检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Information technology, Big Data and Artificial Intelligence, ICIBA 2021

作者： Lin, Wenxiang Liu, Desheng Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing China

ISBN: (纸本)9781665428767

With the improvement of computer computing power, the shortcomings of the computational inefficiency of the genetic mining algorithm are compensated, and the genetic mining become a research hotspot. In this paper, for the Evolutionary Tree Miner (ETM) algorithm in noise processing can not find the low-frequency effective path and remove the shortage of noise, an ETM fusion algorithm based on log classification is proposed. The algorithm performs process model mining for high-frequency and low-frequency logs separately, and get model fusion based on alignment ideas, Eventually mining the complete process model. Through the simulation of event log data verification, the improved algorithm achieves more complete process model mining than the original ETM algorithm. © 2021 IEEE.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

A DQN-based hyperheuristic algorithm for emergency scheduling of Earth observation satellites 2

A DQN-based hyperheuristic algorithm for emergency schedulin...

引用

2nd International Conference on Electronics, Communications and Information technology, CECIT 2021

作者： Liu, Zheng Xiong, Wei Space Engineering University Science and Technology on Complex Electronic System Simulation Laboratory Beijing China

ISBN: (纸本)9781665437578

With the surge of emergency task demand, large-scale Earth observation satellite emergency scheduling has become a practical problem which is urgent to be solved. In view of this situation, this paper analyzes the constrains and conflict relationship in this problem, and proposes a DQN-based hyperheuristic algorithm. The algorithm includes encoding and decoding, deep Q-network and several low-level heuristic operators. A Markov decision model of this problem is established and 7 low-level heuristic operators are designed according the feature of this problem. After training, DQN behaves well when selecting operators for the scheduling scheme. Finally, several groups of comparative experiments verify the algorithm's ability in solving large-scale satellite emergency scheduling problems. © 2021 IEEE.

关键词： Personnel training

来源：评论

学校读者我要写书评

暂无评论

Architecture transformation research on joint border defense systems-of-systems 2021

Architecture transformation research on joint border defense...

引用

2021 5th International Conference on Management Engineering, Software Engineering and Service sciences, ICMSS 2021

作者： Zhang, Mengmeng Yi, Shuanghui Lin, Menglong Chen, Honghui Science and Technology on Information Systems Engineering Laboratory China National Key Laboratory for Complex System Simulation China

ISBN: (纸本)9781450389709

Currently, with the deepening of development and open of China's border, issues of border joint defense become increasingly arduous. Traditional means of cooperation and coordination are far from being able to align requirements;information systems of different joint defense units are difficult to interconnect and interoperate;the previous results of joint defense informatization are difficult to inherit. The main reason is the lack of border joint defense information construction with a top-level design approach. Via the lens of top-level design, this paper establishes a multi-viewpoint architecture framework and transformation process, develops the as-is and to-be joint defense architecture, and finally analyzes transformation principles from the as-is architecture to to-be architecture. This paper mainly explores the architecture transformation mechanisms under the border joint defense scenario. © 2021 ACM.

关键词： Architecture

来源：评论

学校读者我要写书评

暂无评论

A dynamic planning method for satellite imaging mission based on improved genetic algorithm

引用

Applied Mathematics and Nonlinear sciences 2024年第1期9卷

作者： Zhao, Demin Xiong, Wei Wang, Yiran Science and Technology on Complex Electronic System Simulation Laboratory University of Aerospace Engineering Beijing100000 China DFH Satellite CO. Ltd. Beijing100080 China

The ongoing enhancement of imaging satellite platforms in terms of payload capacity, coupled with the proliferation of imaging satellites, introduces new complexities to the mission planning processes. These enhancements enable broader applications and significantly increase the societal benefits derived from imaging satellites. To address these challenges, a specific kinematic model for dynamic imaging attitudes is constructed, taking into account the dynamics of satellite imaging missions. This model uses information from satellite imaging observation tasks to design constraints that govern the planning of imaging tasks. Additionally, an optimization objective function is established to ensure compliance with these planning constraints. Building on the encoding method for relative imaging moments, an adaptive genetic algorithm tailored for satellite imaging task planning is introduced. This algorithm enhances the iterative efficiency of decision variables involved in satellite imaging tasks. Empirical validation through comparative simulation experiments, using a typical satellite imaging mission as a case study, demonstrates the effectiveness of the adaptive genetic algorithm. In various phases of imaging mission planning, the algorithm achieved a 100% task completion rate. The index function gain was enhanced by 21.47%, and the maximum synthetic angular velocity of attitude maneuvers between different targets peaked at the satellite's maneuvering threshold of 7 degrees per second. By leveraging adaptive genetic algorithms, satellite imaging mission planning can optimize mission completion rates and effectively utilize the satellite's maximum attitude maneuver capabilities. © 2024 Demin Zhao et al., published by Sciendo.

关键词： Satellites

来源：评论

学校读者我要写书评

暂无评论

Satellite Interference Signal Classification Using Improved MLP Model

Satellite Interference Signal Classification Using Improved ...

引用

2022 IEEE International Conference on Unmanned systems, ICUS 2022

作者： Xie, Liwei Zhuang, Yaqiang Zhuang, Xuebin Zeng, Xiaohui School of Systems Science and Engineering Sun Yat-Sen University Guangzhou China School of Integrated Circuits and Electronics Beijing Institute of Technology Beijing Key Laboratory of Millimeter Wave and Terahertz Technology Beijing China Science and Technology On Complex Aviation Systems Simulation Laboratory Beijing China

ISBN: (数字)9781665484565

ISBN: (纸本)9781665484565

In response to the existing style of deceptive jamming of Global Position system (GPS) receivers by aerial jammer carriers, a method using improved multi-layer perceptron (MLP) model is proposed to identify and classify interference sources based on the rate of change of satellite incoming angle. The work firstly constructs an airborne GPS interference source localization deployment model, then analyzes and verifies the rationality of this simulation data model, and finally emphasizes the superiority of the proposed method using the classical classification algorithm as a comparison method. The simulation results indicated that the proposed method is capable to identify the corresponding interferers with a greater rate of recognition compared with other method in the built multi-interference source environment, which provides a reference for dealing with the interference identification and classification in the networked GPS interference source deployment environment. © 2022 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

A Client Selection Method Based on Loss Function Optimization for Federated Learning

引用

Computer Modeling in Engineering & sciences 2023年第10期137卷 1047-1064页

作者： Yan Zeng Siyuan Teng Tian Xiang Jilin Zhang Yuankai Mu Yongjian Ren Jian Wan School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou310018China Key Laboratory of Complex System Modeling and Simulation Ministry of EducationHangzhou310018China Zhejiang Engineering Research Center of Data Security Governance Hangzhou310018China Intelligent Robotics Research Center Zhejiang LabHangzhou311100China HDU-ITMO Joint Institute Hangzhou Dianzi UniversityHangzhou310018China

Federated learning is a distributedmachine learningmethod that can solve the increasingly serious problemof data islands and user data privacy,as it allows training data to be kept locally and not shared with other *** trains a globalmodel by aggregating locally-computedmodels of clients rather than their ***,the divergence of local models caused by data heterogeneity of different clients may lead to slow convergence of the global *** this problem,we focus on the client selection with federated learning,which can affect the convergence performance of the global model with the selected local *** propose FedChoice,a client selection method based on loss function optimization,to select appropriate local models to improve the convergence of the global *** firstly sets selected probability for clients with the value of loss function,and the client with high loss will be set higher selected probability,which can make them more likely to participate in ***,it introduces a local control vector and a global control vector to predict the local gradient direction and global gradient direction,respectively,and calculates the gradient correction vector to correct the gradient direction to reduce the cumulative deviationof the local gradient causedby *** experiments to verify the validity of FedChoice on CIFAR-10,CINIC-10,MNIST,EMNITS,and FEMNIST datasets,and the results show that the convergence of FedChoice is significantly improved,compared with FedAvg,FedProx,and FedNova.

关键词： Federated learning model aggregation Non-IID

来源：评论

学校读者我要写书评

暂无评论

Analysis of node importance of satellite network based on triangular motif 23

Analysis of node importance of satellite network based on tr...

引用

Proceedings of the 2023 International Conference on Communication Network and Machine Learning

作者： Zhongmin Pei Boren Hu Zhangkai Luo Jie Ding Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University China Department of Electronics and Optical Engineering Space Engineering University China

ISBN: (纸本)9798400716683

Motif provides a local high-order substructure angle for the analysis of network structure evolution, which is of great significance for the study of the interaction between satellite network structure and function. Taking the time scrambling null motif in steady state as a reference, the stability analysis of satellite network structure is carried out from the perspective of the local structure of the motif characteristics; define the temporal degree of satellite network, and propose a satellite network node importance analysis method based on the number of node-constructed triangle motifs, and compare the changes of motifs characteristics under the deliberate attack of temporal degree and based on triangle motifs. simulation experiments are conducted on 46-node GPS constellations containing satellites and ground stations, and it is found that the network with higher initial triangle concentration showed higher stability. In GPS satellite network where the number of node triangle motif is positively correlated with their temporal degree, the attack strategy based on the triangle motif accelerates the attenuation of the triangle subgraph, and the node importance analysis method of the satellite network has higher accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Knowledge-driven material design platform based on the whole-process simulation and modeling

引用

International Journal of Modeling, simulation, and Scientific Computing 2022年第2期13卷 1-15页

作者： Gongzhuang Peng Tie Li Xiang Zhai Wenzheng Liu Heming Zhang National Engineering Research Center for Advanced Rolling Technology University of Science and Technology Beijing Beijing 100083 P.R.China Shanghai Electro-Mechanical Engineering Institute Shanghai 201109 P.R.China State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System Engineering Beijing 100854 P.R.China Beijing Complex Product Advanced Manufacturing Engineering Research Center Beijing Simulation Center Beijing 100854P.R.China Science and Technology on Space System Simulation Laboratory Beijing Simulation Center Beijing 100854P.R.China National CIMS Engineering Research Center Tsinghua University Beijing 100084P.R.China

In order to realize the agility,collaboration and visualization of alloy material devel-opment process,a product development platform based on simulation and modeling technologies is established in this *** this platform,the whole-process simulation module builds multi-level simulation models based on metallurgical mechanisms from the production line level,the thermo-mechanical coupling field level and the microstructure evolution *** design knowledge management module represents the multi-source heterogeneous material design knowledge through ontology model,including customers’requirement knowledge,material component knowledge,process design knowledge and quality inspection knowledge,and utilizes the case-based reasoning approach to reuse the *** data-driven modeling module applies machine learning algorithms to mine the relationships between product mechanical properties,material components,and process parameters from historical samples,and utilizes multi-objective optimiza-tion algorithms to find the optimal combination of process *** of the developed platform in actual steel mills shows that the proposed method helps to improve the efficiency of product design process.

关键词： Product development knowledge-based engineering multi-scale simulation performance prediction model

来源：评论

学校读者我要写书评

暂无评论

Large Eddy simulation of Flow and Heat Transfer Performance in Periodically Inward Corrugated Tubes

SSRN

引用

SSRN 2023年

作者： Zhong, Yuzhou Song, Yueheng Zhao, Lei Mi, Fei Zhao, Jingquan Zhu, Xiaowei School of Aeronautic Science and Engineering Beihang University Beijing100191 China Science & Technology on Complex Aviation System Simulation Laboratory Beijing100070 China Co. Ltd. Henan453049 China

Corrugated tubes are extensively unitized in enhancing heat transfer within tubular heat exchange devices. The efficiency of these corrugated tubes is closely linked to the geometric characteristics of the surface corrugations. In this study, we conducted an extensive series of Large Eddy simulations on a representative type of enhanced tube featuring periodic inward corrugations (PIC). Our goal was to compile a comprehensive and precise dataset of the thermal and hydraulic properties specific to this design. The key design parameters that define the corrugated patterns are corrugation height, corrugation width, and the length of the straight section. We systematically explored these parameters to understand their impact on heat transfer and fluid dynamics. Among these parameters, corrugation height has been identified as the most influential factor affecting flow and heat transfer properties. As the corrugation height varies from 1/8D to 3/8D, we observed a substantial increase in the friction factor and Nusselt number by a factor of 209 and 5, respectively, at Re = 1000;while the critical Reynolds number decreased roughly from 800 to 100. These findings underscore the significant role of corrugation height in shaping the flow and heat transfer performance of PIC tubes. The other two parameters, corrugation width and straight section length, were also found to be crucial in determining the overall heat transfer coefficient and pressure drop. The results of our study suggest that when utilizing this type of corrugated tubes, careful consideration is required to strike an optimal balance between heat transfer efficiency and pressure loss. The large-sets LES results presented in this paper can serve as valuable inputs for optimizing the design of PIC tubes. © 2023, The Authors. All rights reserved.

关键词： Large eddy simulation

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Security Analysis Framework Based on Threat Matrix

Machine Learning Security Analysis Framework Based on Threat...

引用

IEEE International Conference on Data science in Cyberspace (DSC)

作者： Hu Li Qiongmin Ma Ming Zhang Xiaohui Kuang National Key Laboratory of Science and Technology on Information System Security Beijing China National Key Laboratory for Complex Systems Simulation Beijing China

Machine Learning and Artificial Intelligence technology accelerates technological progress and promotes social development, but also brings many security problems. Machine learning models may be affected, deceived, controlled or destroyed at different stages, e.g. training and inference, which may lead to serious consequences. In view of the main stages of the life cycle of machine learning, we summarizes the related attack and defense technologies based on threat matrix, makes a comprehensive and systematic analysis on the security issues of machine learning, and puts forward several security protection suggestions for intelligent information systems.

关键词：

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：