检索结果-内蒙古大学图书馆

3rd International Workshop and Challenge on computer Vision in Endoscopy, EndoCV 2021

作者： Hong, Ayoung Lee, Giwan Lee, Hyunseok Seo, Jihyun Yeo, Doyeob Robotics Engineering Convergence Chonnam National University Gwangju Korea Republic of Department of AI Convergence Chonnam National University Gwangju Korea Republic of Daegu-Gyeongbuk Medical Innovation Foundation Daegu Korea Republic of Department of Computer Convergence Software Korea University Sejong Korea Republic of Electronics and Telecommunications Research Institute Daejeon Korea Republic of

Owing to the rapid development of deep learning technologies in recent years, autonomous diagnostic systems are widely used to detect abnormal lesions such as polyps in endoscopic images. However, the image characteristics, such as the contrast and illuminance, vary significantly depending on the center from which the data was acquired;this affects the generalization performance of the diagnostic method. In this paper, we propose an ensemble learning method based on k-fold cross-validation to improve the generalization performance of polyp detection and polyp segmentation in endoscopic images. Weighted box fusion methods were used to ensemble the bounding boxes obtained from each detection model trained for data from each center. The segmentation results of the data center-specific model were averaged to generate the final ensemble mask. We used a Mask R-CNN-based model for both the detection and segmentation tasks. The proposed method achieved a score of 0.7269 on the detection task and 0.7423 ± 0.2839 on the segmentation task in Round 1 of the EndoCV2021 challenge. © 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Allied Power Constraint Optimization and Optimal Beam Tracking Scheme for Mobile mmWave Massive MIMO Communications

TechRxiv

引用

TechRxiv 2021年

作者： Ghosh, Joydev Ra, In-Ho Singh, Saurabh Haci, Hüseyin Al-Utaibi, Khaled A. Sait, Sadiq M. School of Computer Science and Robotics Tomsk Polytechnic University Tomsk Russia School of Computer Information and Communication Engineering Kunsan National University Gunsan Korea Republic of Department of Industrial & Systems Engineering Dongguk University Korea Republic of Department of Electrical and Electronics Engineering Near East University Mersin 10 Turkey Computer Science and Software Engineering Department University of Ha’il Saudi Arabia Department of Computer Engineering King Fahd University of Petroleum & Minerals Dhahran Saudi Arabia

The fifth generation (5G) networks and internet of things (IoT) promise to transform our lives by enabling various new applications from driver-less cars to smart cities. These applications will introduce enormous amount of data traffic and number of connected devices in addition to the current wireless networks. Thus 5G networks require many researches to develop novel telecommunication technologies to accommodate these increase in data traffic and connected devices. In this paper, novel power constraint optimization and optimal beam tracking schemes are proposed for mobile mmWave massive MIMO communications. A recently published novel channel model that is different from other widely used ones is considered. The channel model considers the number of clusters and number of rays within each cluster as varying due to user mobility. The proposed power constraint optimization scheme harmonizes conventional total power constraint (TPC) and uniform power constraint (UPC) schemes into a new one called allied power constraint (APC) that can significantly improve the system performance in 5G networks while achieving fairness among users. TPC and UPC have major drawbacks with respect to fairness and achieving quality-of-service (QoS) for users in dense networks. Thus APC aims to harmonize TPC and UPC by adjusting each antenna element’s constraint to adapt for some power resilience to a specific antenna element, hence proposing an intermediate solution between the two extreme case power constraint optimization schemes. Three optimal beam tracking schemes: (i) conventional exhaustive search (CES), (ii) multiobjective joint optimization codebook (MJOC), and (iii) linear hybrid combiner (LHS) scheme, have been provided for the mobile mmWave massive MIMO system with the proposed APC scheme. For the proposed APC scheme a comprehensive performance analysis is provided and compared with TPC and UPC. Spectral efficiency (SE), bit-error-rate (BER), Jain’s fairness index, channel occup

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Distributed Energy Optimization for Mobile Networks Using Potential Games

Distributed Energy Optimization for Mobile Networks Using Po...

引用

IEEE Internatonal Conference on Mobile Adhoc and Sensor Systems (MASS)

作者： Zhizongkai Wang Hanfei Wang Zhongji Wang Yilin Xiao Yunzhi Zhao Xiaowen Li Xufeng Chen Lin Gao Fen Hou Jianwei Huang School of Electronics and Information Engineering and the Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Harbin Institute of Technology Shenzhen Guangdong P.R. China School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network and CSIJRI Joint Research Centre on Smart Energy Storage The Chinese University of Hong Kong Shenzhen Guangdong P.R. China Department of Electrical and Computer Engineering State Key Laboratory of IoT for Smart City University of Macau Macau SAR P.R. China Huawei Technologies P.R. China

ISBN: (数字)9798350363999

ISBN: (纸本)9798350364002

The rapid advancement of information and communication technology (ICT) has made the industry a significant contributor to global carbon emissions. As the foundation of ICT, next-generation mobile communication networks aim to be more powerful and energy-efficient. However, optimizing energy efficiency in real networks is challenging due to large-scale, multi-layer control variables and the dynamic environment. This paper addresses the energy efficiency optimization problem from a network perspective by controlling cross-layer variables including both cell activation status and cell priority, to minimize overall network energy consumption while ensuring user quality-of-experience, which poses an NP-hard mixed-integer nonlinear programming problem. To tackle this, we propose a non-cooperative game where each cell acts as a player, optimizing its activation status and reference signal transmission power (determining its priority). We show that the game is a potential game, guaranteeing the existence of Nash equilibrium and the convergence of simple distributed algorithms towards Nash equilibrium. We further show that the Nash equilibrium points of the game can (but not always) reach the global optimal energy efficiency. Simulation results show that our proposed method can reduce the total system cost (including both energy consumption cost and user experience loss) by up to 28% compared to existing methods in the literature. Moreover, the performance loss of our proposed method, compared to the global optimal solution, is less than 13.7%. In summary, this work offers a realistic network model, introduces a novel game-based method, and provides extensive performance evaluation, making a significant contribution to both industry and academia.

关键词： Industries Energy consumption Costs Simulation Games Nash equilibrium Energy efficiency Information and communication technology Distributed algorithms Optimization

来源：评论

学校读者我要写书评

暂无评论

Socially-optimal mechanism design for incentivized online learning

arXiv

引用

arXiv 2021年

作者： Wang, Zhiyuan Gao, Lin Huang, Jianwei School of Computer Science and Engineering Beihang University Beijing China School of Electronics and Information Engineering Harbin Institute of Technology Shenzhen China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

Multi-arm bandit (MAB) is a classic online learning framework that studies the sequential decision-making in an uncertain environment. The MAB framework, however, overlooks the scenario where the decision-maker cannot take actions (e.g., pulling arms) directly. It is a practically important scenario in many applications such as spectrum sharing, crowdsensing, and edge computing. In these applications, the decision-maker would incentivize other selfish agents to carry out desired actions (i.e., pulling arms on the decision-maker's behalf). This paper establishes the incentivized online learning (IOL) framework for this scenario. The key challenge to design the IOL framework lies in the tight coupling of the unknown environment learning and asymmetric information revelation. To address this, we construct a special Lagrangian function based on which we propose a socially-optimal mechanism for the IOL framework. Our mechanism satisfies various desirable properties such as agent fairness, incentive compatibility, and voluntary participation. It achieves the same asymptotic performance as the state-of-art benchmark that requires extra information. Our analysis also unveils the power of crowd in the IOL framework: a larger agent crowd enables our mechanism to approach more closely the theoretical upper bound of social performance. Numerical results demonstrate the advantages of our mechanism in largescale edge computing. © 2021, CC BY.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Development of Unmanned Cargo VTOL Aircraft 1

引用

59th Symposium on engineering Modelling in Mechanics, 2020

作者： Czyba, Roman Gorol, Zbigniew Lemanowicz, Marcin Pawlak, Mariusz Sikora, Adam Faculty of Automatic Control Electronics and Computer Science Department of Automatic Control and Robotics Silesian University of Technology Akademicka Street 2A Gliwice44-100 Poland Faculty of Mechanical Engineering Department of Theoretical and Applied Mechanics Silesian University of Technology Akademicka Street 2A Gliwice44-100 Poland Faculty of Chemistry Department of Chemical Engineering and Process Design Silesian University of Technology Akademicka Street 2A Gliwice44-100 Poland

ISBN: (数字)9783030684556

ISBN: (纸本)9783030684549

The aim of the paper is to present a design cycle regarding to the construction of an unmanned cargo aircraft with own weight up to 25 kg, operating range of up to 100 km and AGL operating ceiling of up to 1 km. The task of the project team was to plan the design cycle, perform analytical calculations and CFD simulations, and finally to build an unmanned aircraft capable of lifting cargo. At the same time, a number of assumptions and technical regulations regarding constructions had to be met, which are specified in legal regulations regarding the given class of unmanned aerial vehicles. In order to achieve optimal UAV aerodynamic properties, including maximization of the payload while minimizing the own weight, aerodynamic calculations and CFD simulations were performed. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Intelligent upper-limb exoskeleton integrated with soft wearable bioelectronics and deep-learning for human intention-driven strength augmentation based on sensory feedback

arXiv

引用

arXiv 2023年

作者： Lee, Jinwoo Kwon, Kangkyu Soltis, Ira Matthews, Jared Lee, Yoon-Jae Kim, Hojoong Romero, Lissette Zavanelli, Nathan Kwon, Youngjin Kwon, Shinjae Lee, Jimin Na, Yewon Lee, Sung Hoon Yu, Ki Jun Shinohara, Minoru Hammond, Frank L. Yeo, Woon-Hong Department of Mechanical Robotics and Energy Engineering Dongguk University Seoul04620 Korea Republic of IEN Center for Human-Centric Interfaces and Engineering Institute for Electronics and Nanotechnology Georgia Institute of Technology AtlantaGA30332 United States School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30332 United States George W. Woodruff School of Mechanical Engineering Georgia Institute of Technology AtlantaGA30332 United States School of Industrial Design Georgia Institute of Technology AtlantaGA30332 United States School of Electrical and Electronic Engineering Yonsei University Seoul03722 Korea Republic of School of Biological Sciences Georgia Institute of Technology AtlantaGA30332 United States Wallace H. Coulter Department of Biomedical Engineering Georgia Institute of Technology and Emory University School of Medicine AtlantaGA30332 United States Institute for Materials Parker H. Petit Institute for Bioengineering and Biosciences Neural Engineering Center Institute for Robotics and Intelligent Machines Georgia Institute of Technology AtlantaGA30332 United States

The age and stroke-associated decline in musculoskeletal strength degrades the ability to perform daily human tasks using the upper extremities. Here, we introduce an intelligent upper-limb exoskeleton system that uses cloud-based deep learning to predict human intention for strength augmentation. The embedded soft wearable sensors provide sensory feedback by collecting real-time muscle signals, which are simultaneously computed to determine the user's intended movement. The cloud-based deep-learning predicts four upper-limb joint motions with an average accuracy of 96.2% at a 500-550 millisecond response rate, suggesting that the exoskeleton operates just by human intention. In addition, an array of soft pneumatics assists the intended movements by providing 897 newton of force while generating displacement of 87 millimeter at maximum. Collectively, the intent-driven exoskeleton can reduce human muscle activities by 3.7 times on average compared to the unassisted *** Codes 68T40 (Primary) 92C55, 68T99 (Secondary) Copyright © 2023, The Authors. All rights reserved.

关键词： Sensory feedback

来源：评论

学校读者我要写书评

暂无评论

Taming time-varying information asymmetry in fresh status acquisition

arXiv

引用

arXiv 2021年

作者： Wang, Zhiyuan Gao, Lin Huang, Jianwei Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong School of Electronics and Information Engineering Harbin Institute of Technology Shenzhen China School of Science and Engineering Chinese University of Hong Kong Shenzhen Hong Kong Shenzhen Institute of Artificial Intelligence and Robotics for Society

Many online platforms are providing valuable real-time contents (e.g., traffic) by continuously acquiring the status of different Points of Interest (PoIs). In status acquisition, it is challenging to determine how frequently a PoI should upload its status to a platform, since they are self-interested with private and possibly time-varying preferences. This paper considers a general multi-period status acquisition system, aiming to maximize the aggregate social welfare and ensure the platform freshness. The freshness is measured by a metric termed age of information. For this goal, we devise a long-term decomposition (LtD) mechanism to resolve the time-varying information asymmetry. The key idea is to construct a virtual social welfare that only depends on the current private information, and then decompose the per-period operation into multiple distributed bidding problems for the PoIs and platforms. The LtD mechanism enables the platforms to achieve a tunable trade-off between payoff maximization and freshness conditions. Moreover, the LtD mechanism retains the same social performance compared to the benchmark with symmetric information and asymptotically ensures the platform freshness conditions. Numerical results based on real-world data show that when the platforms pay more attention to payoff maximization, each PoI still obtains a non-negative payoff in the long-term. © 2021, CC BY.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Silicone Based Capacitive E-Skin Sensor for Soft Surgical Robots 21st

Silicone Based Capacitive E-Skin Sensor for Soft Surgical Ro...

引用

21th Annual Conference on Towards Autonomous robotics, TAROS 20120

作者： Dawood, Abu Bakar Godaba, Hareesh Althoefer, Kaspar Centre for Advanced Robotics @ Queen Mary School of Engineering and Materials Science Queen Mary University of London LondonE1 4NS United Kingdom Centre for Advanced Robotics @ Queen Mary School of Electronics Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom

ISBN: (纸本)9783030634858

In this extended abstract, we present a soft stretchable multi-modal capacitive skin sensor that can be used for exteroception and proprioception in soft surgical manipulators. A soft skin prototype was made using Ecoflex, embedding three conductive carbon grease terminal layers. This soft skin is capable of measuring stretch and touch simultaneously. The soft skin measures uniaxial stretches from 1 to 1.2475 within an error range of 2.6% and can also quantify as well as localize local indentation. An algorithm is developed that decouples local change, i.e., due to indentation, from global strain, due to stretch. An experimental study was conducted;results are presented. © 2020, Springer Nature Switzerland AG.

关键词： Silicones

来源：评论

学校读者我要写书评

暂无评论

Intelligent vehicle collision avoidance system using 5G-enabled drone swarms 2

Intelligent vehicle collision avoidance system using 5G-enab...

引用

2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond, DroneCom 2020

作者： Jacob, Sunil Menon, Varun G. Parvathi, R. Shynu, P.G. Shemim, Fathima K. S. Mahapatra, Bandana Mukherjee, Mithun Centre for Robotics SCMS School of Engineering and Technology India Department of Computer Science and Engineering SCMS School of Engineering and Technology India Department of Electronics and Communication Engineering SCMS School of Engineering and Technology India School of Information Technology and Engineering VIT University Vellore India Department of Computing and IT University of Bolton Ras Al Khaimah United Arab Emirates Department of Data Science Symbiosis Skills and Open University India Guangdong University of Petrochemical Technology Maoming China

ISBN: (纸本)9781450381055

The number of vehicular collisions is on a toll worldwide. Despite enforcing stringent laws and incorporating various safety features, the causalities are still on the rise. Existing techniques such as vision zero strategy and safe system approach provides only postcrash aid. Although numerous works have been carried out on Intelligent Transportation Systems (ITS), a well-coordinated vehicular collision avoidance system is still missing. In this paper, we utilize the tremendous opportunity provided by ITS, Light Detection and Ranging (LIDAR), Wireless Sensor Networks (WSN), 5G, and propose an effective system using drones with swarm intelligence that can automatically control the vehicles to prevent the collision. The proposed method, Bidirectional Multi- Tier IoT drone with Swarm optimization (BMTD-IoT-S) uses intelligent coordination of the drone swarms with the vehicular networks and always ensures a safe distance between the vehicles using the principle of magnetic levitation. The system is further investigated for optimizing the power, altitude, and angular frequency allocation for static and dynamic BMTD-IoT-S'. The results from simulation confirm the excellent performance of the system in ensuring collision avoidance. © 2020 Association for Computing Machinery.

关键词： Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

GRU controller-based UPQC compensator design for improving power quality in grid-integrated non-linear load system

引用

Scientific Reports 2025年第1期15卷 1-28页

作者： B. Srikanth Goud Harish Pulluri Ch. Naga Sai Kalyan Gundala Srinivasa Rao Bhabasis Mohapatra Narsimha Reddy Kuppireddy Ch. Rami Reddy Mohammad Shorfuzzaman Basem Abu Zneid Mukesh Pushkarna Department of Electrical and Electronics Engineering School of Engineering Anurag University Hyderabad 500088 India Department of Electrical and Electronics Engineering Vasireddy Venkatadri International Technological University (VVITU) Guntur 522 508 India Department of Electrical and Electronics Engineering CMR College of Engineering & Technology Hyderabad India Department of Electrical Engineering ITER Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar 751030 Odisha India Department of Electronics and Communication Engineering Vardhaman College of Engineering Hyderabad Telangana India Department of Electrical and Electronics Engineering Joginpally B R Engineering College Hyderabad 500075 India Department of Computer Science College of Computers and Information Technology Taif University Taif 21944 Saudi Arabia Robotics and Artificial Intelligence Engineering Department Faculty of Engineering Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman Jordan Department of Electrical Engineering GLA University Mathura Mathura Uttar Pradesh India

Power quality has prominently gained its importance in power systems with the advancement of technology. Voltage sags/swells, harmonics, and other disturbances are the major issues causing most of the technical and financial damages which are reducing the quality of energy supplied. To overcome these challenges design of a unified power quality conditioner (UPQC) plays a vital role in mitigating the PQ issues. In this paper, an advanced neural network base approach is developed to manage UPQC to maintain a constant power supply for the end users. DC link of UPQC is taken from PV, fuel, and battery at a specific range. The compensator DC link is linked in a smart grid with nonlinear load. On the other hand, the switching pulse was performed with the use of the Gated Recurrent Unit (GRU) controller technique. Various fault conditions are created to make a dataset that is utilized to design the GRU that analyses the load voltage and current at each second to generate a pulse for UPQC. The performance is evaluated utilizing an advanced controller under various conditions, including swell, sag, harmonics, and combined three-phase faults. The low harmonic content of voltage is 0.04%, 0.25%, and 0.98%. The suggested controller is accessible with 99.5% specificity, 99% sensitivity, and 98% accuracy. The proposed controller provides low harmonic content while operating in a highly secure, dependable, and efficient manner.

关键词：

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：