检索结果-内蒙古大学图书馆

Toward Using Fuzzy Grey Cognitive Maps in Manned and Autonomous Collision Avoidance at Sea

IEEE Journal of Oceanic engineering 2025年第2期50卷 1210-1230页

作者： Gil, Mateusz Poczęta, Katarzyna Wróbel, Krzysztof Yang, Zaili Chen, Pengfei Gdynia Maritime University Research Group on Maritime Transportation Risk and Safety Faculty of Navigation Gdynia81-345 Poland Faculty of Electrical Engineering Automatics Control and Computer Science Kielce University of Technology Kielce25-314 Poland Research Institute LiverpoolL3 3AF United Kingdom Wuhan University of Technology School of Navigation Wuhan430063 China Hubei Key Laboratory of Inland Shipping Technology Wuhan430063 China

With Maritime Autonomous Surface Ships (MASS) slowly but steadily nearing full-scale implementation, the question of their safety persists. Regardless of being a disruptive technology, they will likely be subject to the same factors shaping their safety performance as manned ships nowadays are. Yet, the impact of these factors may be different in each case. The current study presents an application of Fuzzy Grey Cognitive Maps (FGCMs) to the comparative evaluation of factors affecting collision avoidance at sea. To this end, subject matter experts have been elicited, and the data obtained from them have been analyzed, concerning how changes in the intensity of given factors would affect safety performance. The obtained results showed that with the use of FGCM, it was possible to model the relative impact of selected factors both on a specific phase of the maritime collision avoidance process as well as on its entirety. The conducted analysis shows noticeable variability of the influence of some factors, depending on the timing of their activation during the process (time dependence), and using FGCM, it was possible to assess its quantification. Furthermore, the results indicate that greater differences can be found between the factors’ impact on phases of an encounter than between manned and autonomous ships. The outcome of this study may be found interesting for all parties involved in maritime safety modeling as well as working on the forthcoming introduction of autonomous ships. © 1976-2012 IEEE.

关键词： Fuzzy Cognitive Maps

来源：评论

学校读者我要写书评

暂无评论

FedVC: Virtual Clients for Federated Learning with Imbalanced Label Distribution 24

FedVC: Virtual Clients for Federated Learning with Imbalance...

引用

3rd International Conference on Algorithms, Data Mining, and Information Technology, ADMIT 2024

作者： Chen, Zhouguo Chen, Hongda Liu, Shuai Liu, Yongdong Schoolof Computer Science and Engineering Southeast University Jiangsu Nanjing China The 30th Research Institute of China Electronics Technology Group Corporation Sichuan Chengdu China School of Software Engineering Xian Jiaotong University Shaanxi Xian China China Industrial Control Systems Cyber Emergency Response Team Beijing China

ISBN: (纸本)9798400718120

Federated Learning (FL) has gained considerable attention for collaborative training in big data analysis, particularly in terms of privacy and communication constraints. Despite its promising advantages, FL faces the challenge of dealing with imbalanced label distribution on edge devices, which complicates the learning task. In literature, numerous studies have attempted to tackle this issue by introducing additional hyperparameters, which can complicate and prolong the process of model training and tuning. This complexity may potentially lead to overfitting and limited performance on new datasets. In this paper, we present a new Federated Learning framework called FedVC, which introduces virtual clients to minimize hyperparameter reliance. FedVC aims to bridge the gap between balanced and imbalanced label distribution. Compared with traditional federated learning frameworks, the proposed FedVC model designs a dynamically balanced dataset by utilizing virtual clients, which is proposed for the first time in this work. These virtual clients determine which part of the data should be used in one single training round and manage backpropagation timing for local real clients. The balanced dataset promotes greater stability in local models, thereby enhancing the overall stability of the training process. The experimental results show that FedVC outperforms classical FedAvg and the compared baseline methods for the data with imbalanced label distribution. Especially, FedVC exhibits more stable and accurate results than alternative approaches in highly heterogeneous settings. The source code is available at https://***/aikedaerC/FedVC. © 2024 Copyright held by the owner/author(s).

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced wind energy conversion system performance using fast smooth second-order sliding mode control with neuro-fuzzy estimation and variable-gain robust exact output differentiator

引用

Applied Energy 2025年第PartA期377卷

作者： Ullah, Ameen Ullah, Safeer Rahman, Tanzeel Ur Sami, Irfan Rahman, Ata Ur Alghamdi, Baheej Pan, Jianfei College of Mechatronics and Control Engineering Shenzhen University Shenzhen518060 China Department of Electrical Engineering Quaid-e-Azam College of Engineering & Technology Sahiwal57000 Pakistan College of Physics and Optoelectronic Engineering Shenzhen University Shenzhen518060 China School of Electrical and Electronics Engineering Chung-Ang University Dongjak-gu Seoul06974 Korea Republic of Smart Grids Research Group Center of Research Excellence in Renewable Energy and Power Systems King Abdulaziz University Jeddah21589 Saudi Arabia Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia

Wind energy conversion systems (WECS) often face challenges due to the stochastic and intermittent nature of wind, leading to a mismatch between output power generation and fluctuating electrical load requirements. To effectively address this issue, an advanced Maximum Power Point Tracking (MPPT) strategy is crucial for maximizing power extraction. This study introduces a novel MPPT approach based on Fast Smooth Second-Order Sliding Mode control (FSSOSMC) to optimize power output from a 3 kW fixed-pitch variable speed WECS coupled with a permanent magnet synchronous generator (PMSG). To ensure robustness despite uncertain, nonlinear system parameters, an offline neuro-fuzzy algorithm utilizing the Takagi–Sugeno–Kang (TSK) fuzzy inference system is implemented. This method accurately estimates the nonlinear and uncertain components of the control input, enhancing the performance and robustness of the MPPT control techniques. Additionally, a Variable-Gain Robust Exact Output Differentiator (VG-REOD) is employed to accurately estimate the shaft speed, addressing issues related to speed estimation and missing derivative information. The proposed FSSOSMC-based MPPT strategy was benchmarked against super-twisting sliding mode control (STSMC) and feedback linearization control (FBLC) MPPT strategies under stochastic wind speed profiles, parameter variations, and wind speed fluctuations. The results show that the proposed method achieves a tracking accuracy of 98.2% and an overall efficiency of 98.9%, significantly outperforming STSMC (97.1% accuracy, 95.75% efficiency) and FBLC (95.4% accuracy, 93.82% efficiency). The FSSOSMC method also reduced the settling time to 7.879 s and the rise time to 1.062 s, with minimal overshoot of 10.022% and a steady-state error of 0.0015088. These results demonstrate superior tracking performance, high precision, rapid dynamic response, minimal chattering, and robust global performance. The efficacy of the proposed method is validated thro

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Design of Dynamic Experiments (DoDE) to optimize the lutein production by Coccomyxa onubensis in a novel high-cell density reactor

引用

Algal research 2025年 89卷

作者： Tizzani, Rosaria Barberi, Gianmarco Mohamadnia, Sonia Angelidaki, Irini Facco, Pierantonio Sforza, Eleonora BiER Lab (Bioprocess Engineering Research Laboratory) Department of Industrial Engineering University of Padova Via Marzolo 9 Padova 35131 Italy CAPE-Lab (Computer-Aided Process Engineering Laboratory) Department of Industrial Engineering University of Padova via Marzolo 9 Padova 35131 Italy BioCon (Biological Conversion Group) Department of Chemical Engineering Technical University of Denmark DTU Søltofts Plads 228A Lyngby 2800 Denmark

Lutein, a carotenoid involved in light harvesting and photoprotection, has demonstrated significant therapeutic benefits, particularly for ocular health. This study aims to optimize biomass and lutein production from an extremophilic microalga Coccomyxa onubensis in a fed-batch system. C. onubensis was cultivated in a membrane high-cell-density photobioreactor. Design of Dynamic Experiments was employed to optimize dynamic cultivation factors, including time-varying light intensity profiles (80–800 μmol∙ m⁻²∙ s⁻¹), nitrogen feeding strategies (60–600 mg_N∙ L⁻¹), and three constant CO₂ levels (0.04 %, 1 %, and 10 %). Biomass productivity peaked at 1.28 ± 0.23 g∙ L⁻¹∙ d⁻¹ under 6.5 % CO₂, with gradual light increase (peak 800 μmol photons∙ m⁻² ∙ s⁻¹), and moderately high nitrogen (499 mg∙ L⁻¹ over 5 days). Conversely, lutein productivity reached 3.32 ± 0.58 mg∙ L⁻¹∙ d⁻¹ under moderate light intensity (peak 414 μmol photons∙ m⁻²∙ s⁻¹) and limited nitrogen (217 mg_N∙ L⁻¹ over 1 day) under 10 % CO₂. This work provides optimized and validated cultivation strategies for impactful time varying factors, implementable at industrial level. DoDE proved to be valuable tool for multifactorial optimization and interpretation of complex interactions, significantly enhancing biomass and lutein production under acidophilic, high cell density conditions where bacterial contamination can be minimized. © 2025 The Authors

关键词： Acidophilic microalgae Light profile Membrane reactor Nitrogen feeding

来源：评论

学校读者我要写书评

暂无评论

HierDAMap: Towards Universal Domain Adaptive BEV Mapping via Hierarchical Perspective Priors

arXiv

引用

arXiv 2025年

作者： Li, Siyu Cao, Yihong Shi, Hao Zang, Yongsheng He, Xuan Yang, Kailun Li, Zhiyong School of Robotics the National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China Hunan Vanguard Group Corporation Limited Changsha410100 China

The exploration of Bird’s-Eye View (BEV) mapping technology has driven significant innovation in visual perception technology for autonomous driving. BEV mapping models need to be applied to the unlabeled real world, making the study of unsupervised domain adaptation models an essential path. However, research on unsupervised domain adaptation for BEV mapping remains limited and cannot perfectly accommodate all BEV mapping tasks. To address this gap, this paper proposes HierDAMap, a universal and holistic BEV domain adaptation framework with hierarchical perspective priors. Unlike existing research that solely focuses on image-level learning using prior knowledge, this paper explores the guiding role of perspective prior knowledge across three distinct levels: global, sparse, and instance levels. With these priors, HierDA consists of three essential components, including Semantic-Guided Pseudo Supervision (SGPS), Dynamic-Aware Coherence Learning (DACL), and Cross-Domain Frustum Mixing (CDFM). SGPS constrains the cross-domain consistency of perspective feature distribution through pseudo labels generated by vision foundation models in 2D space. To mitigate feature distribution discrepancies caused by spatial variations, DACL employs uncertainty-aware predicted depth as an intermediary to derive dynamic BEV labels from perspective pseudo-labels, thereby constraining the coarse BEV features derived from corresponding perspective features. CDFM, on the other hand, leverages perspective masks of view frustum to mix multi-view perspective images from both domains, which guides cross-domain view transformation and encoding learning through mixed BEV labels. Furthermore, this paper introduces intra-domain feature exchange data augmentation to enhance the efficiency of domain adaptation learning. The proposed method is verified on multiple BEV mapping tasks, such as BEV semantic segmentation, high-definition semantic, and vectorized mapping. It demonstrates competitive perfo

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Pinching Antennas: Principles, Applications and Challenges

arXiv

引用

arXiv 2025年

作者： Yang, Zheng Wang, Ning Sun, Yanshi Ding, Zhiguo Schober, Robert Karagiannidis, George K. Wong, Vincent W.S. Dobre, Octavia A. Fujian Provincial Engineering Technology Research Center of Photoelectric Sensing Application Fujian Normal University Fuzhou350117 China School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Khalifa University Abu Dhabi United Arab Emirates University of Manchester ManchesterM1 9BB United Kingdom Germany Group Electrical & Computer Engineering Dept. Aristotle University of Thessaloniki Thessaloniki54 124 Greece Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada Department of Electrical and Computer Engineering Memorial University St. John’sNL Canada

Flexible-antenna systems, such as fluid antennas and movable antennas, have been recognized as key enabling technologies for sixth-generation (6G) wireless networks, as they can intelligently reconfigure the effective channel gains of the users and hence significantly improve their data transmission capabilities. However, existing flexible-antenna systems have been designed to combat small-scale fading in non-line-of-sight (NLoS) conditions. As a result, they lack the ability to establish line-of-sight links, which are typically 100 times stronger than NLoS links. In addition, existing flexible-antenna systems have limited flexibility, where adding/removing an antenna is not straightforward. This article introduces an innovative flexible-antenna system called pinching antennas, which are realized by applying small dielectric particles to waveguides. We first describe the basics of pinching-antenna systems and their ability to provide strong LoS links by deploying pinching antennas close to the users as well as their capability to scale up/down the antenna system. We then focus on communication scenarios with different numbers of waveguides and pinching antennas, where innovative approaches to implement multiple-input multiple-output and non-orthogonal multiple access are discussed. In addition, promising 6G-related applications of pinching antennas, including integrated sensing and communication and next-generation multiple access, are presented. Finally, important directions for future research, such as waveguide deployment and channel estimation, are highlighted. Copyright © 2025, The Authors. All rights reserved.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

computer-aided-DESIGN OF AN N-MOS CUSTOM IC-SUBSCRIBER CHIP OF THE 32-LINES MICROPROCESSOR BASED PAX (PRIVATE AUTOMATIC EXCHANGE) SYSTEM

引用

MICROELECTRONICS AND RELIABILITY 1985年第3期25卷 425-436页

作者： SRIVASTAVA, A SINGH, S PAVATE, KD Computer-Aided Design Group Central Electronics Engineering Research Institute Extension Centre CSIR Complex Hillside Road New Delhi-110012 India

A 40-pin custom IC-“Subscriber Chip” of the subscriber module of the Intel 8085A microprocessor based PAX system (32P 4 -32 lines and four parallel conversations) has been designed using CAD techniques. The chip design is based on the LOCOS n -MOS(E-D) process, 8 micron minimum feature size geometries, λ-based design rules and the cell based design approach. DIF-POL contact for the gate-source interconnection of the depletion load transistors has been made with the buried contacts. System routing has been done on two layers: metal and polysilicon/diffusion. Single metal layer has been used for power and ground routing having interdigitated structure. Chip has also been designed for its testability analysis based on the chip partioning approach. Two phases of the testing have been evolved and the test pattern generation sequences got fully integrated with the chip layout. Latest CAD techniques: Applicon AGS/860 VLSI Interactive Graphics Design System, MOS circuit simulation program MSINC and Design Rule Check program (DRC) have been used for the design and chip layout. The entire chip has been laid-out in the area of 3.35 × 3.35 mm 2 integrating around 500 components including test devices and structures for the evaluation of devices and process parameters. The Electromask pattern generation (PG) tape has been prepared for making chrome masks. A set of eight masks are to be used in the fabrication of the chip and encapsulated in 40 pin LSI package. The subscriber chip makes the PAX system design simple and reliable.

关键词： INTEGRATED CIRCUITS, LSI

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

Further developments in output structural controllability and an assessment of structural techniques

引用

Journal of Process control 1991年第5期1卷 283-292页

作者： Lin, X. Newell, R.B. Computer Aided Process Engineering Research Group Department of Chemical Engineering The University of Queensland QLD 4072 Australia

Modifications have been made to the technique of output structural controllability to overcome some limitations of this useful technique. A critical assessment of the usefulness of various structural controllability t... 详细信息

关键词： control structural controllability synthesis

来源：评论

学校读者我要写书评

暂无评论

Simulator based driver categorization and linear model identification

引用

IFAC-PapersOnLine 2016年第3期49卷 255-260页

作者： Mihály, András Gáspár, Péter Institute for Computer Science and Control Hungarian Academy of Sciences and MTA-BME Control Engineering Research Group Budapest Hungary

The paper proposes a classification method for different driver behaviors based on an identification method. The categorization and identification is carried out on real-time driving simulator experiments with several test drivers. The purpose of the identification is to define typical driving behaviors with their identified models. The driving assistant systems of the vehicle can be adapted to the behavior of the driver using predefined driver models. © 2016

关键词： Classification methods Driver behavior Driver models Driving assistant systems Driving behavior Identification method Linear modeling Test drivers

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：