检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Choi, Wonhyeok Shin, Mingyu Lee, Hyukzae Cho, Jaehoon Park, Jaehyeon Im, Sunghoon The Department of Electrical Engineering & Computer Science DGIST Daegu Korea Republic of The Department of Interdisciplinary Studies of Atrificial Intelligence DGIST Daegu Korea Republic of The Autonomous Driving Center Hyundai Motor Company Seoul Korea Republic of

Real-time processing is crucial in autonomous driving systems due to the imperative of instantaneous decision-making and rapid response. In real-world scenarios, autonomous vehicles are continuously tasked with interpreting their surroundings, analyzing intricate sensor data, and making decisions within split seconds to ensure safety through numerous computer vision tasks. In this paper, we present a new real-time multi-task network adept at three vital autonomous driving tasks: monocular 3D object detection, semantic segmentation, and dense depth estimation. To counter the challenge of negative transfer — the prevalent issue in multi-task learning — we introduce a task-adaptive attention generator. This generator is designed to automatically discern interrelations across the three tasks and arrange the task-sharing pattern, all while leveraging the efficiency of the hard-parameter sharing approach. To the best of our knowledge, the proposed model is pioneering in its capability to concurrently handle multiple tasks, notably 3D object detection, while maintaining real-time processing speeds. Our rigorously optimized network, when tested on the Cityscapes-3D datasets, consistently outperforms various baseline models. Moreover, an in-depth ablation study substantiates the efficacy of the methodologies integrated into our framework. © 2024, CC BY-NC-SA.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multi-view Inspection of Flare Stacks Operation Using a Vision-controlled autonomous UAV

Multi-view Inspection of Flare Stacks Operation Using a Visi...

引用

Annual Conference of Industrial Electronics Society

作者： Muaz Al Radi Pengfei Li Hamad Karki Naoufel Werghi Sajid Javed Jorge Dias Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi UAE Center for Autonomous Robotic Systems Khalifa University Abu Dhabi UAE Department of Mechanical Engineering Khalifa University Abu Dhabi UAE

Flare stacks are crucial safety control components in petrochemical plants that required efficient monitoring and inspection. In this work, an Unmanned Aerial Vehicle (UAV)-based multi-view operation inspection system for monitoring and assessing the operation of flare stacks is proposed. Image-Based Visual Servoing (IBVS) control is used to guide the autonomous UAV for multi-view visual data collection. Afterwards, the collected visual data is analyzed using a new Multi-View Convolutional Neural Network (MV-CNN) deep learning model to obtain useful conclusions on the system's operation and classify the current state of the observed system. The proposed system's performance was validated in a simulated petrochemical plant environment with operational flare stacks and the results showed superior performance of the proposed MV-CNN model compared to a conventional single-view CNN model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation for Blockchain-Enabled Fog Computing with Deep Reinforcement Learning 22

Resource Allocation for Blockchain-Enabled Fog Computing wit...

引用

Proceedings of the 2022 12th International Conference on Communication and Network Security

作者： Yihe Zhang Shanshan Tu Muhammad Waqas Yongjie Yang Aiming Wu Xuetao Bai Engineering Research Center of Intelligent Perception and Autonomous Control faculty of Information Technology Beijing University of Technology China Computer Engineering Department College of Information Technology University of Bahrain Bahrain and School of Engineering Edith Cowan University Australia

ISBN: (纸本)9781450397520

With the developments of the Internet of Things, the demands of low latency, high bandwidth and high-performance computing has increased higher. Therefore, the distributed computing named Fog Computing has proposed to solve the problem above. Fog computing can provide lower transmission latency, faster response time and less network congestion. However, the fog devices are unable to guarantee the security and privacy of data transmission, due to they are vulnerable to attack. Blockchain technology works as a decentralized public ledger to store and share transactions. Blockchain can improve security and protect data privacy of Fog Computing. Moreover, there are still issues in the blockchain-enabled Fog Computing, the two main issues are the energy consumption and computing efficiency. Thus, in this paper, we propose an optimization framework for blockchain-enabled Fog Computing systems to optimize resource allocation. Besides, we adopt the dueling deep reinforcement learning to obtain the optimal resource allocation strategy, with dynamically selecting the fog server, offloading decision, block size. Simulation results show that the proposed framework can reduce the energy consumption and computation overhead of the system, as well as can improve the computing efficiency.

关键词： Fog Computing Deep Reinforcement Learning Blockchain Internet of things

来源：评论

学校读者我要写书评

暂无评论

On the Effect of Quantization on Dynamic Mode Decomposition

On the Effect of Quantization on Dynamic Mode Decomposition

引用

IEEE Conference on Decision and control

作者： Dipankar Maity Debdipta Goswami Sriram Narayanan Department of Electrical and Computer Engineering an affiliated faculty of the North Carolina Battery Complexity Autonomous Vehicle and Electrification Research Center (BATT CAVE) University of North Carolina at Charlotte NC USA Department of Mechanical and Aerospace Engineering The Ohio State University Columbus OH USA

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

Dynamic Mode Decomposition (DMD) is a widely used data-driven algorithm for estimating the Koopman Operator. This paper investigates how the estimation process is affected when the data is quantized. Specifically, we examine the fundamental connection between estimates of the operator obtained from unquantized data and those from quantized data. Furthermore, using the law of large numbers, we demonstrate that, under a large data regime, the quantized estimate can be considered a regularized version of the unquantized estimate. This key theoretical finding paves the way to accurately recover the unquantized estimate from quantized data. We also explore the relationship between the two estimates in the finite data regime. The theory is validated through repeated numerical experiments conducted on three different dynamical systems.

关键词： Quantization (signal) Heuristic algorithms Estimation Dynamical systems Optimization

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Analytics of Flare Stacks Using Deep Learning Detection

Vision-Based Analytics of Flare Stacks Using Deep Learning D...

引用

International Conference on Advanced Robotics (ICAR)

作者： Muaz Al Radi Said Boumaraf Hamad Karki Jorge Dias Naoufel Werghi Sajid Javed Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi UAE Center for Autonomous Robotic Systems Khalifa University Abu Dhabi UAE Department of Mechanical Engineering Khalifa University Abu Dhabi UAE

Flare stacks play a critical role in oil refineries and chemical plants, but monitoring their performance is a challenging task that often requires skilled operators. To address this challenge, we propose a novel approach that combines video capturing and machine learning techniques to automate the monitoring of flare stack operations in real-time. Our vision-based system analyzes captured video footage of the flare stack's scene and employs state-of-the-art deep learning detection models, including YOLOv5, YOLOv7, and the Detection Transformer (DETR), to detect and analyze combustion-related objects such as flame and smoke. Rigorous experiments show that the proposed technique was able to accurately detect flame and smoke objects in flare stacks scene and the best model showed encouraging performance metrics. By leveraging the power of recent deep detection models, our proposed system offers a promising alternative to labor-intensive manual inspection by keeping a continuous and automated watchable eye in combustion quality, facilitating more efficient and reliable flare stack operation analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Voltage Stability for DC Microgrids Integrating Hybrid Electric Vehicles with Virtual Inertia and Damping control

引用

Transportation Research Procedia 2025年 84卷 571-578页

作者： Hossam Ali Mohamed Zaery Syed Muhammad Amrr S.M. Suhail Hussain Vijay Vital Mohammad A. Abido Department of Electrical Engineering Faculty of Energy Engineering Aswan University 81528 Aswan Egypt School of Electrical Computer and Energy Engineering Arizona State University Tempe AZ 85281 USA K.A.CARE Energy Research & Innovation Center King Fahd University of Petroleum and Minerals (KFUPM) Dhahran 31261 Saudi Arabia Control & Instrumentation Engineering Department KFUPM Dhahran 31261 Saudi Arabia Interdisciplinary Research Center for Sustainable Energy Systems KFUPM Dhahran 31261 Saudi Arabia Electrical Engineering Department King Fahd University of Petroleum and Minerals Dhahran 31261 Saudi Arabia SDAIA-KFUPM Joint Research Center for Artificial Intelligence KFUPM Dhahran 31261 Saudi Arabia

DC microgrids (MGs) have experienced swift growth, driven by the expanding integration of energy storage devices(ESD), renewable energy sources (RESs), and localized loads. However, it suffers from insufficient inertia owing to less rotating mass sources, which can lead to poor voltage stability. This paper introduces a control method that emulates both inertia and damping to mitigate fluctuations in DC voltage, enhance system stability, and address the low inertia concern. The proposed virtual inertia and damping (VID) control system is adopted through using hybrid electric vehicle (HEV). The suggested HEV comprises three power sources: a battery, a fuel cell (FC), and a supercapacitor (SC). In this setup, both the battery and the FC are employed to supply virtual damping owing to their high-energy density, and the SC is utilized to support virtual inertial characteristics due to its high-power density. Through this approach, enhancements in the DC voltage stability of an islanded DC MG can be achieved. Simulations demonstrate that the proposed control system significantly outperforms existing works utilizing virtual inertia (VI) based on an EV’s battery only, as well as over systems lacking VI. The proposed control system effectively reduces voltage fluctuations and improves system stability, specifically in terms of the rate of change of voltage (ROCOV) and accelerated settling time.

关键词： Voltage Stability DC Microgrids Virtual Inertia Damping Hybrid Electric Vehicle Renewable Energy Sources

来源：评论

学校读者我要写书评

暂无评论

Privacy-Aware Joint DNN Model Deployment and Partition Optimization for Delay-Efficient Collaborative Edge Inference

arXiv

引用

arXiv 2025年

作者： Cheng, Zhipeng Xia, Xiaoyu Wang, Hong Liwang, Minghui Chen, Ning Fan, Xuwei Wang, Xianbin School of Future Science and Engineering Soochow University Suzhou215006 China School of Computing Technologies RMIT University MelbourneVIC Australia Department of Control Science and Engineering The National Key Laboratory of Autonomous Intelligent Unmanned Systems Tongji University Shanghai201804 China Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Tongji University Shanghai201804 China Qingdao China College of Computer and Information Sciences Fujian Agriculture and Forestry University Fuzhou350002 China Department of Electrical and Computer Engineering Western University ON Canada

Edge inference (EI) is a key solution to address the growing challenges of delayed response times, limited scalability, and privacy concerns in cloud-based Deep Neural Network (DNN) inference. However, deploying DNN models on resource-constrained edge devices faces more severe challenges, such as model storage limitations, dynamic service requests, and privacy risks. This paper proposes a novel framework for privacy-aware joint DNN model deployment and partition optimization to minimize long-term average inference delay under resource and privacy constraints. Specifically, the problem is formulated as a complex optimization problem considering model deployment, user-server association, and model partition strategies. To handle the NP-hardness and future uncertainties, a Lyapunov-based approach is introduced to transform the long-term optimization into a single-time-slot problem, ensuring system performance. Additionally, a coalition formation game model is proposed for edge server association, and a greedy-based algorithm is developed for model deployment within each coalition to efficiently solve the problem. Extensive simulations show that the proposed algorithms effectively reduce inference delay while satisfying privacy constraints, outperforming baseline approaches in various scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

SpaceCube GHOST: A Resilient Processor for Low-Power, High-Reliability Space Computing

SpaceCube GHOST: A Resilient Processor for Low-Power, High-R...

引用

IEEE Conference on Aerospace

作者： Noah Perryman Nicholas Franconi Gary Crum Christopher Wilson Alan D. George Department of Electrical and Computer Engineering NSF Center for Space High-Performance and Resilient Computing (SHREC) University of Pittsburgh Pittsburgh PA Science Data Processing Branch Code 587 Software Engineering Division NASA Goddard Space Flight Center Greenbelt MD

There is a direct need for high-visibility nasa missions that provide significant scientific impact or have a high mission class using completely radiation-hardened (rad-hard) electronics solutions, to enable artificial intelligence (AI) applications in harsh environments despite severe size, weight, and power (SWaP) constraints. For these missions, where current state-of-the-art solutions are too power-demanding or are incapable of surviving the intended radiation environment, an alternative rad-hard processing architecture that can leverage the control-flow capabilities of scalar processors while also incorporating the hardware-acceleration capabilities of an FPGA is of significant value. Therefore, in this research, we propose a miniaturized (3.5 in. × 3.5 in. form factor) processor card featuring the GR740 quad-core rad-hard processor and the CertusPro-NX-RT radiation-tolerant FPGA, called the SpaceCube GR740 Host for Onboard Science and Telemetry (GHOST) architecture. The card will be designed to conform to the nasa Goddard Space Flight center (GSFC) CubeSat Card Specification (CS2), which provides a common template to build new 1U CubeSat-sized cards compatible with a variety of other avionics designs. The GR740 features a fault-tolerant quad- processor LEON4FT SPARC V8 integer unit with a 7-stage pipeline and 4×4 KiB instruction and data caches. To extend the capabilities of the GR740, the CertusPro-NX-RT, a low-power radiation-tolerant FPGA, was combined to create a hybrid system architecture, providing the benefits of a programmable logic fabric. The GHOST architecture supports high-reliability, general-purpose processing and system monitoring via the GR740 while simultaneously increasing the AI-based application performance via a combination of the GR740 and CertusPro-NX-RT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Urban Digital Twins for Intelligent Road Inspection

Urban Digital Twins for Intelligent Road Inspection

引用

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Fan, Rui Zhang, Yikang Guo, Sicen Li, Jiahang Feng, Yi Su, Shuai Zhang, Yanting Wang, Wenshuo Jiang, Yu Junaid Bocus, Mohammud Zhu, Xingyi Chen, Qijun Department of Control Science & Engineering Frontiers Science Center for Intelligent Autonomous Systems State Key Laboratory of Intelligent Autonomous Systems Shanghai201804 China Donghua University Department of Computer Science & Technology Shanghai201620 China McGill University Department of Civil Engineering MontrealH3A 0C3 Canada Cto Office at ClearMotion BillericaMA01821 United States University of Bristol Department of Electrical & Electronic Engineering BristolBS8 1UB United Kingdom Tongji University Key Laboratory of Road and Traffic Engineering Ministry of Education Shanghai200092 China

ISBN: (纸本)9781665480451

Urban digital twin (UDT) technologies offer new opportunities for intelligent road inspection (IRI). This paper first reviews the state-of-the-art algorithms used in the two key components of UDT-based IRI systems: (1) multi-temporal, multi-dimension, multi-score, and heterogeneous road data acquisition, and (2) road distress detection. This paper then summarizes the UDTIRI competition, organized in conjunction with IEEE Bigdata 2022. More details on our competition are available at ***/view/udtiri-workshop/bigdata-2022. © 2022 IEEE.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization Air Base Stations Deployment and User Association in Heterogeneous Space-Air-Ground Integrated Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Ao, Shaoyou Niu, Yong Han, Zhu Xiong, Lei Wang, Ning Ai, Bo Beijing Jiaotong University Beijing Engineering Research Center of High-speed Railway Broadband Mobile Communications School of electronic and Information Engineering Beijing100044 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of Beijing Jiaotong University State Key Laboratory of Advanced Rail Autonomous Operation Beijing100044 China Zhengzhou University School of Information Engineering Zhengzhou450001 China

With the development of 6 G and beyond, space-air-ground integrated networks (SAGINs) have evolved into key elements to promote high-speed and seamless connections for users. This paper studies a heterogeneous SAGIN with satellite, multiple unmanned aerial vehicles (UAVs) and high-altitude platforms (HAPs) serve as aerial base stations (ABSs) in a scenario where ground base stations (GBSs) are overloaded. To optimize the number of ABSs within the system's power limit and maximize the system's downlink throughput, we optimize the 3D deployment of ABSs and user association in the millimeter wave (mmWave) frequency band. We formulate an optimization problem to satisfy the access quality of service (QoS) requirements. This problem is a mixed- integer nonlinear programming problem. Therefore, we divide it into two subproblems: the heterogeneous network ABS deployment problem and the user association problem. We propose a Broyden-Fletcher-Goldfarb-Shanno (BFGS) formula based sequential quadratic programming (SQP) algorithm for the ABS deployment problem and a coalition game algorithm for the user association problem. Finally, we employ a block coordinate descent (BCD) algorithm to iteratively solve the two subproblems until convergence. Extensive simulations with various parameters and user deployments demonstrate that our algorithm outperforms other selected schemes. © 1967-2012 IEEE.

关键词： Quadratic programming

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：