检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Huang, Guangjing Wu, Qiong Li, Jingyi Chen, Xu The School of Computer Science and Engineering Sun Yat-sen University Guangzhou China The Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

Federated learning (FL) has emerged as a promising paradigm that enables clients to collaboratively train a shared global model without uploading their local data. To alleviate the heterogeneous data quality among clients, artificial intelligence-generated content (AIGC) can be leveraged as a novel data synthesis technique for FL model performance enhancement. Due to various costs incurred by AIGC-empowered FL (e.g., costs of local model computation and data synthesis), however, clients are usually reluctant to participate in FL without adequate economic incentives, which leads to an unexplored critical issue for enabling AIGC-empowered FL. To fill this gap, we first devise a data quality assessment method for data samples generated by AIGC and rigorously analyze the convergence performance of FL model trained using a blend of authentic and AI-generated data samples. We then propose a data quality-aware incentive mechanism to encourage clients’ participation. In light of information asymmetry incurred by clients’ private multi-dimensional attributes, we investigate clients’ behavior patterns and derive the server’s optimal incentive strategies to minimize server’s cost in terms of both model accuracy loss and incentive payments for both complete and incomplete information scenarios. Numerical results demonstrate that our proposed mechanism exhibits highest training accuracy and reduces up to 53.34% of the server’s cost with real-world datasets, compared with existing benchmark mechanisms. Copyright © 2024, The Authors. All rights reserved.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Test Access Control for an Embedded MAC Unit Based Core using IEEE Std 1687

Test Access Control for an Embedded MAC Unit Based Core usin...

引用

2021 International Conference on Power, Energy and Innovations, ICPEI 2021

作者： Grout, Ian University of Limerick Department of Electronic and Computer Engineering Limerick Ireland

ISBN: (纸本)9781665402163

Ahstract-A major move today in developing and deploying embedded electronic systems is to include trained machine learning (ML) models that can be used for predicting new data in order to include added value to the embedded system functionality. The ML model can be implemented in software or hardware, and would typically require a highly parallelized architecture in order to reduce computation times. The design effort to create a suitable implementation is non-trivial. However, an aspect of the overall system development and deployment requirements that can be overlooked is the testability of the design hardware. In this paper, the test access for a trained ML model implemented in hardware as a MAC unit, and realized within a field programmable gate array (FPGA), is presented. The IEEE Std 1687 to provide access to embedded instrumentation is utilized to support the test requirements. The ML trained model is considered as an embedded computation core connected to a host processor. © 2021 IEEE.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Virtual Doctor: The role, responsibilities, and counterparts of the general medical AI

Virtual Doctor: The role, responsibilities, and counterparts...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Carbonell, Eduard Lloret Huang, Jiaxuan Shen, Yiqing Ke, Jing Shanghai Jiao Tong University School of Electronic Information and Electrical Engineering Shanghai China Dulwich College Shanghai Pudong: International School Shanghai China Johns Hopkins University Department of Computer Science MD United States

ISBN: (纸本)9798350386226

The apparition of multimodal solutions helped closing this breach by teaching AI solutions how to use multiple inputs to infer a given task. Elevating AI algorithms to a higher level by increasing robustness and accuracy. This approach also made models more human, by learning from multiple sources just as how clinicians do. However, such models are still far from being flexible due to mostly be constrained into one singular task, vastly differing from real clinicians who are in charge of broad fields with multiple tasks to perform. This niche is perfect for AI algorithms to grow. However, existing AI models lack flexibility to act similarly to doctors. Thus, some innovations are required to overcome this rigidity. One possible solution would be the emergence of Medical Artificial Intelligence (GMAI) seeks to evolve the current paradigm by aspiring to emulate more humanlike intelligence in medical applications. The emergence of these "Virtual Doctors"has the potential to significantly transform the healthcare paradigm, offering convenient healthcare solutions with just a few clicks at any time of the day. The focal point of this paper is to delineate the prospective applications of GMAI within the field of telemedicine, positioned as 'teledoctors', and to outline the existing technological gap between these innovative models and their conventional counterparts. More specifically, we envision GMAI as a 'Virtual Doctor,' functioning as an adaptable telemedicine system capable of addressing a broad array of inquiries and providing diagnoses for a diverse range of medical conditions by utilizing patient- or doctor-provided data inputs. While a general AI model for medical imaging may offer some benefits, it is vital to consider such a model's potential drawbacks and limitations. It is crucial to balance the benefits of AI and the need for human expertise and oversight in medical imaging. © 2024 IEEE.

关键词： Telemedicine

来源：评论

学校读者我要写书评

暂无评论

Provably Secure Conditional-Privacy Access Control Protocol for Intelligent Customers-Centric Communication in VANET

引用

IEEE Transactions on Consumer electronics 2024年第1期70卷 1747-1756页

作者： Saleem, Muhammad Asad Li, Xiong Mahmood, Khalid Shamshad, Salman Ayub, Muhammad Faizan Bashir, Ali Kashif Omar, Marwan University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu12599 China National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan The University of Lahore Department of Software Engineering Lahore54590 Pakistan Manchester Metropolitan University Department of Computing and Mathematics ManchesterM15 6BH United Kingdom Woxsen University Woxsen School of Business Hyderabad502345 India Lebanese American University Department of Computer Science and Mathematics Beirut1102 2801 Lebanon Illinois Institute of Technology Information Technology and Management ChicagoIL60555 United States

Globally, the development of Intelligent Cyber-Physical Transportation Systems (ICTS) aims to tackle several challenges, including reducing traffic accidents and fuel usage, alleviating congestion, shortening travel time, and enhancing overall transportation safety. These systems leverage advanced customer-centric communication and networked control methods, such as inter-vehicle, vehicle-to-roadside (V2R), and vehicle-to-vehicle (V2V) communication through the use of vehicular ad hoc networks (VANETs) to cover all aspects of transportation-based information. In existing systems, once devices are registered with a Trusted Authority (TA), subsequent authentication still relies on the TA's assistance. However, these devices typically remain stationary, and frequent interaction with the TA becomes impractical and costly in highly mobile VANET environments. To address this challenge, we propose a secure access control protocol with conditional privacy for VANETs. Unlike other protocols, our protocol does not require the TA's involvement during authentication between vehicles and RSUs. Additionally, our protocol leverages pseudonym mechanisms to provide conditional privacy, enabling legitimate vehicles to remain anonymous while malicious ones can be tracked. Our proposed scheme is supported by both formal and informal security analyses and has been shown to be secure against several known attacks in VANETs. Furthermore, compared to relevant studies, our protocol achieves 30.2505% of efficiency in terms of computation cost and 11.09276% of efficiency in terms of communication cost, respectively. © 1975-2011 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Demand-Oriented Allocation with Fairness in Multi-Operator Dynamic Spectrum Sharing Systems 15

Demand-Oriented Allocation with Fairness in Multi-Operator D...

引用

2022 IEEE Congress on Cybermatics: 15th IEEE International Conferences on Internet of Things, iThings 2022, 18th IEEE International Conferences on Green Computing and Communications, GreenCom 2022, 2022 IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2022 and 8th IEEE International Conference on Smart Data, SmartData 2022

作者： Wang, Mengying Wang, Wei Xu, Wenjing Bi, Jiameng Ye, Qiang College of Electronic and Information Engineering Nanjing University of Aeronautics and Astronautics China Department of Computer Science Memorial University of Newfoundland Canada

ISBN: (数字)9781665454179

ISBN: (纸本)9781665454179

Inter-operator spectrum sharing with guaranteed operator fairness is a challenging issue due to the differentiated service requirements and operator priorities. In this paper, we introduce an incentive mechanism to promote spectrum sharing and propose a fair spectrum allocation algorithm by considering the demand and response from different operators. Specifically, we design a new fairness factor based on operator spectrum demand and utility which can affect the spectrum pricing to change spectrum allocation schemes. The spectrum allocation problem is formulated as a two-stage Stackelberg game and the proposed algorithm solves the problem by finding the Nash equilibrium of each sub-game according to convex optimization theory. Simulation results show that under maximum fairness coefficient, the proposed algorithm can improve operator satisfaction by 30% on average. © 2022 IEEE.

关键词： Site selection

来源：评论

学校读者我要写书评

暂无评论

980 nm micro-cavity lasers with sub-milliampere threshold

980 nm micro-cavity lasers with sub-milliampere threshold

引用

CLEO: Science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

作者： Lin, Qi Xue, Ying Huang, Jie Gu, Wen Lau, Kei May Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Hong Kong Division of Emerging Interdisciplinary Area Hong Kong University of Science and Technology Clear Water Bay Hong Kong

We report electrically-pumped InGaAs/GaAs/GaAsP quantum well micro-cavity lasers on GaAs with low thresholds down to the sub-milliamp level and a maximum operating temperature of 95°C. Micro-lasers with various c... 详细信息

关键词： III-V semiconductors

来源：评论

学校读者我要写书评

暂无评论

An Efficient CNN-Based Automated Diagnosis Framework from COVID-19 CT Images

引用

computers, Materials & Continua 2021年第10期69卷 1323-1341页

作者： Walid El-Shafai Noha A.El-Hag Ghada M.El-Banby Ashraf A.M.Khalaf Naglaa F.Soliman Abeer D.Algarni Fathi E.Abd El-Samie Department Electronics and Electrical Communications Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Department of Electronics and Electrical Communications Faculty of EngineeringMinia UniversityEgypt Department of Industrial Electronics and Control Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh84428Saudi Arabia

Corona Virus Disease-2019(COVID-19)continues to spread rapidly in the *** has dramatically affected daily lives,public health,and the world *** paper presents a segmentation and classification framework of COVID-19 images based on deep ***,the classification process is employed to discriminate between COVID-19,non-COVID,and pneumonia by Convolutional Neural Network(CNN).Then,the segmentation process is applied for COVID-19 and pneumonia CT ***,the resulting segmented images are used to identify the infected region,whether COVID-19 or *** proposed CNN consists of four Convolutional(Conv)layers,four batch normalization layers,and four Rectified Linear Units(ReLUs).The sizes of Conv layer used filters are 8,16,32,and *** maxpooling layers are employed with a stride of 2 and a 2×2 *** classification layer comprises a Fully-Connected(FC)layer and a soft-max activation function used to take the classification decision.A novel saliencybased region detection algorithm and an active contour segmentation strategy are applied to segment COVID-19 and pneumonia CT *** acquired findings substantiate the efficacy of the proposed framework for helping the specialists in automated diagnosis applications.

关键词： Classification segmentation COVID-19 CNN deep learning diagnosis applications

来源：评论

学校读者我要写书评

暂无评论

Comparison of RGB and white LED Illumination in Honey Imaging System Using Histogram Approach 20

Comparison of RGB and white LED Illumination in Honey Imagin...

引用

20th IEEE Student Conference on Research and Development, SCOReD 2022

作者： Abubakar, Sabiran Ariffin, Nur Hazliza Parthiban, Rajendran Arsad, Norhana School of Engineering Monash University Malaysia Subang Jaya Malaysia Monash University Department of Electrical and Computer Engineering Clayton Australia Center of Advanced Electronic and Communication Engineering Universiti Kebangsaan Malaysia Faculty of Engineering and Built Environment Bangi Malaysia

ISBN: (数字)9781665474887

ISBN: (纸本)9781665474887

LED illumination-based multispectral imaging (LEDMSI) is one of the effective methods in the spectral image acquisition system. The availability of high-intensity LEDs with many different colours makes it possible to produce satisfying data for multivariate image analysis, including deep learning multispectral systems. However, the impact of white LED correlated colour temperature (CCT) on data images has received attention in the field. In this paper, we aimed to compare the effect of red-green-blue (RGB) and CCT of an LED light source on honey images. Light and dark honey are considered image samples in the experiment. The honey images were recorded under the influence of RGB LED and three categories of CCT white LED using an 18-megapixel DSLR camera. All the pictures are saved in a JPEG format and uploaded in ImageJ software to acquire the spectra measurement (raw data) and histogram analysis. The result showed that CCT variations indicated a variation histogram as shown in the variation of RGB LED. Moreover, grayscale intensity analysis shows better brightness, contrast, and distinction between the two types of honey. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Beam Scanning for Integrated Sensing and Communication in IRS-aided mmWave Systems 24

Beam Scanning for Integrated Sensing and Communication in IR...

引用

24th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2023

作者： Li, Renwang Shao, Xiaodan Sun, Shu Tao, Meixia Zhang, Rui Shanghai Jiao Tong University Department of Electronic Engineering Shanghai China Shanghai Jiao Tong University Shanghai Key Laboratory of Digital Media Processing and Transmission Shanghai China The Chinese University of HongKong School of Science and Engineering Shenzhen Research Institute of Big Data Shenzhen China National University of Singapore Department of Electrical and Computer Engineering Singapore

ISBN: (纸本)9781665496261

This paper investigates an intelligent reflecting surface (IRS) aided millimeter-wave integrated sensing and communication (ISAC) system. Specifically, based on the passive beam scanning in the downlink, the IRS finds the optimal beam for reflecting the signals from the base station to a communication user. Meanwhile, the IRS estimates the angle of a nearby target based on its echo signal received by the sensing elements mounted on the IRS (i.e., semi-passive IRS). We propose an ISAC protocol for achieving the above objective via simultaneous (beam) training and sensing (STAS). Then, we derive the achievable rate of the communication user and the Cramer-Rao bound (CRB) of the angle estimation for the sensing target in closed-form. The achievable rate and CRB exhibit different performance against the duration of beam scanning. Specifically, the average achievable rate initially rises and subsequently declines, while the CRB monotonically decreases. Consequently, the duration of beam scanning should be carefully selected to balance communication and sensing performance. Simulation results have verified our analytical findings and shown that, thanks to the efficient use of downlink beam scanning signal for simultaneous communication and target sensing, the STAS protocol outperforms the benchmark protocol with orthogonal beam training and sensing. © 2023 IEEE.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

A Compact Quasi-Yagi Microstrip Patch Antenna with High Gain and Bandwidth for UWB Application

引用

International Journal of electronics and Telecommunications 2023年第3期69卷 431-437页

作者： Chowdhury, Hasanur Rahman Hussain, Sakhawat Department of Electrical and Electronic Engineering University of Dhaka Dhaka1000 Bangladesh Department of Electrical & Computer Engineering Michigan State University East LansingMI United States The Department of Electrical and Electronic Engineering University of Dhaka Dhaka1000 Bangladesh

A quasi-Yagi microstrip patch antenna with four directors and truncated ground plane has been designed and fabricated to have an ultra-wide bandwidth, high gain, low return loss and better directivity with center frequency at 3.40 GHz. After optimization, the proposed antenna yields an ultra-wide bandwidth of 1.20 GHz with lower and upper cutoff frequencies at 3.12 GHz and 4.32 GHz, respectively. High gain of 5.25 dB, return loss of -28 dB and directivity of 6.28 dB are obtained at resonance frequency of 3.40 GHz. The measured results of fabricated antenna have shown excellent agreement with the simulation results providing bandwidth of 1.34 GHz with lower and upper cutoff frequencies at 3.04 GHz and 4.38 GHz, respectively. The antenna gain of 5.33 dB, return loss of -44 dB are obtained at resonance frequency of 3.36 GHz. The dimension of the antenna is only of 65 mm x 45 mm ensuring compact in size. © The Author(s).

关键词： Cutoff frequency

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：