检索结果-内蒙古大学图书馆

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Shuang Li Ke Li Wei Li Control and Simulation Center Harbin Institute of Technology China and National Key Laboratory of Modeling and Simulation for Complex Systems China Department of Computer Science University of Exeter Exeter UK

Bayesian Optimization (BO) is a powerful method for tackling expensive blackbox optimization problems. As a sequential model-based optimization strategy, BO iteratively explores promising solutions until a predetermined budget, either iterations or time, is exhausted. The decision on when to terminate BO significantly influences both the quality of solutions and its computational efficiency. In this paper, we propose a simple, yet theoretically grounded, two-step method for automatically terminating BO. Our core concept is to proactively identify if the search is within a convex region by examining previously observed samples. BO is halted once the local regret within this convex region falls below a predetermined threshold. To enhance numerical stability, we propose an approximation method for calculating the termination indicator by solving a bilevel optimization problem. We conduct extensive empirical studies on diverse benchmark problems, including synthetic functions, reinforcement learning, and hyperparameter optimization. Experimental results demonstrate that our proposed method saves up to ≈ 80% computational budget yet is with an order of magnitude smaller performance degradation, comparing against the other peer methods. In addition, our proposed termination method is robust in terms of the setting of its termination criterion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

General theory for designing phonon transport in alloyed/doped materials

引用

science China(Physics,Mechanics & Astronomy) 2024年第12期67卷 133-140页

作者： Chenhan Liu Chao Wu Wei Liu Yunshan Zhao Gang Zhang Hongmin Yang Yunfei Chen Micro-and Nano-scale Thermal Measurement and Thermal Management Laboratory Key Laboratory of Numerical Simulation for Large Complex SystemsMinistry of EducationSchool of Energy and Mechanical EngineeringNanjing Normal UniversityNanjing210023China School of Electrical and Automation Engineering Nanjing Normal UniversityNanjing210023China Phonon Engineering Research Center of Jiangsu Province Center for Quantum Transport and Thermal Energy ScienceInstitute of Physics Frontiers and Interdisciplinary SciencesSchool of Physics and TechnologyNanjing Normal UniversityNanjing210023China Agency for Science Technology and ResearchInstitute of High-Performance ComputingSingapore138632Singapore Jiangsu Key Laboratory for Design and Manufacture of Micro-Nano Biomedical Instruments School of Mechanical EngineeringSoutheast UniversityNanjing211100China

Alloying/doping is a widely used technique for improving the electrical,mechanical,and optical properties of ***,this technology induces significant distortions in the lattice structure,mass distribution,and potential field,greatly enhancing phonon ***,we introduce the concept of alloying/doping path and employ crystal symmetry,lattice deformation,and electron distribution to characterize *** on this new concept,the phonon thermal transport behavior in alloyed/doped materials can be well designed,and along different alloying/doping paths,the difference in thermal conductivity can be up to 45 *** one hand,strategic alloying/doping that combines high crystal symmetry,large lattice contraction,and the same electron distribution suppresses phonon-phonon scattering phase space,induces phonon stiffening,and bolsters electronic structure symmetry,*** synergistic effects significantly improve thermal *** the other hand,random alloying/doping has a low symmetry,leading to the typical“U”shape of alloying/doping level-dependent thermal *** theory is corroborated in three-dimensional(3D)Si,2D MoS_(2),and quasi-1D TiS_(3),affirming its efficacy and broad applicability in controlling phonon transport.

关键词： phonon transport alloyed/doped materials crystal symmetry lattice contraction electronic structure

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

Short-Term Traffic Flow Prediction Method Based on Spatio-Temporal Characteristics of complex Road Network

Short-Term Traffic Flow Prediction Method Based on Spatio-Te...

引用

2021 International Conference on Applied Mathematics, Modeling and Computer simulation, AMMCS 2021

作者： Zhu, Huawei Mao, Yihao Zhao, Yiming Shi, Liyuan Shao, Yanli School of Information and Electrical Engineering Zhejiang University City College Hangzhou310015 China Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China

ISBN: (纸本)9781643682549

With the development of urbanization, the number of residents' motor vehicles has increased sharply, and traffic congestion problem has become increasingly serious. The construction of Intelligent Traffic System (ITS) has become the main means to alleviate traffic congestion. Short-term traffic flow prediction has guiding significance for residents' travel planning and intelligent management of transportation, and has become one of the research hotspots in intelligent transportation ***, A short-term traffic flow prediction method based on the spatio-temporal characteristics of complex road networks is proposed to further improve the prediction accuracy and reduce the prediction cost. Firstly, a graph convolutional network (GCN) capable of processing non-Euclidean data structures is used to extract the spatial characteristics of traffic flow data. Then, the long and short-term memory (LSTM) neural network is used to process the time characteristics. Finally, the two are combined to realize the effective processing of the spatio-temporal characteristics of traffic flow data. Experimental results on the real traffic flow dataset prove the feasibility and effectiveness of the proposed method, and can provide a basis for intelligent traffic control and smart city construction. © 2022 The authors and IOS Press.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Design of large ring-column antenna satellite attitude-orbit integrated füll propulsion system

引用

Zhendong yu Chongji/Journal of Vibration and Shock 2025年第11期44卷 1-11页

作者： Wang, Shijie Sun, Minzhe Gao, Feng Ji, Yi Sun, Guanghui Dong, Fuxiang School of Astronautics Harbin Institute of Technology Harbin150001 China Frontier Science Center of Space Environment and Interaction of Matters Harbin150001 China State Key Lab for Modeling and Simulation of Complex Systems Harbin150001 China General Department of Communication and Navigation Satellite China Academy of Space Technology Beijing100094 China

As a key space structure in geostationary orbit, 100-meter level large ring-column antenna satellite is tasked with providing high-speed information transmission and stable communication Service in this orbit. This requires satellites having precise orbit maintenance and attitude control capabilities. Due to such satellites typically having larger masses and special structural designs, here, the high-precision orbit prediction algorithm was used to finely model and analyze effects of key space environmental factors of solar pressure, non-spherical perturbations and 3-body gravity on space Operation of such spacecrafts. Furthermore, referring to the design concept of formation-flying gravity field measurement satellites, a distributed füll thrust control strategy based on thruster layout optimization for such spacecrafts was proposed. Then, an improved explicit model predictive control algorithm was proposed based on Laguerre function to convert device capability limitations and Performance requirements into input-output constraints, combine multi-parameter programming, and realize attitude-orbit integrated control of such satellites. The simulation results showed that during stable Operation, position maintenance errors of such satellites can be controlled within a meter-level ränge, and attitude angle errors are better than 0. 03°;the computational efficiency of the proposed control algorithm is significantly higher than that of the Standard model predictive control algorithm and Laguerre function-based model predictive control algorithm;the hardware memory occupied is much lower than that of the explicit model predictive control *** theoretical analysis and numerical verification, it was shown that this study can provide an effective solving scheme for füll thruster integrated control of large ring-column antenna satellites in oomplex space environment using onboard Computers with limited Computing power. © 2025 Chinese Vibration Engineering Society.

关键词： Geostationary satellites

来源：评论

学校读者我要写书评

暂无评论

Prompting Large Language Models with Answer Heuristics for Knowledge-Based Visual Question Answering

Prompting Large Language Models with Answer Heuristics for K...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhenwei Shao Zhou Yu Meng Wang Jun Yu Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University China School of Computer Science and Information Engineering Hefei University of Technology China

Knowledge-based visual question answering (VQA) requires external knowledge beyond the image to answer the question. Early studies retrieve required knowledge from explicit knowledge bases (KBs), which often introduces irrelevant information to the question, hence restricting the performance of their models. Recent works have sought to use a large language model (i.e., GPT-3 [3]) as an implicit knowledge engine to acquire the necessary knowledge for answering. Despite the encouraging results achieved by these methods, we argue that they have not fully activated the capacity of GPT-3 as the provided input information is insufficient. In this paper, we present Prophet-a conceptually simple framework designed to $prompt$ GPT-3 with answer heuristics for knowledge-based VQA. Specifically, we first train a vanilla VQA model on a specific knowledge-based VQA dataset without external knowledge. After that, we extract two types of complementary answer heuristics from the model: answer candidates and answer-aware examples. Finally, the two types of answer heuristics are encoded into the prompts to enable GPT-3 to better comprehend the task thus enhancing its capacity. Prophet significantly outperforms all existing state-of-the-art methods on two challenging knowledge-based VQA datasets, OK-VQA and A-OKVQA, delivering 61.1% and 55.7% accuracies on their testing sets, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FedAG:A Federated Learning Method Based on Data Importance Weighted Aggregation

FedAG:A Federated Learning Method Based on Data Importance W...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Xu, Mengchu Zeng, Yan Xue, Meiting Zhang, Ji-Lin Wan, Jian Zhou, Mingyao Wen, Yilin Shi, Yukun Hangzhou Dianzi University School of Computer Science and Technology Hangzhou China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education Hangzhou China Zhejiang Engineering Research Center of Data Security Governance Hangzhou China Hangzhou Dianzi University School of Cyberspace Hangzhou China Huawei Enterprise Communication Technology Co Hangzhou China

ISBN: (纸本)9798350345384

Federated learning is a distributed machine learning approach that trains models with multiple clients and data locally. However, the existing methods ignore the differences between local models caused by the data heterogeneity, and give a high aggregation weight for the low-quality local model, which leads to low accuracy of the global model. For this problem, we propose a federated learning method based on data importance weighted aggregation, FedAG. It constructs an evaluation model of data importance based on the data distribution skewness, data volume, and data quality of clients, and aggregates local models with different weights computed by the evaluation model of data importance into a global model. We make experiments on five datasets including EMNIST, MNIST, and CIFAR-10. The results show that the accuracy of FedAG is respectively improved by 6.5%, 1.8%, 1.3% and 2.1%, compared with FedAvg, FedProx, FedVar, and Scaffold algorithms. © 2023 IEEE.

关键词： Scaffolds

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

An Anomaly Detection Method Based on Adaptive Log and Dual Feature Fusion Analysis for Distributed systems

An Anomaly Detection Method Based on Adaptive Log and Dual F...

引用

Information systems and Computing technology (ISCTech), International Conference on

作者： Yijiang Jia Kefei Li Ping Lu Baodi Xie Huayang Wang Jincai Chen School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Wuhan China National Key Laboratory of Modeling and Simulation for Complex Systems Beijing China

In this study, we present a middleware-based approach for detecting anomalies in distributed systems. Our method facilitates the dynamic collection of logs at various levels of detail and incorporates an a priori dictionary-based compression strategy to process and transmit logs, minimizing the performance impact on distributed systems. Additionally, we utilize a dual feature fusion technique to analyze the logs. We evaluate the effectiveness of our approach by performing anomaly detection in a publish/subscribe distributed system and comparing it with existing methods. The results illustrate that our method outperforms other approaches, demonstrating superior performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Radar Active Deception Jamming Identification Method Based on RESNET and Bispectrum Features 2

Research on Radar Active Deception Jamming Identification Me...

引用

2nd International Conference on Computer Engineering and Application, ICCEA 2021

作者： Wang, Kunteng Dong, Zeyu Wan, Tao Jiang, Kaili Xiong, Wanan Fang, Xueli University of Electronic Science Technology of China School of Electronic Science and Engineering Chengdu China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu China Key Laboratory of Complex Aviation Simulation System Beijing China

ISBN: (纸本)9781665426169

In the complex electromagnetic environment of modern electronic warfare, active deception jamming poses a serious threat to radar. This paper proposes the identification of active deception jamming based on residual neural network (RESNET), and studies the bispectral characteristics of the signal and the method of identifying the active deception jamming of RESNET. This algorithm firstly extracts the bispectral features of the jamming signal, and uses the bispectral diagonal slice as the input of RSNET to realize the recognition of active deception jamming. simulation results show that the algorithm has high recognition accuracy, not only has good anti-noise performance, but also has excellent robustness under low JSR. © 2021 IEEE.

关键词： Radar

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：