检索结果-内蒙古大学图书馆

8th Symposium on Novel Photoelectronic Detection technology and Applications

作者： Guo, Xiaoyun Wu, Chengfeng Fang, Xueli Xu, Cheng Li, Hui Beijing Institute of Mechanical and Electrical Engineering Beijing China Beijing Institute of Mechanical and Electrical Engineering Science and Technology on Complex System Control and Intelligent Agent Cooperative Laboratory Beijing China Beijing Institute of Mechanical and Electrical Engineering Key Laboratory of Complex Aviation Simulation System Beijing China

ISBN: (数字)9781510653122

ISBN: (纸本)9781510653115

Cross-domain synergy and intelligence will become important features of future warfare. Cross-domain guidance is one of the typical forms of cross-domain synergy. It can significantly improve the ability to respond quickly to random targets and time-sensitive targets and enhance the anti-jamming ability in the case of confrontation. This article introduces the concept and winning mechanism of cross-domain guidance, analyzes the research progress of cross-domain guidance at home and abroad, combs the key technologies of cross-domain guidance, summarizes the current challenges and problems in cross-domain guidance research, and proposes development suggestions. © 2022 SPIE

关键词： Optical engineering

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Interest Representation Network for Click-Through Rate Prediction

Evolutionary Interest Representation Network for Click-Throu...

引用

2023 IEEE International Conference on Web Services, ICWS 2023

作者： Zhou, Renjie Jin, Zhenming Wan, Jian Zhang, Jilin Guo, Xingyu Liu, Qiang Hangzhou Dianzi University Key Laboratory of Complex Systems Modeling and Simulation of the Ministry of Education School of Computer Science and Technology Hangzhou China Hangzhou Dianzi University Key Laboratory of Complex Systems Modeling and Simulation of the Ministry of Education Itmo Joint Institute Hangzhou China Zhejiang University of Science and Technology School of Information and Electronic Engineering Hangzhou China Zhejiang Police College Dept. of Computer and Information Technology Hangzhou China

ISBN: (纸本)9798350304855

The rapid development of the Internet has revo-lutionized our lives, providing us with an array of convenient services. However, this revolution has also led to the problem of data overload. Personalized recommendation services have been widely recognized as an effective solution to this problem by both the industrial and academic communities. Accurate prediction of click-through rate (CTR) is a critical task in personalized recommendation systems since it can improve the user's shopping experience, ultimately increasing revenue for the platform. To achieve accurate CTR prediction, it is crucial to capture user interests. While several methods for interest modeling exist, challenges related to user interest evolution and user behavior noise need further attention. This paper proposes a novel CTR prediction model named the Evolutionary Interest Representation Network (EIRN), which learns the evolving interest representation of users from their behaviors, profiles, and environmental attributes. In the model, we introduce an advertisement correlation graph decomposition layer and a noise filter layer to enhance and purify the user behavior representation. An interest extraction layer is designed to capture sequential correlations and common characteristics between user behaviors, representing their interests. Additionally, as user interests evolve over time and their importance changes, an attention-based interest evolution layer is designed to track the evolution of user interests. Our proposed method is validated using four public datasets and an industrial dataset, showing its superiority over existing CTR prediction methods. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Multi-View Subspace Clustering Via Simultaneously Cycle Projection and Similarity Learning

Multi-View Subspace Clustering Via Simultaneously Cycle Proj...

引用

International Conference on Wavelet Active Media technology and Information Processing (ICWAMTIP)

作者： Xiang Tao Liu Jie Qiao Wenshen Xiao Siying Ye Mao National Key Laboratory of Complex Aviation System Simulation Southwest China Institute of Electronic Technology Chengdu China University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798331519254

ISBN: (纸本)9798331519261

At present, most of the existing methods combine the data from different views mechanically to obtain the latent subspace with complementary information, which not only fails to make full use of the data information from specific perspectives but also brings redundancy. Therefore, we propose a novel multi-view subspace clustering method. It utilizes cycle projection to obtain a subspace construction model. At the same time, by learning the global structure and local manifold structure of this subspace while assigning learnable weights to different views, the consensus information among views and specific information from different views are captured according to the importance of different views. In this way, our method effectively reduces the original noise and redundancy, and further carries out the improvement of complementarity and consistency among views. The proposed method is optimized by using the Augmented Lagrangian Multiplier with Alternating Direction Minimization (ALM- ADM) algorithm. Experiment results on benchmark datasets confirm the effectiveness of our method.

关键词： Manifolds Technological innovation Clustering methods Redundancy Noise Clustering algorithms Information processing Media Minimization Similarity learning

来源：评论

学校读者我要写书评

暂无评论

Brain-inspired Intelligent Robotics:Theoretical Analysis and systematic Application

引用

Machine Intelligence Research 2023年第1期20卷 1-18页

作者： Hong Qiao Ya-Xiong Wu Shan-Lin Zhong Pei-Jie Yin Jia-Hao Chen The State Key Laboratory of Management and Control for Complex System Institute of AutomationChineseAcademyof SciencesBeijing100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Chinese Academy of Science Center for Excellence in Brain Science and Intelligence Technology Shanghai 200031China School of Mechanical Engineering University of Science and Technology BeijingBeijing 100083China

Traditional joint-link robots have been widely used in production lines because of their high precision for single *** the development of the manufacturing and service industries,the requirement for the comprehensive performance of robotics is *** types of bio-inspired robotics have been investigated to realize human-like motion control and manipulation.A study route from inner mechanisms to external structures is proposed to imitate humans and animals *** this idea,a brain-inspired intelligent robotic system is constructed that contains visual cognition,decision-making,motion control,and musculoskeletal *** paper reviews cutting-edge research in brain-inspired visual cognition,decision-making,motion control,and musculoskeletal *** software systems and a corresponding hardware system are established,aiming at the verification and applications of next-generationbrain-inspired musculoskeletal robots.

关键词： Brain-inspired intelligent robot software and hardware decision making muscle control cognitive intelligence.

来源：评论

学校读者我要写书评

暂无评论

Analysis of the SEIR mean-field model in dynamic networks under intervention

引用

Infectious Disease Modelling 2025年第3期10卷 850-874页

作者： Li, Jiangmin Jin, Zhen Tang, Ming Complex System Research Center Shanxi University Shanxi Taiyuan 030006 China Key Laboratory of Complex Systems and Data Science of Ministry of Education Shanxi University Shanxi Taiyuan 030006 China Shanxi Key Laboratory for Mathematical Technology in Complex Systems Shanxi University Shanxi Taiyuan 030006 China School of Physics and Electronic Science East China Normal University Shanghai 200241 China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai 200241 China

For emerging respiratory infectious diseases like COVID-19, non-pharmaceutical interventions such as isolation are crucial for controlling the spread. From the perspective of network transmission, non-pharmaceutical interventions like isolation alter the degree distribution and other topological structures of the network, thereby controlling the spread of the infectious disease. In this paper, we establish a SEIR mean-field propagation dynamics model for the synchronous evolution of dynamic networks caused by propagation and tracing isolation. We employ the reducing-dimension method to convert the mean-field model in networks into an equivalent and simpler low-dimension model, and then calculate the exact expression of the final size. In addition, we get the differential equations of the degree distribution over time in dynamic networks under tracing isolation and the relationships between the first and second moment of the dynamic network. While the degree of a node remains constant regardless of its state in many previous studies, this paper takes into account that the degree of each node changes over time whatever its state under the disease spread and intervention measures. © 2025 The Authors

关键词： Degree distribution Dynamic network The final size Tracing isolation

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

Research on Active Vibration Control of the Plate Based on Modal Space Control 2nd

Research on Active Vibration Control of the Plate Based on M...

引用

2nd International Conference of Mechanical system Dynamics, ICMSD 2023

作者： Lu, Hanjing Ma, Ziyao College of Engineering Peking University Beijing China Institute of Launch Dynamics Nanjing University of Science and Technology Nanjing China National Key Laboratory of Complex Multibody System Dynamics Nanjing China

ISBN: (纸本)9789819980475

In this study, we have devised an innovative strategy for active vibration control in plates by harnessing modal space control techniques. Our methodology encompasses the creation of a dynamic model to capture the plate's vibrational dynamics and subsequent simulation of its behavior. Building upon this, we have established a streamlined state-space representation, thereby simplifying the integration of control methodologies. To further optimize the control system's performance, we have meticulously optimized the placement of actuators and sensors. The culmination of our efforts is reflected in compelling numerical findings, underscoring the efficacy of our proposed active vibration control system. Notably, our system exhibits a remarkable ability to effectively curtail vibration displacement in the plate, reinforcing its potential impact in practical applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Vibration control

来源：评论

学校读者我要写书评

暂无评论

Analysis and Optimization of Medium Frequency Noise in Vehicle Cabin Based on FE-SEA Hybrid Method 2nd

Analysis and Optimization of Medium Frequency Noise in Vehic...

引用

2nd International Conference of Mechanical system Dynamics, ICMSD 2023

作者： Zhang, Dongye Gu, Junjie Zhang, Yanni Institute of Launch Dynamics Nanjing University of Science and Technology Jiangsu Province Nanjing210094 China National Key Laboratory of Complex Multibody System Dynamics Jiangsu Province Nanjing210094 China

ISBN: (纸本)9789819980475

This paper demonstrates the coupling relationship between Finite Element (FE) models and Statistical Energy Analysis (SEA) models based on wave theory and modal theory. A vehicle hybrid FE-SEA model is established by considering points, lines, surfaces, and loads. The VA One software is utilized to construct material and acoustic packages for the mixed model materials and acoustic media, and to perform vehicle cabin noise simulation analysis. This study investigates the effects of acoustic materials and damping materials on vehicle cabin noise under different working conditions, obtaining sound pressure level curves at the driver’s head under various conditions. By adding different structures of sound-absorbing materials to the model, the vibration and sound radiation performance of the cabin body panels are compared. Considering the comprehensive factors such as weight and driver’s comfort, an optimized design scheme for vehicle cabin noise reduction and vibration damping is proposed. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

Anti-bias Target Association Method Based on Laplacian Spectrum and Kuhn-Munkres Algorithm 1

引用

3rd International Conference on Autonomous Unmanned systems, ICAUS 2023

作者： Bai, Xiaomeng Xu, Cheng Fu, Wenxing Guan, Xujun Zhang, Hang Fu, Wenxing Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China Beijing Electro-Mechanical Engineering Institute Beijing100074 China Unmanned System Research Institute Northwestern Polytechnical University Xi’an710072 China

ISBN: (数字)9789819710911

ISBN: (纸本)9789819710904

In the problem of collaborative situational awareness, the single sensor inevitably has random errors, systematic errors, false alarms, and missed alarms. To improve the accuracy of target association in the above cases, this paper proposes an anti-bias target association method based on the Laplacian spectrum and Kuhn-Munkres (KM) algorithm. The main contributions of the paper include addressing the coupling problem between system error calibration and target association through two stages, focusing on the structural characteristics of the target formation in the first stage and the absolute position of the target itself in the second stage. The algorithm takes into account both factors and achieves accurate association under complex errors. The test results demonstrate that the proposed method effectively improves the accuracy of anti-bias target association. © Beijing HIWING Scientific and Technological Information Institute 2024.

关键词： systematic errors

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：