检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Qiu, ZiJie Jin, Luozhijie Du, Zijian Chen, Hongyu Cen, Yan Sun, Siqi Mei, Yongfeng Zhang, Hao Research Institute of Intelligent Complex Systems Fudan University Shanghai China School of Information Science and Technology Fudan University Shanghai200433 China Department of Physics Fudan University Shanghai200433 China Department of Optical Science and Engineering Key Laboratory of Micro and Nano Photonic Structures Ministry of Education Fudan University Shanghai200433 China Department of Materials Fudan University Shanghai200433 China State Key Laboratory of Photovoltaic Science and Technology Fudan University Shanghai200433 China

Discovering functional crystalline materials through computational methods remains a formidable challenge in materials science. Here, we introduce VQCrystal, an innovative deep learning framework that leverages discrete latent representations to overcome key limitations in current approaches to crystal generation and inverse design. VQCrystal employs a hierarchical VQ-VAE architecture to encode global and atom-level crystal features, coupled with an machine learning-based inter-atomic potential(IAP) model and a genetic algorithm to realize property-targeted inverse design. Benchmark evaluations on diverse datasets demonstrate VQCrystal’s advanced capabilities in representation learning and novel crystal discovery. Notably, VQCrystal achieves state-of-the-art performance with 91.93% force validity and a Fréchet Distance of 0.152 on MP-20, indicating both strong validity and high diversity in the sampling process. To demonstrate real-world applicability, we apply VQCrystal for both 3D and 2D material design. For 3D materials, the density-functional theory validation confirmed that 62.22% of bandgaps and 99% of formation energies of the 56 filtered materials matched the target range. Moreover, 437 generated materials were validated as existing entries in the full database outside the training set. For the discovery of 2D materials, 73.91% of 23 filtered structures exhibited high stability with formation energies below -1 eV/atom. Our results highlight VQCrystal’s potential to accelerate the discovery of novel materials with tailored properties. © 2024, CC BY.

关键词： Crystalline materials

来源：评论

学校读者我要写书评

暂无评论

Neural piecewise-constant delay differential equations

arXiv

引用

arXiv 2022年

作者： Zhu, Qunxi Shen, Yifei Li, Dongsheng Lin, Wei Research Institute of Intelligent Complex Systems Fudan University China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Hong Kong Microsoft Research Asia China School of Mathematical Sciences State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science Institutes of Brain Science Shanghai Center for Mathematical Sciences Center for Computational Systems Biology LCNBI and Research Institute of Intelligent Complex Systems Fudan University China

Continuous-depth neural networks, such as the Neural Ordinary Differential Equations (ODEs), have aroused a great deal of interest from the communities of machine learning and data science in recent years, which bridge the connection between deep neural networks and dynamical systems. In this article, we introduce a new sort of continuous-depth neural network, called the Neural Piecewise-Constant Delay Differential Equations (PCDDEs). Here, unlike the recently proposed framework of the Neural Delay Differential Equations (DDEs), we transform the single delay into the piecewiseconstant delay(s). The Neural PCDDEs with such a transformation, on one hand, inherit the strength of universal approximating capability in Neural DDEs. On the other hand, the Neural PCDDEs, leveraging the contributions of the information from the multiple previous time steps, further promote the modeling capability without augmenting the network dimension. With such a promotion, we show that the Neural PCDDEs do outperform the several existing continuousdepth neural frameworks on the one-dimensional piecewiseconstant delay population dynamics and real-world datasets, including MNIST, CIFAR10, and *** Codes 34Kxx, 93Cxx, 92B2 © 2022, CC BY.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Safe Control of Multiagent systems With Malicious Attacks Using Adaptive Fault-Tolerant Consensus Control

引用

IEEE Transactions on Aerospace and Electronic systems 2025年

作者： Zhang, Pu Zhang, Kun Huang, Yulong Ni, Junkang Lv, Yuezu Gong, Xin Duan, Haibin Xi'an University of Technology School of Automation and Information Engineering Xi'an710048 China Beihang University School of Astronautics Beijing100191 China Harbin Engineering University College of Intelligent Systems Science and Engineering Harbin150001 China Northwestern Polytechnical University School of Automation Xi'an710072 China Beijing Institute of Technology MIIT Key Laboratory of Complex-field Intelligent Sensing Beijing100081 China Southeast University School of Cyber Science and Engineering Nanjing211189 China Beihang University School of Automation Science and Electrical Engineering Beijing100083 China

This paper proposed a hierarchical control framework that integrates an upper observer layer and a lower tracking layer. Based on higher-order sliding mode observer in the upper layer, a distributed high-order sliding mode observer (SMO) is used to approximate the leader's state, which can also identify some unknown and uncertain terms caused by malicious attacks. For the lower tracking layer, an adaptive fixed-time prescribed performance fault-tolerant control (FTPPFTC) method is leveraged to address the problem of malicious attacks and help the following agent achieve the stable tracking performance. By using the developed method, it is proved that the tracking errors of the multi-agent systems can converge into a small neighborhood within the fixed time. Finally, the numerical examples and comparative results illustrate the effectiveness of the proposed control method. © 1965-2011 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Traffic Prediction via Denoised Endpoint Distribution

Multi-agent Traffic Prediction via Denoised Endpoint Distrib...

引用

IEEE/RSJ International Conference on intelligent Robots and systems (IROS)

作者： Yao Liu Ruoyu Wang Yuanjiang Cao Quan Z. Sheng Lina Yao Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Shenyang China School of Computing Macquarie University Sydney Australia School of Computer Science and Engineering University of New South Wales Sydney Australia Data 61 CSIRO & School of Computer Science and Engineering University of New South Wales Sydney Australia

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

The exploration of high-speed movement by robots or road traffic agents is crucial for autonomous driving and navigation. Trajectory prediction at high speeds requires considering historical features and interactions with surrounding entities, a complexity not as pronounced in lower-speed environments. Prior methods have assessed the spatiotemporal dynamics of agents but often neglected intrinsic intent and uncertainty, thereby limiting their effectiveness. We present the Denoised Endpoint Distribution model for trajectory prediction, which distinctively models agents’ spatio-temporal features alongside their intrinsic intentions and un-certainties. By employing Diffusion and Transformer models to focus on agent endpoints rather than entire trajectories, our approach significantly reduces model complexity and enhances performance through endpoint information. Our experiments on open datasets, coupled with comparison and ablation studies, demonstrate our model’s efficacy and the importance of its components. This approach advances trajectory prediction in high-speed scenarios and lays groundwork for future developments.

关键词： Uncertainty Navigation Soft sensors Robot kinematics Predictive models Transformers Road traffic Trajectory complexity theory Spatiotemporal phenomena

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection Based on Principle of Justifiable Granularity and Probability Density Estimation

Anomaly Detection Based on Principle of Justifiable Granular...

引用

Chinese Automation Congress (CAC)

作者： Sheng Du Xian Ma Xiang Li Min Wu Weihua Cao Witold Pedrycz School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada Systems Research Institute Polish Academy of Sciences Warsaw Poland Department of Computer Engineering Faculty of Engineering and Natural Sciences Istinye University Sariyer/Istanbul Turkiye

Anomaly detection is essential to ensure the safety of industrial processes. This paper presents an anomaly detection approach based on the probability density estimation and principle of justifiable granularity. First, time series data are transformed into a two-dimensional information granule by the principle of justifiable granularity. Then, the test statistic is constructed, and the probability density and cumulative distribution functions of the test statistic are calculated. Next, the confidence level determines the test threshold. Finally, the time series data of a key parameter in the sintering process is used as a case study. The experimental result demonstrates that the proposed approach can detect abnormal time series data effectively, providing an accurate and effective solution for detecting time series anomalies in industrial processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Sliding Mode Control for Random Teleoperation System with Time-Varying Delay

Adaptive Sliding Mode Control for Random Teleoperation Syste...

引用

第40届中国控制会议

作者： Haitao Jian Shiqi Zheng Chenghao Zhao Haiming Li Shihao Wang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

This paper focuses on the control problem of a class of random teleoperation systems. To overcome the difficulties caused by the random environment, a new adaptive sliding mode control method for random teleoperation system is *** with the previous work, the model in this paper is built by random differential equations. In addition, different time-varying delays are introduced between the two communication channels. Furthermore, a new design scheme for random teleoperation system with varying-time delay is proposed. Radial Basis Function neural network（RBFNN） is introduced to deal with the unknown nonlinearities of the system. Using this method, good position tracking performance and stability can be obtained.

关键词： Adaptive control Sliding mode Teleoperation Random Lagrangian system Time-varying delay

来源：评论

学校读者我要写书评

暂无评论

Multicarrier Waveform Design for mmWave/THz Integrated Sensing and Communication

Multicarrier Waveform Design for mmWave/THz Integrated Sensi...

引用

International Wireless Communications and Mobile computing Conference, IWCMC

作者： Fan Zhang Tianqi Mao Ruiqi Liu Leyi Zhang Dezhi Zheng Tengfei Wang Zhaocheng Wang Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China MIIT Key Laboratory of Complex-Field Intelligent Sensing Beijing Institute of Technology Beijing China Yangtze Delta Region Academy Beijing Institute of Technology (Jiaxing) Jiaxing China Wireless and Computing Research Institute ZTE Corporation Beijing China Technology Planning Department ZTE Corporation Beijing China

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

Integrated sensing and communication (ISAC) is recognized as one of key enabling technologies for the Meta-verse. To enhance both communication data rate and sensing accuracy, the exploitation of millimeter wave (mmWave) and terahertz (THz) frequencies becomes mandatory due to huge amount of spectrum resources. To combat the severe path-loss at mmWave/THz band, large-scale antenna arrays are usually employed to form directional beams. However, the ultra-broad bandwidth induces undesirable beam squint (BS) effects, where the beams from different subcarriers point to diverse angles, leading to the communication performance loss. Fortunately, this BS effect can be leveraged to facilitate the multi-angle super-resolution sensing with minimal beam sweeping overhead. Against this background, we propose a novel multicarrier waveform design methodology for the BS-assisted ISAC systems, which optimizes the frequency resource allocation between sensing and communications to reach a good dual-functional performance trade-off. To mitigate mutual interference, both functions are assigned non-overlapping subcarriers. The subcarrier assignment design is formulated as a mixed integer programming problem to maximize the communication throughput while ensuring the required sensing range and resolution, which involves high complexity to get an exact solution. To this end, we propose a two-stage iterative update algorithm to obtain a quasi-optimal solution with low computational complexity. Numerical results demonstrate that our proposed methodology achieves high-rate communication and high-resolution sensing simultaneously with relatively low overhead.

关键词： Wireless communication Design methodology Superresolution Integrated sensing and communication Throughput Iterative algorithms Resource management

来源：评论

学校读者我要写书评

暂无评论

Fault Detection Based on Canonical Correlation Analysis with Rank Constrained Optimization

Fault Detection Based on Canonical Correlation Analysis with...

引用

第40届中国控制会议

作者： Yuhan Zhang Xianchao Xiu Ying Yang Wanquan Liu State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering ScienceCollege of EngineeringPeking University School of Intelligent Systems Engineering Sun Yat-sen University

Canonical correlation analysis（CCA） has attracted increasing attention in the field of fault detection because it provides an effective way to explore the relationship between the input and output *** paper develops a novel rank constrained CCA（RCCCA） framework,which is the first approach that takes the rank prior information into ***,the rank constrained optimization is able to capture the global structures of variables,and thus improve the performance of fault *** order to solve RCCCA,an alternating minimization algorithm is designed,which aims to preserve the maximum correlation with the low-rank learning.A fault detection residual is then generated,and the test statistic is constructed to determine whether a fault *** RCCCA-based fault detection is finally tested on a numerical example and the Tennessee Eastman benchmark *** results indicate the efficiency and feasibility of the proposed method.

关键词： Fault detection canonical correlation analysis rank constrained optimization alternating minimization algorithm Tennessee Eastman process

来源：评论

学校读者我要写书评

暂无评论

Performance Improvement of TFRC Congestion Control Algorithm in Wireless Network Streaming Media Transmission

Performance Improvement of TFRC Congestion Control Algorithm...

引用

第40届中国控制会议

作者： Kang Li Yan Yuan Yitao Chen Zhicheng Zhao School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

This paper studies a rate-based TCP-Friendly Rate Control（TFRC） mechanism, which is widely used in multimedia real-time services, and analyzes its basic workflow, throughput model and calculation of key parameters. In order to meet the demand of real-time service for network transmission, the bandwidth-delay product（BDP） is applied to the congestion control of TFRC as the network congestion warning signal, and the improved TFRC algorithm is proposed. The simulation results show that this method can achieve good results in the network transmission of real-time services, and its friendliness and smoothness are improved to a certain extent.

关键词： Real-time multimedia application TFRC Bottleneck bandwidth and round-trip time（BBR） Wireless network

来源：评论

学校读者我要写书评

暂无评论

A New Dynamic Event-Triggered Mechanism Based Model Predictive Control for systems with Polytopic Uncertainties

A New Dynamic Event-Triggered Mechanism Based Model Predicti...

引用

第40届中国控制会议

作者： Fan Wei Xiongbo Wan School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

This paper investigates the problem of model predictive control（MPC） for systems with polytopic uncertainties under the event-triggered communication mechanism. To save network resources, a new dynamic event-triggered mechanism（DETM） is proposed, which contains an adaptive internal dynamic variable（IDV） and a time-varying parameter. A "min-max"optimization problem is put forward to dealing with the MPC problem for systems with polytopic uncertainties. With the aid of a Lyapunov-like function dependent on the IDV of the DETM, an auxiliary optimization problem is devised with constraints in terms of linear matrix inequalities. By solving such an auxiliary optimization problem, sub-optimal feedback gains are obtained which ensure the input-to-state practical stability of the closed-loop system. A numerical example is provided to demonstrate the effectiveness of the devised MPC algorithm.

关键词： Model predictive control dynamic event-triggered mechanism networked systems input-to-state practical stability

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：