检索结果-内蒙古大学图书馆

Multi-Antenna UAV Assisted Hybrid FSO/RF Data Collection for IoT: Optimal Design for Fairness

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Xu, Fang Xie, Zhijie Hu, Kai Liu, Yu Song, Shenghui Gulliver, Thomas Aaron Xie, Yiyuan Yang, Yandong Duo, Bin Wang, Yuanchen Southwest University College of Electronic and Information Engineering Chongqing400715 China Hong Kong University of Science and Technology ECE Department Hong Kong Tianjin University School of microelectronics Tianjin300072 China University of Victoria Department of electrical and computer engineering VictoriaBCV8P5C2 Canada AI & HPC Software Department in IEI Beijing China Chengdu University of Technology School of computer and network security department Chengdu610059 China Xi'an Jiaotong University School of Cyber Science and Engineering Xi'an710049 China

Wireless sensors are often deployed in hard-to-reach locations for data collection. Unmanned aerial vehicles(UAVs) can easily fly over such locations and so it is a promising solution to collect data from remote sensors. This paper considers a UAV-assisted hybrid free space optical (FSO)/radio frequency (RF) data collection network for Internet of Things (IoT) applications. In this network, multiple remote sensors transfer information to a UAV with multiple antennas through RF links using time division multiple access (TDMA). The UAV uses decode and forward (DF) protocol to send information to a base station (BS) via FSO link. Successive interference cancellation (SIC) is employed to decode the information at the BS. Multi-agent deep reinforcement learning (DRL) is modified and applied to obtain a near-optimal scheme, for transmit power allocation, to minimize the maximum outage probability of decoding the information from the sensors under dynamic weather condition/UAV state. Numerical results are presented to illustrate the system design tradeoffs. Furthermore, the validity and superiority of our proposed approach is verified by comparing it with exhaustive search and differential evolution algorithms. © 1965-2011 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

A mini review and hypothesis for coronavirus detection using photonics: surface enhanced Raman scattering and fluorescence resonance energy transfer

引用

Infectious Diseases Research 2023年第1期4卷 10-13页

作者： Akshat Dharmeshkumar Modi Austin Tian Yang Akriti Sharma Department of Biological Sciences University of Toronto ScarboroughToronto M1C1A4Canada Department of Genetics and Development Krembil Research InstituteUniversity Health NetworkToronto M5T0S8Canada Department of Computer and Mathematical Sciences University of Toronto ScarboroughToronto M1C1A4Canada Department of Biomedical Engineering University of TorontoToronto M5S1A1Canada.

COVID-19 has devastated numerous nations around the world and has overburdened numerous healthcare systems,which has also caused the loss of livelihoods due to prolonged shutdowns and further led to a cascading effect on the global ***-19 infections have an incubation period of 2–7 days,but 40 to 45%of cases are asymptomatic or show mild to moderate respiratory symptoms after the period due to subclinical lung abnormalities,making it more likely to spread the pandemic *** restrict the spread of the virus,on-site diagnosis methods that are quicker,more precise,and easily accessible are *** Antigen Detection Tests and Polymerase Chain Reaction tests are currently the primary methods used to determine the presence of COVID-19 *** tests are typically time-consuming,not accurate,and,more importantly,not available to ***,in this review and hypothesis,we proposed equipment that employs the properties of photonics to improve the detection of COVID-19 viruses by taking the advantage of typical binding of coronavirus with angiotensin-converting enzyme 2(ACE2)*** hypothetical model would combine Surface-Enhanced Raman Scattering(SERS)and Fluorescence Resonance Energy Transfer(FRET)to provide great flexibility,high sensitivities,and enhanced accessibility.

关键词： COVID-19 coronavirus ACE2 virus detection photonics surface-enhanced Raman scattering fluorescence resonance energy transfer

来源：评论

学校读者我要写书评

暂无评论

Collaborative Authentication for 6G networks: An Edge Intelligence based Autonomous Approach

arXiv

引用

arXiv 2023年

作者： Fang, He Xiao, Zhenlong Wang, Xianbin Xu, Li Hanzo, Lajos The School of Electronic and Information Engineering Soochow University Soochow215301 China The Department of Informatics and Communication Engineering School of Informatics Xiamen University Xiamen361005 China The Department of Electrical and Computer Engineering Western University LondonONN6A 5B9 Canada The College of Computer and Cyber Security The Fujian Provincial Key Laboratory of Network Security and Cryptology Fujian Normal University Fuzhou350117 China School of Electronics and Computer Science University of Southampton SO17 1BJ United Kingdom

The conventional device authentication of wireless networks usually relies on a security server and centralized process, leading to long latency and risk of single-point of failure. While these challenges might be mitigated by collaborative authentication schemes, their performance remains limited by the rigidity of data collection and aggregated result. They also tend to ignore attacker localization in the collaborative authentication process. To overcome these challenges, a novel collaborative authentication scheme is proposed, where multiple edge devices act as cooperative peers to assist the service provider in distributively authenticating its users by estimating their received signal strength indicator (RSSI) and mobility trajectory (TRA). More explicitly, a distributed learning-based collaborative authentication algorithm is conceived, where the cooperative peers update their authentication models locally, thus the network congestion and response time remain low. Moreover, a situation-aware secure group update algorithm is proposed for autonomously refreshing the set of cooperative peers in the dynamic environment. We also develop an algorithm for localizing a malicious user by the cooperative peers once it is identified. The simulation results demonstrate that the proposed scheme is eminently suitable for both indoor and outdoor communication scenarios, and outperforms some existing benchmark schemes. Copyright © 2023, The Authors. All rights reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

R-Bench: Are your Large Multimodal Model Robust to Real-world Corruptions?

引用

IEEE Journal on Selected Topics in Signal Processing 2025年

作者： Li, Chunyi Zhang, Jianbo Zhang, Zicheng Wu, Haoning Tian, Yuan Sun, Wei Lu, Guo Min, Xiongkuo Liu, Xiaohong Lin, Weisi Zhang, Xiao-Ping Zhai, Guangtao Shanghai Jiao Tong University Institute of Image Communication and Network Engineering Shanghai200240 China Nanyang Technological University College of Computing and Data Science 639798 Singapore Shanghai AI Lab Shanghai200232 China East China Normal University School of Communication and Electronic Engineering Shanghai200240 China Shanghai Jiao Tong University John Hopcroft Center Shanghai200240 China Toronto Metropolitan University Department of Electrical Computer and Biomedical Engineering TorontoONM5B 2K3 Canada

The outstanding performance of Large Multimodal Models (LMMs) has made them widely applied in vision-related tasks. However, various corruptions in the real world mean that images will not be as ideal as in simulations, presenting significant challenges for the practical application of LMMs. To address this issue, we introduce R-Bench, a benchmark focused on the Real-world Robustness of LMMs. Specifically, we: (a) model the complete link from user capture to LMMs reception, comprising 33 corruption dimensions, including 7 steps according to the corruption sequence, and 7 groups based on low-level attributes;(b) collect reference/distorted image dataset before/after corruption, including 2,970 question-answer pairs with human labeling;(c) propose comprehensive evaluation for absolute/relative robustness and benchmark 20 mainstream LMMs. Results show that while LMMs can correctly handle the original reference images, their performance is not stable when faced with distorted images, and there is a significant gap in robustness compared to the human visual system. We hope that R-Bench will inspire improving the robustness of LMMs, extending them from experimental simulations to the real-world application. © 2007-2012 IEEE.

关键词： AI-Generated Content Image Compression Perceptual Quality Ultra-Low Bitrate

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware Sampling for Long-tailed Semi-supervised Learning

arXiv

引用

arXiv 2024年

作者： Yang, Kuo Li, Duo Hu, Menghan Zhai, Guangtao Yang, Xiaokang Zhang, Xiao-Ping The Shanghai Key Laboratory of Multidimensional Information Processing School of Communication and Electronic Engineering East China Normal University Shanghai200241 China The Kargobot of DiDi Shanghai201210 China The Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai200240 China Tsinghua Berkeley Shenzhen Institute Shenzhen China The Department of Electrical Computer and Biomedical Engineering Toronto Metropolitan University ONM5B 2K3 Canada

For semi-supervised learning with imbalance classes, the long-tailed distribution of data will increase the model prediction bias toward dominant classes, undermining performance on less frequent classes. Existing methods also face challenges in ensuring the selection of sufficiently reliable pseudo-labels for model training and there is a lack of mechanisms to adjust the selection of more reliable pseudo-labels based on different training stages. To mitigate this issue, we introduce uncertainty into the modeling process for pseudo-label sampling, taking into account that the model performance on the tailed classes varies over different training stages. For example, at the early stage of model training, the limited predictive accuracy of model results in a higher rate of uncertain pseudo-labels. To counter this, we propose an Uncertainty-Aware Dynamic Threshold Selection (UDTS) approach. This approach allows the model to perceive the uncertainty of pseudo-labels at different training stages, thereby adaptively adjusting the selection thresholds for different classes. Compared to other methods such as the baseline method FixMatch, UDTS achieves an increase in accuracy of at least approximately 5.26%, 1.75%, 9.96%, and 1.28% on the natural scene image datasets CIFAR10-LT, CIFAR100-LT, STL-10-LT, and the medical image dataset TissueMNIST, respectively. The source code of UDTS is publicly available at: https://***/yangk/UDTS. Copyright © 2024, The Authors. All rights reserved.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Class-Incremental Learning with Prior Knowledge

arXiv

引用

arXiv 2024年

作者： Jiang, Wenhao Li, Duo Hu, Menghan Zhai, Guangtao Yang, Xiaokang Zhang, Xiao-Ping Shanghai Key Laboratory of Multidimensional Information Processing School of Communication and Electronic Engineering East China Normal University Shanghai200241 China Kargobot of DiDi Shanghai201210 China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai200240 China Tsinghua Berkeley Shenzhen Institute Shenzhen China Department of Electrical Computer and Biomedical Engineering Toronto Metropolitan University ONM5B 2K3 Canada

To tackle the issues of catastrophic forgetting and overfitting in few-shot class-incremental learning (FSCIL), previous work has primarily concentrated on preserving the memory of old knowledge during the incremental phase. The role of pre-trained model in shaping the effectiveness of incremental learning is frequently underestimated in these studies. Therefore, to enhance the generalization ability of the pre-trained model, we propose Learning with Prior Knowledge (LwPK) by introducing nearly free prior knowledge from a few unlabeled data of subsequent incremental classes. We cluster unlabeled incremental class samples to produce pseudo-labels, then jointly train these with labeled base class samples, effectively allocating embedding space for both old and new class data. Experimental results indicate that LwPK effectively enhances the model resilience against catastrophic forgetting, with theoretical analysis based on empirical risk minimization and class distance measurement corroborating its operational principles. The source code of LwPK is publicly available at: https://***/StevenJ308/LwPK. Copyright © 2024, The Authors. All rights reserved.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

SGDA: Towards 3D Universal Pulmonary Nodule Detection via Slice Grouped Domain Attention

arXiv

引用

arXiv 2023年

作者： Xu, Rui Liu, Zhi Luo, Yong Hu, Han Shen, Li Du, Bo Kuang, Kaiming Yang, Jiancheng The School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Hubei Luojia Laboratory Wuhan China The Department of Computer and Network Engineering The University of Electro-Communications 1-5-1 Chofugaoka Chofushi Tokyo182-8585 Japan The School of Information and Electronics Beijing Insititute of Technology Beijing100081 China The JD Explore Academy Beijing China The Dianei Technology Shanghai200120 China The Shanghai Jiao Tong University Shanghai China Dianei Technology Shanghai China EPFL Lausanne Switzerland

Lung cancer is the leading cause of cancer death worldwide. The best solution for lung cancer is to diagnose the pulmonary nodules in the early stage, which is usually accomplished with the aid of thoracic computed tomography (CT). As deep learning thrives, convolutional neural networks (CNNs) have been introduced into pulmonary nodule detection to help doctors in this labor-intensive task and demonstrated to be very effective. However, the current pulmonary nodule detection methods are usually domain-specific, and cannot satisfy the requirement of working in diverse real-world scenarios. To address this issue, we propose a slice grouped domain attention (SGDA) module to enhance the generalization capability of the pulmonary nodule detection networks. This attention module works in the axial, coronal, and sagittal directions. In each direction, we divide the input feature into groups, and for each group, we utilize a universal adapter bank to capture the feature subspaces of the domains spanned by all pulmonary nodule datasets. Then the bank outputs are combined from the perspective of domain to modulate the input group. Extensive experiments demonstrate that SGDA enables substantially better multi-domain pulmonary nodule detection performance compared with the state-of-the-art multi-domain learning methods. © 2023, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

The Outline and the Current Status of the Power Transmission System Development Project for the Realization of the SSPS 73

The Outline and the Current Status of the Power Transmission...

引用

73rd International Astronautical Congress, IAC 2022

作者： Sasaki, Kenji Machida, Hirotaka Ijichi, Koichi Kashimura, Osamu Ishimura, Kosei Ishikawa, Ryo Honjo, Kazuhiko Ozawa, Yuichiro Tanaka, Koji Japan Space Systems 3-5-8 Shibakoen Minato-ku Tokyo105-0011 Japan Waseda University Dept. of Modern Mechanical Engineering School of Creative Science and Engineering 30401 Okubo Shinjuku-ku Tokyo169-8555 Japan Department of Computer and Network Engineering The University of Electro-Communications 1-5-1 Chofugaoka Chofu Tokyo182-8585 Japan Electronics Technologies Office Technologies Development Department IHI Aerospace Co. Ltd. 900 Fujiki Gunma-ken Tomioka-shi370-2398 Japan Japan Aerospace Exploration Agency Institute of Space and Astronautical Science 3-1-1 Yoshinodai Chuo-ku Kanagawa Sagamihara252-5210 Japan

The outline and the status of the current development project towards the realization of the operational SSPS which is the final object of the development will be presented. The current project under development consists of three major tasks. First one is to develop so called power generation and transmission panel whose size is about 50 cm square and 10 cm thick, and the target weight should be less than 9 kg. The second is to improve the conversion efficiency from DC to microwave to exceed 60%. The third is to demonstrate power transmission from the ground to the target on unmanned vehicle high up about one kilo-meter in the air. All these three development activities are for the realization of the operational SSPS toward the final operational system on the Geostationary Orbit (GEO) Space Solar Power System (SSPS) after the one step of the power beaming experiment from the Low Earth Orbit (LEO) satellite to the ground as the next logical development step. © 2022 International Astronautical Federation, IAF. All rights reserved.

关键词： Power transmission

来源：评论

学校读者我要写书评

暂无评论

Multi-camera motion compensation for remote monitoring of heart rate and respiration

Multi-camera motion compensation for remote monitoring of he...

引用

Imaging Systems and Applications, ISA 2021 - Part of OSA Imaging and Applied Optics Congress 2021

作者： Kuramoto, Lindsay Chu, Ryan Ringuette, Dene Zhu, Eric Mihailidis, Alex Levi, Ofer Edward S. Rogers Sr. Department of Electrical and Computer Engineering University of Toronto TorontoON Canada Institute of Biomaterials and Biomedical Engineering University of Toronto TorontoON Canada Krembil Research Institute TorontoONM5T 0S8 Canada Toronto Rehabilitation Institute – University Health Network TorontoONM5G 2A2 Canada Department of Occupational Science and Occupational Therapy University of Toronto TorontoON Canada

We demonstrate a motion-tolerant vital signs monitoring using multiple, depth sensing cameras. Results show successful isolation of the respiratory waveform from walking motion and successful isolation of heart rate f... 详细信息

ISBN: (纸本)9781557528209

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Implantable Neural Probe System for Patterned Photostimulation and Electrophysiology Recording

Implantable Neural Probe System for Patterned Photostimulati...

引用

CLEO: Science and Innovations, S and I 2022

作者： Chen, Fu-Der Wahn, Hannes Xue, Tianyuan Jung, Youngho Straguzzi, John N. Azadeh, Saeed S. Stalmashonak, Andrei Chua, Hongyao Luo, Xianshu Shah, Prajay Chameh, Homeira Moradi Lo, Patrick Guo-Qiang Valiante, Taufik A. Sacher, Wesley D. Poon, Joyce K.S. Max Planck Institute for Microstructure Physics Weinberg 2 Halle06120 Germany Department of Electrical and Computer Engineering University of Toronto 10 King's College Rd. TorontoONM5S 3G4 Canada Advanced Micro Foundry Pte. Ltd. 11 Science Park Road Singapore Science Park II 117685 Singapore Krembil Brain Institute University Health Network TorontoON Canada Division of Neurosurgery Department of Surgery Toronto Western Hospital University of Toronto TorontoON Canada Institute of Biomedical Engineering University of Toronto TorontoON Canada

We demonstrate a system for implantable nanophotonic neural probes with custom packaging and peripherals. The probes, which were manufactured on 200mm Si wafers, monolithically integrate SiN waveguides with TiN electr... 详细信息

ISBN: (纸本)9781557528209

关键词： Electrophysiology

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：