检索结果-内蒙古大学图书馆

IEEE International Conference on Electronics and Communication engineering (ICECE)

作者： Maryam Cheraghy Meysam Soltanpour Belal Abuhaija Hemn Barzan Abdalla Kennedy Ehimwenma dept. Computer Science and Technology Wenzhou-Kean University Wenzhou China dept. Control Science and Engineering Shandong University Jinan China

ISBN: (数字)9798331517755

ISBN: (纸本)9798331517762

This paper tackles a joint optimization problem in uplink sparse code multiple access (SCMA) networks to enhance network fairness, i.e., Jain's fairness index (JFI). We propose a novel game-theoretic approach, the worst-case player first-strategy selection (WCPFSS) algorithm, to maximize the minimum achievable rate for all subcarriers while ensuring fair power allocation and optimized subcarrier assignment. This approach effectively manages user interference because each subcarrier acts as a player to exchange their strategies, which are clusters of users associated with each subcarrier. The simulation results confirm the superiority of the proposed WCPFSS method w.r.t. JFI for differential setup parameters.

关键词： Codes Simulation Clustering algorithms Interference Minimax techniques Resource management Indexes Uplink Game theory Optimization

来源：评论

学校读者我要写书评

暂无评论

Tube-based coalitional MPC with plug-and-play features

引用

IFAC-PapersOnLine 2023年第2期56卷 7704-7709页

作者： E. Masero P.R. Baldivieso-Monasterios J.M. Maestre P.A. Trodden E.F. Camacho Dept. of Ingeniería de Sistemas y Automática Universidad de Sevilla Spain Dept. of Automatic Control and Systems Engineering University of Sheffield UK Dept. of Systems Science Graduate School of Informatics Kyoto University Japan

This paper presents a distributed setting of model predictive control (MPC) to manage linear multi-agent systems consisting of coupled subsystems. Specifically, local controllers can work in coalitions to improve performance and handle plug-and-play events. This study provides insight into a coalitional MPC strategy based on optimized tubes that handles plug-in and plug-out subsystems. Moreover, we explore an inherent robustness gap to absorb disturbances not covered by the tubes without having to group local controllers. A comparison of our approach with centralized and decentralized MPC is reported using an illustrative example.

关键词： Model predictive control distributed control multi-agent systems time-varying systems robust control plug-and-play events

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Platooning control of Non-Cooperative Autonomous Vehicles in a Mixed Traffic Environment

Deep Reinforcement Learning Platooning Control of Non-Cooper...

引用

IEEE International Conference on Automation Science and engineering (CASE)

作者： Danilo Menegatti Andrea Wrona Antonio Di Paola Simone Gentile Alessandro Giuseppi Dept. of Computer Control and Management Engineering "Antonio Ruberti" Sapienza University of Rome Rome Italy Dept. of Electrical and Information Engineering Polytechnic of Bari Bari Italy

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Ensuring secure spacing between vehicles is vital for road safety, efficient traffic flow, and system stability in autonomous driving. While traditional cooperative platooning approach, relying on centralized coordination exploiting wireless network, faces practical implementation challenges due to communication constraints and diverse driving behaviors, this work introduces a scalable non-cooperative multi-agent platooning strategy based on Deep Reinforcement Learning, leveraging on decentralized decision-making principles. The agents’ aim is to adjust their velocities dynamically to ensure safe following distances and adapt to surrounding vehicle behavior, without the possibility of exchanging information over a wireless network. Extensive simulations validate the effectiveness and robustness of the proposed approach, making it suitable for real-world autonomous driving scenarios.

关键词： Wireless networks Deep reinforcement learning control systems Aerodynamics Robustness Stability analysis Sensors Vehicle dynamics Autonomous vehicles Optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-Point Positional Insertion Tuning for Small Object Detection

arXiv

引用

arXiv 2024年

作者： Goto, Kanoko Karasawa, Takumi Hirose, Takumi Kawakami, Rei Inoue, Nakamasa Dept. of Computer Science Institute of Science Tokyo Tokyo Japan Dept. of Systems and Control Engineering Institute of Science Tokyo Tokyo Japan

Small object detection aims to localize and classify small objects within images. With recent advances in large-scale vision-language pretraining, finetuning pretrained object detection models has emerged as a promising approach. However, finetuning large models is computationally and memory expensive. To address this issue, this paper introduces multi-point positional insertion (MPI) tuning, a parameter-efficient finetuning (PEFT) method for small object detection. Specifically, MPI incorporates multiple positional embeddings into a frozen pretrained model, enabling the efficient detection of small objects by providing precise positional information to latent features. Through experiments, we demonstrated the effectiveness of the proposed method on the SODA-D dataset. MPI performed comparably to conventional PEFT methods, including CoOp and VPT, while significantly reducing the number of parameters that need to be tuned. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Constrained Predictive Current control in dq Frame for a Permanent Magnet Synchronous Machine

Constrained Predictive Current Control in dq Frame for a Per...

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Madalin Costin Corneliu Lazar Dept.of Automatic Control and Applied Informatics "Gheorghe Asachi" Technical University of Iasi Iasi Romania Dept. of Automatic Control and Electrical Engineering "Dunarea de Jos" University of Galati Galati Romania

In the paper, the design and Simulink implementation of a predictive current control structure in dq frame for a permanent magnet synchronous machine (PMSM) are presented. Starting from the multivariable model of the currents in the dq reference frame, first it is decoupled and through the rejection of the disturbance introduced by the back-EMF, two single-input single-output (SISO) systems result whose dynamics are generated by R-L circuits. For these SISO systems, the model predictive control (MPC) algorithms are designed that allow the consideration of physical limitations through constraints The performances of the current control structure with MPC algorithms are compared with those obtained with the conventional PI controllers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Adaptive CUSUM Approach for Automating Sleep Apnoea Analysis Based on Pulse and Oximetry Data 20

An Adaptive CUSUM Approach for Automating Sleep Apnoea Analy...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Yang, Dongjin Bhargava, Eishaan Elphick, Heather Mihaylova, Lyudmila S. University of Sheffield Dept. of Automatic Control and Systems Engineering United Kingdom Sheffield Children's Hospital Department of Paediatric Otolaryngology Sheffield United Kingdom Sheffield Children's Hospital Department of Paediatric Respiratory and Sleep Medicine Sheffield United Kingdom

ISBN: (纸本)9798350320831

Sleep apnoea is a common sleep disorder during human sleep. It is usually diagnosed by a doctor after recording one nights' sleep signals. Patients have to go to the hospital to record sleep signals, which is time-consuming and resource-intensive. The study focused on two signals, pulse data and oximetry data, with the aim of detecting apnoea using a single signal. This paper introduced an anomaly detection approach using the adaptive cumulative sum (ACUSUM) change point detection algorithm to monitor outliers in the signal. In addition, the test results of ACUSUM will be compared with the test results of classical CUSUM. Besides, the threshold selection has been changed from an unchanging constant to a value related to the standard deviation of the selected signal based on a rational subgroup process. The results of the comparison confirm that ACUSUM is better than classical CUSUM in the accuracy of automatic detection. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Em-RIPE: Runtime Intrusion Prevention Evaluator for ARM Microcontroller Systems

Em-RIPE: Runtime Intrusion Prevention Evaluator for ARM Micr...

引用

2022 International Conference on Electrical, computer, Communications and Mechatronics engineering, ICECCME 2022

作者： Roascio, Gianluca Serra, Gabriele Eftekhari Moghadam, Vahid Politecnico di Torino Dept. of Control and Computer Engineering Turin Italy Scuola Superiore sant'Anna TECIP Department Pisa Italy

ISBN: (数字)9781665470957

ISBN: (纸本)9781665470957

Although they have been known for some time, the security implications of buffer overflows (BOF) continue to rouse great attention among software experts in the academic and commercial sectors. Recently, there has been particular interest in discussing how to mitigate risks deriving from BOF on embedded and loT devices, which have lower computational capabilities given their low-cost and low-power requirements. Although the literature is rich of solutions for these devices as well, authors often fail to quantitatively compare their techniques with related work from a security perspective, and mostly rely on qualitative analysis. Existing evaluator benchmarks (such as the famous RIPE, introduced in 2011) are designed to be used only on general-purpose systems, e.g., with a rich Linux OS and Intel architecture. This paper presents Em-RIPE, a prototype evaluation tool written for assessing protections applied to real-time embedded systems, such as microcontrollers equipped with ARM processors. This first version of the tool supports 105 different possible attack combinations, on which the resilience level of the platform under test can be measured. As experimental data, the obtained pro-tection coverage for major compiler-based firmware protections is reported. © 2022 IEEE.

关键词： Firmware

来源：评论

学校读者我要写书评

暂无评论

NEW TOOL FOR SYSTEM IDENTIFICATION AND PREDICTIVE control BASED ON NEURAL NETWORKS USING LABVIEW SOFTWARE

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer Science 2022年第2期84卷 91-110页

作者： Alshareefi, Hamid Lupu, Ciprian Alboudkhal, Hayder Ismail, Laith Dept. of Automatic Control and Computers University POLITEHNICA of Bucharest Romania Ministry of Electricity Iraq Dept. of Computer Technology Engineering AL-TURATH University College Baghdad Iraq

In this paper, a new tool for system identification and model predictive control (MPC) has been developed. The mathematical approximation of the model identification was derived using the neural network theory. The emphasis of this paper is to employ a multi-layer recurrent neural network with three layers to match an autoregressive-moving average (ARMA) model in the identification stage to provide the mathematical model for the model predictive controller in the control stage. The tool was designed using LabVIEW software and the MathScript facility. The tool can be used to identify and control simulated or real systems using the stored input/output data of the system. © 2022, Politechnica University of Bucharest. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent Operational Decision Support System for Sugar Factory Resource Efficiency 5

Intelligent Operational Decision Support System for Sugar Fa...

引用

5th IEEE International Conference on Modern Electrical and Energy System, MEES 2023

作者： Lutska, Nataliia Zaiets, Nataliia Vlasenko, Lidiia Junge, Stefan National University of Food Technologies Dept. of Automation and Computer Technologies of Control Systems Kyiv Ukraine National University of Life and Environmental Sciences of Ukraine Dept. of Automation and Robotic Systems Kyiv Ukraine State University of Trade and Economics Dept. of Software Engineering and Cyber Security Kyiv Ukraine Berlin University of Applied Sciences Dept. of Packaging Technology Berlin Germany

ISBN: (纸本)9798350359787

With the economic crisis that is looming over the world due to changes in the energy sector and a reduction in the supply of certain types of products, energy and resource efficiency issues are becoming more relevant for the food industry. Also important is the preservation of the environment and the implementation of Cleaner Production trends. Most enterprises follow the concept of Industry 4.0 and increase efficiency through the implementation of intelligent methods, in particular machine learning. The paper proposes a neural network model of sugar production. The model makes it possible to predict the main estimates of resource efficiency used to correct the technological modes of production by the operator-technologist. The structure of the operational decision support system has been developed and is used by personnel to model and predict changes in resource efficiency estimates and KPIs calculated on their basis. Its feature is the integration of methods for achieving resource efficiency, improving environmental performance and ensuring KPIs. To do this, at the initial stage, an analysis of the main flows that affect resource efficiency and an assessment of their importance was carried out. Ensuring Production Performance is confirmed by the simulation and the adequacy of the created neural network accuracy of more than 95%. © 2023 IEEE.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Cooperation and mental states neurophysiological assessment for pilots' training and expertise evaluation

Cooperation and mental states neurophysiological assessment ...

引用

2023 IEEE International Workshop on Technologies for Defense and Security, TechDefense 2023

作者： Borghini, Gianluca Giorgi, Andrea Ronca, Vincenzo Mezzadri, Lorenzo Capotorto, Rossella Arico, Pietro Di Flumeri, Gianluca Babiloni, Fabio Sapienza University of Rome Dept. of Molecular Medicine Rome Italy Sapienza University of Rome Dept. of Anatomical Histological Forensic and Orthopaedic Sciences Rome Italy Sapienza University of Rome Dept. of Computer Control and Management Engineering Antonio Ruberti Rome Italy Urbe Aero Ato Flight Training School Rome Italy

ISBN: (纸本)9798350319392

The aim of the study was to validate a methodology for professional pilots' neurophysiological assessment to improve training program tailoring and management. In particular, the assessment focused on quantifying (i) mental workload, (ii) stress level (iii) and the cooperation degree between the two members of the crews. Two groups of pilots were involved in the experiments: Experienced and Unexperienced. Additionally, the Instructor was responsible to provide subjective evaluation about the pilots' mental states and cooperation. During the entire flight simulations, the pilots' brain activity was acquired through the Electroencephalography (EEG). The results demonstrated that it is possible to quantify operators' mental states and degree of cooperation while dealing with flight simulations under realistic settings. Pilots' mental workload and stress behavioral levels resulted to be positively and significantly correlated with the corresponding neurophysiological measurements (all R > 0.6, all p © 2023 IEEE.

关键词： Electroencephalography

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：