检索结果-内蒙古大学图书馆

System Optimal Routing and Distribution of Benefits on National Road Networks

Transportation Research Procedia 2025年 82卷 2532-2545页

作者： Alexander Roocroft Giuliano Punzo Muhamad Azfar Ramli Department of Automatic Control and Systems Engineering University of Sheffield Sheffield United Kingdom Institute of High Performance Computing A*STAR Singapore

Rerouting drivers from selfish route choices to system-optimal traffic patterns has the potential to improve the performance of existing infrastructure. Previous research has looked into assessing the potential of rerouting through the empirical price of anarchy, a measure of network efficiency. However, studies using real-world measurements have been limited by methodological accuracy and network size. Also, they have lacked understanding of the spatial distribution of benefits from rerouting and the relationship with marginal external cost road charges that can be used for implementation. In this article, we create an accurate data-driven traffic assignment model of England's Strategic Road Network. We use it to calculate the national price of anarchy, which is found to be almost 1 implying gains from rerouting at the national scale are minimal and smaller than in other studies. The results show the distribution of rerouting benefits varies strongly with different network zones and demand profiles. This did not match the distribution of marginal external cost charges. Some zones have noticeable benefits from rerouting although the overall network benefit is small, however, these zones do not coincide with where the largest road charges have to be applied for system-optimal rerouting. These results have implications for rerouting implementation.

关键词： Strategic Road Network Empirical Price of Anarchy National Traffic Assignment

来源：评论

学校读者我要写书评

暂无评论

Sensorformer: A Memory-efficient Transformer for Industrial Sensor Fusion 27

Sensorformer: A Memory-efficient Transformer for Industrial ...

引用

27th International Conference on Automation and Computing, ICAC 2022

作者： Zhang, Ze Farnsworth, Michael Tiwari, Divya Jewell, Geraint Tiwari, Ashutosh The University of Sheffield Department of Automatic Control and Systems Engineering Sheffield United Kingdom Department of Electronic and Electrical Engineering The University of Sheffield Sheffield United Kingdom

ISBN: (数字)9781665498074

ISBN: (纸本)9781665498074

The deep learning model, Transformer, and its variants have achieved state-of-the-art performance in many domains, such as natural language processing, vision recognition, protein structure prediction, as well as industrial multi-sensor data processing tasks. However, the high memory usage and O(N2) computational complexity of Transformer can result in the high cost and low efficiency in industrial scenarios, especially in the case of edge computing. To mitigate this problem, we propose a novel auto-decorrelation block based on the Fast Fourier Transform and the self-attention mechanism of Transformer to reduce memory occupation and computational complexity. Instead of removing the related data, this model merges the correlated channels progressively throughout the whole inference process. The proposed method was tested on a public dataset based on condition monitoring of a hydraulic system. Results demonstrated that our proposed method reduced memory usage to around one-fifth of its original size while maintaining similar inference accuracy. The inference time can also be 2 times faster. This allows the transformer to be used for industrial multi-sensor data processing tasks in a more resource-efficient and faster manner. © 2022 IEEE.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Stability of Nonlinear Model Predictive control Under Consecutive Packet Losses

Stability of Nonlinear Model Predictive Control Under Consec...

引用

UKACC International Conference on control (control)

作者： Paulo Loma-Marconi Paul Trodden Iñaki Esnaola Department of Automatic Control & Systems Engineering University of Sheffield Sheffield United Kingdom

ISBN: (数字)9798350374261

ISBN: (纸本)9798350374278

In this paper, we study the stability of a discrete-time nonlinear networked system controlled by model predictive control without explicit terminal constraints. The system is subject to input constraints and random packet losses on the actuation communication channel between the controller and the plant. We consider the scenario where a buffer-intended to store transmitted control sequences and provide some robustness to packet losses-is present, and also the scenario where a buffer is not present. We analyse the stability of the closed-loop system in these stochastic scenarios, employing the assumption that the terminal cost is merlye a local, rather than global, control Lyapunov function (CLF). We develop conditions that characterize an upper bound on the number of consecutive packet losses in order that stability is maintained.

关键词： Costs Upper bound Packet loss Stochastic processes Propagation losses Stability analysis Robustness

来源：评论

学校读者我要写书评

暂无评论

Enhancing 3D Human Skeleton Key-point Detection through Weakly Supervised Learning and Multi-level Attention Mechanisms

Enhancing 3D Human Skeleton Key-point Detection through Weak...

引用

2023 IEEE EMBS Special Topic Conference on Data Science and engineering in Healthcare, Medicine and Biology, IEEECONF 2023

作者： Xu, Meng Gong, Yuanhao Dogramadzi, Sanja University of Sheffield Department of Automatic Control and Systems Engineering SheffieldS10 2TN United Kingdom Shenzhen University Faculty of Electronics and Information Engineering China

ISBN: (纸本)9798350383386

With the soaring interest in understanding the dynamics of human body skeletons for applications such as action recognition and video understanding, the significance of precise 3D key-point detection has become increasingly prominent. Despite the advancements, existing approaches struggle to address the issues of occlusions and limited annotated data. This paper proposes a novel framework integrating a multilevel attention mechanism and weakly supervised 3D key-point generation to tackle these prevalent issues, enhancing both the accuracy and efficiency of human pose estimation. © 2023 IEEE.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning-Based Approach for Optimal Output Tracking in Uncertain Nonlinear systems with Mismatched Disturbances

A Reinforcement Learning-Based Approach for Optimal Output T...

引用

UKACC International Conference on control (control)

作者： Zezhi Tang J Anthony Rossiter George Panoutsos Department of Automatic Control and Systems Engineering University of Sheffield Sheffield United Kingdom

ISBN: (数字)9798350374261

ISBN: (纸本)9798350374278

In this paper, the optimal control problem of uncertain nonlinear systems is considered. A nonlinear disturbance observer (NDO) is proposed to measure the lumped uncertainties present in the system. Disturbances that do not enter the same channel as the control signal, so-called mismatched disturbances, are difficult to reject directly within the control channel. To overcome the challenge, a generalized disturbance observer-based compensator is implemented to address the uncertainty compensation problem by attenuating its influence on the output channel. In real time, by augmenting the system states with the output tracking error, we develop a composite actor-critic reinforcement learning (RL) scheme for approximating the optimal control policy as well as the ideal value function pertaining to the compensated system by solving the Hamilton-Jacobi-Bellman (HJB) equation. Concurrent learning is applied in this article by using the recorded data of the known model of the system, in order to enhance the robustness of the system by canceling the influence of the probing signal. Simulation results demonstrate the effectiveness of the proposed scheme, offering an optimal solution for the output tracking problem in a second-order model with mismatched disturbances.

关键词： Uncertainty Simulation Measurement uncertainty Optimal control Reinforcement learning Mathematical models Robustness

来源：评论

学校读者我要写书评

暂无评论

RGB-D Image-Based Deep Neural Network Body Shape Classifier

RGB-D Image-Based Deep Neural Network Body Shape Classifier

引用

2023 IEEE EMBS Special Topic Conference on Data Science and engineering in Healthcare, Medicine and Biology, IEEECONF 2023

ISBN: (纸本)9798350383386

Leveraging the untapped potential of depth information in RGB-D images, this study introduces a deep neural network classifier for advanced body shape classification. Going beyond traditional RGB image analysis, our method innovatively employs multi-task learning, simultaneously performing body shape classification, posture estimation, and body part segmentation to achieve superior accuracy. This approach promises to revolutionize personalization avenues in healthcare, fashion, and entertainment industries, establishing a new benchmark in body shape analysis. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Power-Communication Co-Simulation Platform for Real-Time Microgrid Cyber Security Analysis

A Power-Communication Co-Simulation Platform for Real-Time M...

引用

Artificial Intelligence of Things and systems (AIoTSys), International Conference on

作者： Dongmeng Qiu Mengxiang Liu Xin Zhang Department of Automatic Control and Systems Engineering University of Sheffield Sheffield United Kingdom

ISBN: (数字)9798331507886

ISBN: (纸本)9798331507893

The rapid digitalisation process in power system has greatly benefited the large-scale integration of distributed energy resources (DERs), essentially accelerating the progress towards net zero. However, numerous cyber attacks such as false data injection (FDI) attacks are impeding the normal control and operation activities. This paper aims to establish a real-time microgrid co-simulation platform to fully study the impacts of realistic attack events on micorgrid's control performance. Although there exist a large number of power-communication co-simulation platforms for the power system, they are designed to mainly provide validation services for control and operation algorithms and little attention has been paid to the cyber security. In the established microgrid platform, power and communication parts are simulated in Typhoon Hardware-in-the-loop(HIL) 602+ and EXata Network Simulator, respectively, and a dedicated synchronisation scheme is developed and embedded in Raspberry Pis to achieve master-slave data exchange between them. Based on the advanced cyber libraries provided by EXata, realistic FDI and packet drop attacks are mounted against the mapped communication links within EXata. The results indicate that these cyber attacks can severely influence the microgrid control performance including destabilising system states and specific state deviations, further demonstrating the necessity of deploying effective cyber-resilience enhancement mechanisms.

关键词： Tropical cyclones Prevention and mitigation Microgrids Real-time systems Main-secondary Libraries Power systems Synchronization Security Cyberattack

来源：评论

学校读者我要写书评

暂无评论

MATLAB files to support learning of simple frequency response design

引用

IFAC-PapersOnLine 2024年第26期58卷 1-6页

作者： J.A. Rossiter Department of Automatic Control and Systems Engineering University of Sheffield Sheffield S1 3JD UK

This paper presents a small number of MATLAB APPs and livescript files designed to help students both understand and implement frequency response tools into feedback design. The paper presents the thinking behind the ... 详细信息

关键词： control101 toolbox frequency response lead and lag compensation virtual laboratories independent learning

来源：评论

学校读者我要写书评

暂无评论

Computationally Efficient Kalman Filter Framework for Intra-Frame Image Reconstruction with a Rolling Shutter Camera

Computationally Efficient Kalman Filter Framework for Intra-...

引用

IEEE International Conference on Image Processing

作者： Sabeethan Kanagasingham Andrew R. Mills Visakan Kadirkamanathan Department of Automatic Control and Systems Engineering The University of Sheffield Sheffield United Kingdom

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

This paper addresses the problem of reconstructing image sequences from a rolling shutter camera-based thermal image acquisition system that integrates the image field over an exposure time. It proposes a novel approach to extend the distributed Kalman filtering framework for intra-frame reconstruction. This accounts for the exposure effect through a state-augmentation model, while respecting the row-byrow image acquisition process. Additionally, two alternative rolling shutter scan strategies: interlaced-x and random, are explored to mitigate delays in observing abrupt changes inherent in sequential rolling shutter scans. Simulation results demonstrate that the proposed approach effectively accommodates exposure and achieves reliable intra-frame reconstruction quality. The interlaced-x scan strategy, with x equal to the size of the image partition block, emerges as the preferred choice, highlighting improved performance in recovering from sudden events. The augmented distributed Kalman filter offers a scalable solution to enhance temporal resolution and overall reliability of thermal imaging of dynamic thermal processes.

关键词： Image resolution Simulation Thermal variables measurement Three-dimensional printing Size measurement Time measurement Steady-state

来源：评论

学校读者我要写书评

暂无评论

Improving Workplace Safety in the Cargo Industry through Posture Monitoring using Mediapipe and Machine Learning 17

Improving Workplace Safety in the Cargo Industry through Pos...

引用

17th International Conference on INnovations in Intelligent systems and Applications, INISTA 2023

作者： Cobb, Buket Sonbas Candan, Fethi Harran University Department of Electrical-Electronics Engineering Sanliurfa63190 Turkey University of Sheffield Department of Automatic Control and Systems Engineering SheffieldS1 3JD United Kingdom

ISBN: (纸本)9798350338904

This research reveals the potential of Mediapipe with machine learning methods in addressing the critical need for real-time posture monitoring, offering a promising solution for creating secure work environments and improving health and safety conditions not only in the cargo industry but also in other fields, such as healthcare, sports, and industry. The findings indicate that the Random Forest Classifier demonstrates the highest accuracy in classifying untrained movements, indicating its potential for developing a posture correction warning system. Further research is needed to validate the findings and explore real-world applications. Overall, this study contributes to the advancement of workplace safety and sets the foundation for future developments in posture monitoring systems using Mediapipe and machine learning using Python programming. © 2023 IEEE.

关键词： Python

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：