period for the entire training of students. How to help teachers and students accurately analyze the key factors that affect middle school performance and determine the dependence between these factors and performance has become a problem that urgently needs to be solved. Based on the simulated test scores of 6298 junior high school students in a certain urban area of kunming, this research designed a questionnaire on the "learning effects and development factors of middle school students" and conducted a statistical analysis of the students' scores and their responses to study the learning effects and development factors of middle school students' relevance. Based on the C5.0 decision tree algorithm, the information gain of each attribute is calculated, the decision tree is constructed, and the correlation between the learning effect of middle school students and development factors is found to optimize the training structure. The research results have clarified the factors that affect the teaching effect so that both teaching parties can benefit from them and jointly improve the teaching quality. © 2022 IET Conference Proceedings. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

The Impact of Domain Name Server(DNS)over Hypertext Transfer Protocol Secure(HTTPS)on Cyber Security:Limitations,Challenges,and Detection Techniques

引用

Computers, Materials & Continua 2024年第9期80卷 4513-4542页

作者： Muhammad Dawood Shanshan Tu Chuangbai Xiao Muhammad Haris Hisham Alasmary Muhammad Waqas Sadaqat Ur Rehman Faculty of Information Technology Beijing University of TechnologyBeijing100124China National Center of Robotics and Automation University of Engineering and TechnologyPeshawar25000Pakistan Department of Computer Science College of Computer ScienceKing Khalid UniversityAbha61421Saudi Arabia School of Computing and Engineering Sciences Faculty of Engineering and ScienceUniversity of GreenwichLondonSE109LSUnited Kingdom School of Engineering Edith Cowan UniversityPerthWA 6027Australia School of Computer Science and Engineering University of SalfordManchesterM54BRUnited Kingdom

The DNS over HTTPS(Hypertext Transfer Protocol Secure)(DoH)is a new technology that encrypts DNS traffic,enhancing the privacy and security of ***,the adoption of DoH is still facing several research challenges,such as ensuring security,compatibility,standardization,performance,privacy,and increasing user *** significantly impacts network security,including better end-user privacy and security,challenges for network security professionals,increasing usage of encrypted malware communication,and difficulty adapting DNS-based security ***,it is important to understand the impact of DoH on network security and develop newprivacy-preserving techniques to allowthe analysis of DoH traffic without compromising user *** paper provides an in-depth analysis of the effects of DoH on *** discuss various techniques for detecting DoH tunneling and identify essential research challenges that need to be addressed in future security ***,this paper highlights the need for continued research and development to ensure the effectiveness of DoH as a tool for improving privacy and security.

关键词： DNS DNS over HTTPS cybersecurity machine learning

来源：评论

学校读者我要写书评

暂无评论

Integral Terminal Sliding Mode Control for Quadrotor Based on a Novel Power Reaching Law 6th

Integral Terminal Sliding Mode Control for Quadrotor Based o...

引用

6th International Conference on Computing, Control, and Industrial engineering, CCIE 2021

作者： Yang, Shubo Mao, Jianlin Xu, Feng Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China School of Mechanical Engineering University of Science and Technology Beijing Beijing100083 China

ISBN: (纸本)9789811939266

In this article, addressing such problems as the chattering phenomenon and slow speed of keeping up with the predetermined trajectory in the application of sliding mode control to quadrotor, a rare nonlinear sliding mode control strategy is proposed. First, a new power reaching law is introduced, and the time to reach the desired trajectory and the error range when it is stable are analyzed and verified. Secondly, a nonlinear integral function is introduced into the terminal sliding mode surface so that it both reduces the steady-state error and avoids the singularity issue of sliding mode state. In the end, the nonlinear sliding mode controller is designed with quadrotor as the object. According to simulation results: with this controller, the quadrotor can quickly complete tracking;compared with the power improved reaching law and the existing sliding mode surface respectively, this controller suppresses chattering to a certain extent, and the time for the system to converge to stability was accelerated by 14.29%. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Noise-robust Cross-modal Interactive Learning with Text2image Mask for Multi-modal Neural Machine Translation 29

Noise-robust Cross-modal Interactive Learning with Text2imag...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Ye, Junjie Guo, Junjun Xiang, Yan Tan, Kaiwen Yu, Zhengtao Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Artificial Intelligence Kunming China

Multi-modal neural machine translation (MNMT) aims to improve textual level machine translation performance in the presence of text-related images. Most of the previous works on MNMT focus on multi-modal fusion methods with full visual features. However, text and its corresponding image may not match exactly, visual noise is generally inevitable. The irrelevant image regions may mislead or distract the textual attention and cause model performance degradation. This paper proposes a noise-robust multi-modal interactive fusion approach with cross-modal relation-aware mask mechanism for MNMT. A text-image relation-aware attention module is constructed through the cross-modal interaction mask mechanism, and visual features are extracted based on the text-image interaction mask knowledge. Then a noise-robust multi-modal adaptive fusion approach is presented by fusion the relevant visual and textual features for machine translation. We validate our method on the Multi30K dataset. The experimental results show the superiority of our proposed model, and achieve the state-of-the-art scores in all En-De, En-Fr and En-Cs translation tasks © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Research on Predictive Analysis of Public Courses and Graduation Grades in Universities Based on GA-BP Neural Network 5th

Research on Predictive Analysis of Public Courses and Gradua...

引用

5th International Conference on Computer science and Educational Informatization, CSEI 2023

作者： Wen, Jun Zhang, Xiaoli Zhu, Guifu Xu, Nuo Yang, Can Nie, Jialei Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650000 China Information Technology Center Kunming University of Science and Technology Kunming650000 China

ISBN: (纸本)9789819994915

Learning public courses in universities has a significant influence on the learning of professional courses, average graduation credit scores, further education, and going abroad in the later stages of university. It is important to analyse the learning situation of students in public courses and predict their future learning based on these learning data. This article takes the performance data of 12 public courses of all undergraduate students from a university of science and technology from 2010 to 2015 as the research object. Through data processing and establishing a GA-BP neural network model, the average graduation credit score of students is predicted. The results indicate that the overall error between the predicted value and the true value is relatively small, and the prediction is more accurate, proving the importance of university public courses and the feasibility of the GA-BP neural network algorithm. Finally, the article compares this algorithm with multiple linear regression and a BP neural network using two evaluation indicators, RMSE and R Squared, and the results show that this algorithm has the highest accuracy. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Students

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：