检索结果-内蒙古大学图书馆

Research Progress of Parallel control and Management

IEEE/CAA Journal of Automatica Sinica 2020年第2期7卷 355-367页

作者： Gang Xiong Xisong Dong Hao Lu Dayong Shen State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Computer Science and Technology Beijing Institute of TechnologyBeijing 100081China College of Systems Engineering National University of Defense TechnologyChangsha 410073China

Based on ACP(artificial systems,computational experiments,and parallel execution)methodology,parallel control and management has become a popularly systematic and complete solution for the control and management of complex *** paper focuses on summarizing comprehensive review of the research literature of parallel control and management achieved in the recent years including the theoretical framework,core technologies,and the application *** future research,application directions,and suggestions are also discussed.

关键词： ACP methodology artificial systems computational experiments parallel control parallel management parallel systems

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable fault-tolerant control of in-wheel electric vehicles with steering system failure

引用

IFAC-PapersOnLine 2015年第26期48卷 49-54页

作者： Mihay, Andra Gapár, Peter MTA-BME Control Engineering Research Group Budapest University of Technology and Economics Hungary Institute for Computer Science Control Hungarian Academy of Sciences MTA-BME Control Engineering Research Group Budapest Hungary

The paper deals with the robust and fault tolerant control of an in-wheel electric vehicle, operated by four independently actuated in-wheel motors and steer-by-wire steering system. The goal of the design is to realize velocity and road trajectory tracking of the in-wheel vehicle, even during a fault event in the steer-by-wire steering system. When such a fault is detected, the control system is reconfigured and the torque allocation of the in-wheel engines is recalculated to substitute for the yaw moment originally generated by the steering system. Thus, the vehicle is able to follow the designed path and velocity solely with torque vectoring generated by the independently-controlled in-wheel motors. The high-level motion control of the vehicle is realized founded on the LPV framework, while the reconfiguration is based on constrained optimization techniques. The operation of the designed control system is demonstrated in a CarSim simulation environment. © 2015, IF AC (International Federation of Automatic control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Electric machine control Automobile steering equipment Constrained optimization control systems Electric automobiles Fault tolerance Four wheel steering Integrated control Systems engineering Traction motors Vehicle wheels Constrained optimization techniques Fault tolerant control High level motion control In wheel Reconfigurable control Simulation environment Torque allocations Trajectory tracking

来源：评论

学校读者我要写书评

暂无评论

Drug-Target Interactions Prediction Based on Signed Heterogeneous Graph Neural Networks

引用

Chinese Journal of Electronics 2024年第1期33卷 231-244页

作者： Ming CHEN Yajian JIANG Xiujuan LEI Yi PAN Chunyan JI Wei JIANG College of Information Science and Engineering Hunan Normal University School of Computer Science Shaanxi Normal University Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of Sciences Computer Science Department BNU-HKBU United International College

Drug-target interactions(DTIs) prediction plays an important role in the process of drug *** computational methods treat it as a binary prediction problem, determining whether there are connections between drugs and targets while ignoring relational types information. Considering the positive or negative effects of DTIs will facilitate the study on comprehensive mechanisms of multiple drugs on a common target, in this work, we model DTIs on signed heterogeneous networks, through categorizing interaction patterns of DTIs and additionally extracting interactions within drug pairs and target protein pairs. We propose signed heterogeneous graph neural networks(SHGNNs), further put forward an end-to-end framework for signed DTIs prediction, called SHGNN-DTI,which not only adapts to signed bipartite networks, but also could naturally incorporate auxiliary information from drug-drug interactions(DDIs) and protein-protein interactions(PPIs). For the framework, we solve the message passing and aggregation problem on signed DTI networks, and consider different training modes on the whole networks consisting of DTIs, DDIs and PPIs. Experiments are conducted on two datasets extracted from Drug Bank and related databases, under different settings of initial inputs, embedding dimensions and training modes. The prediction results show excellent performance in terms of metric indicators, and the feasibility is further verified by the case study with two drugs on breast cancer.

关键词： Drug-target interactions Signed heterogeneous network Link sign prediction Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

EMO: Edge Model Overlays to Scale Model Size in Federated Learning

arXiv

引用

arXiv 2025年

作者： Wu, Di He, Weibo Feng, Wanglei Wen, Zhenyu Qian, Bin Varghese, Blesson School of Computer Science University of St Andrews United Kingdom Institute of Cyberspace Security College of Information Engineering Zhejiang University of Technology China University of Science and Technology of China China State Key Laboratory of Industrial Control Technology Zhejiang University China

Federated Learning (FL) trains machine learning models on edge devices with distributed data. However, the computational and memory limitations of these devices restrict the training of large models using FL. Split Federated Learning (SFL) addresses this challenge by distributing the model across the device and server, but it introduces a tightly coupled data flow, leading to computational bottlenecks and high communication costs. We propose EMO as a solution to enable the training of large models in FL while mitigating the challenges of SFL. EMO introduces Edge Model Overlay(s) between the device and server, enabling the creation of a larger ensemble model without modifying the FL workflow. The key innovation in EMO is Augmented Federated Learning (AFL), which builds an ensemble model by connecting the original (smaller) FL model with model(s) trained in the overlay(s) to facilitate horizontal or vertical scaling. This is accomplished through three key modules: a hierarchical activation replay cache to decouple AFL from FL, a convergence-aware communication controller to optimize communication overhead, and an ensemble inference module. Evaluations on a real-world prototype show that EMO improves accuracy by up to 17.77% compared to FL, and reduces communication costs by up to 7.17× and decreases training time by up to 6.9× compared to SFL. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Distributed State Estimation Under Multi-step Random Transmission Delay and Packet Loss

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Dai, Hongyun Fu, Junjie Duan, Peihu Wen, GuanGhui Huang, Tingwen Southeast University School of Mathematics Nanjing 210096 China Purple Mountain Laboratories Nanjing 211111 China KTH Royal Institute of Technology School of Electrical Engineering and Computer Science Stockholm Sweden Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen 518055 China

This paper investigates the problem of underwater distributed state estimation with multi-step random communication delay and packet loss. Since underwater communication adopts acoustic communication, the information transmission speed is relatively slow, and multi-step delay and packet loss situations are frequently encountered. Based on the hybrid consensus filtering algorithm and a proper buffer setting, a distributed Kalman filtering algorithm is proposed, which can deal with possible multistep random time delay and packet loss. A sufficient condition for the filtering stability is rigorously established. In addition, the state estimation problem for an uncertain target model in underwater environments is addressed by combining the Interacting Multiple Model method. Finally, numerical simulations validate the effectiveness of the proposed algorithm and the accuracy of the conclusions, while also demonstrating that this method achieves a 13.9% reduction in the cross-secenario composite RMSE compared to similar buffer-based approaches, further emphasizing its superiority. © 1965-2011 IEEE.

关键词： consensus kalman filter Distributed state estimation multi-step communication delay packet loss

来源：评论

学校读者我要写书评

暂无评论

Using Vector Representation of Propositions and Actions for STRIPS Action Model Learning

引用

Journal of Beijing institute of technology 2018年第4期27卷 485-492页

作者： Wei Gao Dunbo Cai Beijing Aerospace Control Center Beijing 100094China School of Computer Science and Engineering Wuhan Institute of TechnologyWuhan 430205China

Action model learning has become a hot topic in knowledge engineering for automated planning.A key problem for learning action models is to analyze state changes before and after action executions from observed"plan traces".To support such an analysis,a new approach is proposed to partition propositions of plan traces into ***,vector representations of propositions and actions are obtained by training a neural network called Skip-Gram borrowed from the area of natural language processing(NLP).Then,a type of semantic distance among propositions and actions is defined based on their similarity measures in the vector ***,k-means and k-nearest neighbor(kNN)algorithms are exploited to map propositions to *** approach is called state partition by word vector(SPWV),which is implemented on top of a recent action model learning framework by Rao et *** results on the benchmark domains show that SPWV leads to a lower error rate of the learnt action model,compared to the probability based approach for state partition that was developed by Rao et al.

关键词： automated planning action model learning vector representation of propositions

来源：评论

学校读者我要写书评

暂无评论

Analysis and Rejection of Angular Position-based Disturbances for PMSM-actuated Testing Table Systems 34

Analysis and Rejection of Angular Position-based Disturbance...

引用

第三十四届中国控制会议

作者： HUO Xin TONG Xingang LIU Xiaokun ZHANG Xiaorou Control and Simulation Center Harbin Institute of Technology School of Engineering and Computer Science Oakland University

ISBN: (纸本)9781467374439

High-precise testing table is a typical continuously rotating mechanism which is used to test and calibrate inertial components. High operation smoothness is a significant index associated to these kinds of equipments, which is influenced mostly by the external disturbances acting on the systems. In this paper, the disturbances existing in the system are investigated by experiments, and the characteristic of the disturbances is analyzed using frequency spectrum analysis tools, both in time domain and spatial domain. Accordingly angular position-based repetitive controller is presented to reject these kinds of disturbances in sense of time sampling. Comparisons and simulation results are presented to illustrate the effectiveness of the control design.

关键词： Testing Table Systems,Disturbance Analysis,Disturbance Rejection,Repetitive control

来源：评论

学校读者我要写书评

暂无评论

Accelerating Data Transfer in Dataflow Architectures Through a Look-Ahead Acknowledgment Mechanism

引用

Journal of computer Science & technology 2022年第4期37卷 942-959页

作者： Yu-Jing Feng De-Jian Li Xu Tan Xiao-Chun Ye Dong-Rui Fan Wen-Ming Li Da Wang Hao Zhang Zhi-Min Tang State Key Laboratory of Computer Architecture Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China Beijing Smartchip Microelectronics Technology Company Limited Beijing 100000China School of Computer and Control Engineering University of Chinese Academy of SciencesBeijing 100190China

The dataflow architecture,which is characterized by a lack of a redundant unified control logic,has been shown to have an advantage over the control-flow architecture as it improves the computational performance and power efficiency,especially of applications used in high-performance computing(HPC).Importantly,the high computational efficiency of systems using the dataflow architecture is achieved by allowing program kernels to be activated in a simultaneous ***,a proper acknowledgment mechanism is required to distinguish the data that logically belongs to different *** solutions include the tagged-token matching mechanism in which the data is sent before acknowledgments are received but retried after rejection,or a handshake mechanism in which the data is only sent after acknowledgments are ***,these mechanisms are characterized by both inefficient data transfer and increased area *** performance of the dataflow architecture depends on the efficiency of data *** order to optimize the efficiency of data transfer in existing dataflow architectures with a minimal increase in area and power cost,we propose a Look-Ahead Acknowledgment(LAA)*** accelerates the execution flow by speculatively acknowledging ahead without *** simulation analysis based on a handshake mechanism shows that our LAA increases the average utilization of computational units by 23.9%,with a reduction in the average execution time by 17.4%and an increase in the average power efficiency of dataflow processors by 22.4%.Crucially,our novel approach results in a relatively small increase in the area and power consumption of the on-chip logic of less than 0.9%.In conclusion,the evaluation results suggest that Look-Ahead Acknowledgment is an effective improvement for data transfer in existing dataflow architectures.

关键词： dataflow model control-flow model high-performance computing application data transfer power efficiency

来源：评论

学校读者我要写书评

暂无评论

Modular Verification of SPARCv8 Code

引用

Journal of computer Science & technology 2020年第6期35卷 1382-1405页

作者： Jun-Peng Zha Xin-Yu Feng Lei Qiao Department of Computer Science and Technology Nanjing UniversityNanjing 210023China State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China Beijing Institute of Control Engineering Beijing 100080China

Inline assembly code is common in system software to interact with the underlying hardware platforms. The safety and correctness of the assembly code is crucial to guarantee the safety of the whole system. In this paper, we propose a practical Hoare-style program logic for verifying SPARC (Scalable Processor Architecture) assembly code. The logic supports modular reasoning about the main features of SPARCv8 ISA (instruction set architecture), including delayed control transfers, delayed writes to special registers, and register windows. It also supports relational reasoning for refinement verification. We have applied it to verify that there is a contextual refinement between a context switch routine in SPARCv8 and a switch primitive. The program logic and its soundness proof have been mechanized in Coq.

关键词： Scalable Processor Architecture Version 8(SPARCv8) assembly code verification context switch Coq refinement verification

来源：评论

学校读者我要写书评

暂无评论

QTFN:A General End-to-End Time-Frequency Network to Reveal the Time-Varying Signatures of the Time Series

引用

Big Data Mining and Analytics 2024年第3期7卷 905-919页

作者： Tao Chen Yang Jiao Lei Xie Hongye Su State Key Laboratory of Industrial Control Technology Zhejiang UniversityHangzhou 310027China Shenzhen Key Laboratory of Intelligent Bioinformatics and College of Computer Science and Control EngineeringShenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China

Nonstationary time series are ubiquitous in almost all natural and engineering *** the time-varying signatures from nonstationary time series is still a challenging problem for data *** Time-Frequency Distribution(TFD)provides a powerful tool to analyze these ***,they suffer from Cross-Term(CT)issues that impair the readability of ***,to achieve high-resolution and CT-free TFDs,an end-to-end architecture termed Quadratic TF-Net(QTFN)is proposed in this *** by classic TFD theory,the design of this deep learning architecture is heuristic,which firstly generates various basis functions through ***,more comprehensive TF features can be extracted by these basis ***,to balance the results of various basis functions adaptively,the Efficient Channel Attention(ECA)block is also embedded into ***,a new structure called Muti-scale Residual Encoder-Decoder(MRED)is also proposed to improve the learning ability of the model by highly integrating the multi-scale learning and encoder-decoder ***,although the model is only trained by synthetic signals,both synthetic and real-world signals are tested to validate the generalization capability and superiority of the proposed QTFN.

关键词： Time-Frequency Analysis(TFA) Multi-scale Residual Encoder-Decoder(MRED) quadratic Time-Frequency Distribution(TFD)

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：