检索结果-内蒙古大学图书馆

ASME 2024 43rd International Conference on Ocean, Offshore and Arctic engineering, OMAE 2024

作者： Glasspool, Jonathan Tao, Longbin Venugopal, Vengatesan Pillai, Ajit C. School of Engineering The University of Edinburgh United Kingdom Department of Naval Architecture Ocean and Marine Engineering Faculty of Engineering University of Strathclyde United Kingdom Institute for Energy Systems School of Engineering The University of Edinburgh United Kingdom Renewable Energy Group Faculty of Environment Science and Economy University of Exeter United Kingdom

ISBN: (纸本)9780791887851

The mooring system of a floating offshore wind turbine (FOWT) impacts both the capital and operational expenses. The future success of floating offshore wind is, therefore, dependent on finding optimum mooring system designs from the wide field of possibilities. This paper introduces a methodology to identify appropriate mooring systems with the lowest cost using Arven Offshore Wind Farm as a case study. The methodology employs a systematic screening pipeline, utilizing short-duration time domain simulations in OrcaFlex to assess mooring line systems’ suitability based on DNV-ST-0437 and DNV-ST-0119 compliant load cases. Through progressively more detailed simulations, the pipeline efficiently narrows down the field of mooring configurations, assessing design parameters in one tenth of the time of a full enumeration. This approach allows for the identification of a lowest-cost mooring system, highlighting the design trade-offs between cost and key design parameters. For the Arven case study, the methodology has identified a semi-taut three-line nylon system with 225 m anchor radius, 1200 kN pretension and a 192 mm line diameter as being the most efficient system. The outlined methodology provides a broadly applicable and efficient means to identify optimum mooring systems for diverse development sites worldwide. Copyright © 2024 by ASME.

关键词： Mooring

来源：评论

学校读者我要写书评

暂无评论

Temporal-Aware Lightweight Visual Tracking Method for Dynamic Traffic Scenes

Temporal-Aware Lightweight Visual Tracking Method for Dynami...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Xuming Cen Nan Hu Haozhe Wang Shiyi Liu School of Electrical and Control Engineering Shenyang Jianzhu University Shenyang China Department of Computer Science Faculty of Environment Science and Economy University of Exeter Exeter UK

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

In traffic-based tracking scenes, acknowledging category diversity and visual field motion is pivotal. This leads tracking models to prioritize multi-category feature learning, motion analysis, and extended time series modeling rather than singularly focusing on attribute acquisition and background modeling. With this goal in mind, we construct a tracking model by integrating re-identification branches into a lightweight detection model. Simultaneously, we establish an inter-frame spatio-temporal attention mechanism using the Feature Transfer Module. This mechanism aligns the current frame features with the corresponding local features of the previous frame, which can bolster feature representation and downstream task performance. Experimental results on the traffic dataset validate the efficacy of the proposed approach in addressing challenges such as occlusion and deformation within traffic scenes. The proposed method attains a significant 31.5 MOTA and 35.7 AP on the BDD100K dataset with random data selection.

关键词： Representation learning Analytical models Visualization Privacy Target tracking Time series analysis Security

来源：评论

学校读者我要写书评

暂无评论

Towards Combating Frequency Simplicity-biased Learning for Domain Generalization 38

Towards Combating Frequency Simplicity-biased Learning for D...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： He, Xilin Hu, Jingyu Lin, Qinliang Luo, Cheng Xie, Weicheng Song, Siyang Khan, Muhammad Haris Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Provincial Key Laboratory of Intelligent Information Processing China University of Exeter United Kingdom Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

Domain generalization methods aim to learn transferable knowledge from source domains that can generalize well to unseen target domains. Recent studies show that neural networks frequently suffer from a simplicity-biased learning behavior which leads to over-reliance on specific frequency sets, namely as frequency shortcuts, instead of semantic information, resulting in poor generalization performance. Despite previous data augmentation techniques successfully enhancing generalization performances, they intend to apply more frequency shortcuts, thereby causing hallucinations of generalization improvement. In this paper, we aim to prevent such learning behavior of applying frequency shortcuts from a data-driven perspective. Given the theoretical justification of models' biased learning behavior on different spatial frequency components, which is based on the dataset frequency properties, we argue that the learning behavior on various frequency components could be manipulated by changing the dataset statistical structure in the Fourier domain. Intuitively, as frequency shortcuts are hidden in the dominant and highly dependent frequencies of dataset structure, dynamically perturbating the over-reliance frequency components could prevent the application of frequency shortcuts. To this end, we propose two effective data augmentation modules designed to collaboratively and adaptively adjust the frequency characteristic of the dataset, aiming to dynamically influence the learning behavior of the model and ultimately serving as a strategy to mitigate shortcut learning. Code is available at AdvFrequency. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recovering Packet Collisions below the Noise Floor in Multi-gateway LoRa Networks

Recovering Packet Collisions below the Noise Floor in Multi-...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Wenliang Mao Zhiwei Zhao Kaiwen Zheng Geyong Min School of Computer Science and Engineering University of Electronic Science and Technology of China China Department of Computer Science University of Exeter UK

LoRa has been widely applied in various vertical areas such as smart grids, smart cities, etc. Packet collisions caused by concurrent transmissions have become one of the major limitations of LoRa networks due to the ALOHA MAC protocol and dense deployment. The existing studies on packet recovery usually assume that the collided packet signals are above the noise floor. However, considering the large-scale deployment and low-power nature of LoRa communications, many collided packets are below the noise floor. Consequently, the existing schemes will suffer from significant performance degradation in practical LoRa networks. To address this issue, we propose CPR, a Cooperative Packet Recovery mechanism aiming at recovering the collided packets below the noise floor. CPR firstly employs the incoherence of signals and noises at multiple gateways to detect and extract the frequency features of the collided packets hidden in the noise. Then, CPR adopts a novel gateway selection strategy to select the most appropriate gateways based on their packet power domain features extracted from collision detection, such that the interference can be eliminated and the original packets can be recovered. Extensive experimental results demonstrate that CPR can significantly increase the symbol recovery ratio in low-SNR scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimised Mission Planning for Heterogeneous Uncrewed Vehicle Teams

引用

IEEE Access 2024年 1-1页

作者： Hajkarim, Sina M.H. Sujit, P.B. Menon, Prathyush P. Department of Engineering Faculty of Environment Science and Economy University of Exeter Exeter United Kingdom Department of Electrical Engineering and Computer Science Indian Institute of Science Education and Research Bhopal Bhopal Bypass Road Bhopal Madhya Pradesh India

In this paper, we present a new mission planning optimisation method for coverage missions involving Uncrewed Aerial Systems (UAS) and Ground Vehicles (GV) to minimize the mission planning time and the UAS and GV route length. Optimal planning of paths for the UAS and GV using the Mixed Integer Linear Program (MILP), often struggles with computational inefficiency and limited scalability in scenarios with a growing number of waypoints and vehicles. To overcome the MILP computational issues, we present a reinforcement learning technique based on rollout policy optimisation called as Multi-Agent Rollout Policy Optimisation (MARPO). Through simulations, we showcase MARPO’s ability to match the precision of conventional MILP formulation in small instances and excel in scalability and computational efficiency in larger cases. Additionally, MARPO is compared with a heuristic method, Multi-Agent Greedy Path-Finding Algorithm (MAGPA), and the superior performance of MARPO in terms of total path length and computational efficiency is demonstrated. Several simulations are presented to showcase the advantages of MARPO. In simulations with 1 UAS and 1 UGV, MARPO achieved path lengths up to 1.56% longer than MILP’s optimum for 9 to 25 waypoints, while significantly reducing computation time by up to 99.88%. In larger scenarios of 36 and 49 waypoints, where MILP was infeasible, MARPO provided convincing solutions with greatly enhanced computational efficiency, demonstrating its robust scalability and effectiveness. Authors

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Reliable and Energy-Efficient Reprogramming for Smart LoRaWAN

Reliable and Energy-Efficient Reprogramming for Smart LoRaWA...

引用

Smart World Congress (SWC), IEEE

作者： Wenliang Mao Zhiwei Zhao Mengyu Kang Rong Cong Geyong Min Zheng Chang Xiong Wang School of Computer Science and Engineering University of Electronic Science and Technology of China China Department of Computer Science University of Exeter UK

As a promising low-power wide-area network communication technology, Long Range Wide Area Networks (LoRaWAN) have been widely adopted by smart applications, such as smart metering, smart grids and smart cities. In these applications, massive deployed end devices demand reprogramming with the latest standards and preventing security vulnerabilities through their life cycle, which makes reprogramming a crucial issue. The existing reprogramming scheme in LoRaWAN, called LoRaWAN firmware update over-the-air (FUOTA), suffers from inefficient firmware dissemination and computation-intensive coding. Moreover, considering the topology difference and unique physical layer parameters (e.g., spreading factors) of LoRaWAN, classical reprogramming schemes in wireless sensor networks are not suitable for LoRaWAN. To address this challenge, we propose a reprogramming scheme called DAU (Divide And Upgrade) for LoRaWAN. To ensure reliability, we exploit the channel activity detection (CAD) technique to effectively detect negative acknowledgments (NACKs) from devices and use a lightweight coding scheme to reduce computing and storage overhead. Besides, devices are divided into groups using different spreading factors (SFs) to reduce network energy consumption. To further reduce the setup time of reprogramming, we leverage the beacons of LoRaWAN to quickly disseminate the meta-data of firmware to devices participating in the reprogramming. Extensive experimental results based on outdoor testbed demonstrate that DAU can significantly reduce energy consumption compared to FUOTA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Disturbance Rejection Attitude Control of Quadrotor UAVs Based on Improved BAS Algorithm

Disturbance Rejection Attitude Control of Quadrotor UAVs Bas...

引用

IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems

作者： Fanke Yang Xiangyuan Jiang Jin Li Chunbo Luo Sile Ma School of Institute of Marine Science and Technology Shandong University Qingdao China School of Department of Computer Science University of Exeter Exeter U.K.

This research focuses on achieving rapid and stable control of quadrotor unmanned aerial ve-hicles' (UAVs) attitude using an Active Disturbance Rejection Controller (ADRC). To tackle the challenge of numerous and complex ADRC parameters, optimization algorithms are employed for parameter tuning. We introduce a variable step-size search mechanism based on the Beetle Antennae Search algorithm (BAS) and leverage the Sine Cosine Algorithm (SCA) for pre-search. The parameter tuning results reveal that the refined optimization algorithm displays superior global optimization capability, convergence rate, and stability. Both simulation and experimental outcomes suggest that the ADRC controller with optimized parameters exhibits remarkable control and anti-disturbance performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Resource Allocation for IRS-Aided VLC Network with Energy Harvesting

Joint Resource Allocation for IRS-Aided VLC Network with Ene...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Ding Yao Zheng Chang Geyong Min School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Faculty of Information Technology University of Jyvaskyla Jyvaskyla Finland Department of Computer Science University of Exeter Exeter U.K.

To satisfy the explosive growing traffic demands for high-speed service, visible light communication (VLC) has become a promising technology these years. This paper presents a novel intelligent reflective surface (IRS)-aided VLC network system, which takes into account the existence of both information users (IUs) for receiving data information and energy harvesting users (EHUs) for capturing light energy. We determine the IRS association, power allocation, as well as direct current (DC) offset distribution to maximize the sum rate at the IUs, subject to the energy constraints at EHUs. As a solution to such a complex non-convex optimization problem, we propose a two-stage alternating optimization algorithm by decomposing it into two subproblems, with each subproblem being solved iteratively. We solve the subproblem of IRS association with a heuristic method and tackle another subproblem of power allocation and DC offset distribution with a successive convex approximation (SCA)-based algorithm. Based on our numerical results, we conclude that the proposed algorithm is convergent, and a significant improvement in sum rate can be achieved by joint resource management while meeting certain requirement of harvesting energy. Moreover, IRS can reduce the sensitivity to obstacles and improve sum rate performance in VLC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Multimodal Decoupling-Fusion Framework for offline Multiple Appropriate Facial Reaction Generation

Hierarchical Multimodal Decoupling-Fusion Framework for offl...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Qincheng Lv Xiaofeng Liu Jie Li Rongrong Ni Pujun Xue Siyang Song College of Information Science and Engineering Hohai University Changzhou China College of Artificial Intelligence and Automation Hohai University Changzhou China School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing China School of Microelectronics and Control Engineering Changzhou University Changzhou China School of Computer Science University of Exeter Exeter U.K.

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Facial reactions convey crucial emotional information and coordinating interpersonal relationships in human dyadic interactions. While existing Multiple Appropriate Facial Reaction Generation (MAFRG) methods focus on generating multiple reasonable facial reactions, none of these approaches combines 2D and 3D facial behaviour information nor account for the influence of individuals’ facial identities, leading to inconsistencies in the generated facial reactions and limited capability in capturing subtle variations in facial depth and expression dynamics. This paper proposes a novel Hierarchical Multimodal Decoupling-Fusion (HMDF) framework that decouples 3D facial identity from expression behaviors, eliminating identity-based interference in the reaction generation process, which are integrated with audio-visual features through a cross-attention mechanism. Experiments show that our framework achieved the enhanced diversity and synchrony in the generated facial reactions.

关键词： Three-dimensional displays Interference Signal processing Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

An adaptive stacked hourglass network with Kalman filter for estimating 2D human pose in video

An adaptive stacked hourglass network with Kalman filter for...

引用

作者： Hu, Tao Xiao, Chunxia Min, Geyong Najjari, Noushin School of Computer Science Wuhan University Wuhan China School of Information Engineering Hubei Minzu University Enshi China College of Engineering Mathematics and Physical Science University of Exeter Exeter United Kingdom

One of the main challenges in computer science and image processing is 2D human pose estimation. Specifically, occlusion and in particular occlusion of human joints caused by camera angle are of paramount importance. In this paper, a new highly accurate network was proposed that can estimate 2D human poses in video images using deep learning. We employ the Single Shot MultiBox Detector network to detect the centre position of each human within a video frame and then use the stacked hourglass network to estimate the 2D human pose. We approximate the human motion as a linear motion between different frames in a certain period;and optimize the human centres based on the local outlier factor and Kalman filters. The same method is applied to optimize the human pose estimations in video, which can address the inaccurate prediction caused by human joints occlusion. The proposed adaptive network is tested using the two well-known benchmarks for human pose estimation (MPII and Joint-annotated Human Motion Data Base datasets), and we also generate some 2D human pose estimating qualitative results of single and multiple people in Internet videos. The experimental results show that the proposed network has strong practicability and can achieve high accuracy on adaptive estimating the 2D human pose in video. © 2020 John Wiley & Sons, Ltd

关键词： Kalman filters

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：