检索结果-内蒙古大学图书馆

10th IEEE World Forum on Internet of Things, WF-IoT 2024

作者： Al-Habob, Ahmed A. Dobre, Octavia A. Jing, Yindi Memorial University Faculty of Engineering and Applied Science St. John'sNL Canada University of Alberta Department of Electrical and Computer Engineering EdmontonAB Canada

ISBN: (纸本)9798350373011

This paper investigates an unmanned aerial vehicle (UAV)-enabled network slicing problem to provide content delivery and sensing data gathering services. Two tenants provide services to their clients by sharing a common infrastructure of a set of UAVs. The content delivery tenant needs to guarantee that each of its clients (users) receives the required content, while the sensing tenant aims to gather an adequate amount of uncorrelated data. An energy consumption minimization framework is considered to meet the tenants' requirements by optimizing the number of deployed UAVs, the deployment location of each UAV, the transmit power of each deployed UAV, and the user-UAV association. Taking into consideration the spatial correlation among the sensing users, a subset of these users is activated to gather the required sensing information. A heuristic solution approach is presented to select the suitable deployment location of the UAVs, activate the optimum subset of the sensing users, and associate the users of both tenants with the deployed UAVs. Simulation results illustrate that the proposed framework significantly reduces the total energy consumption. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Predictive Beamforming Approach for Secure Integrated Sensing and Communication

Predictive Beamforming Approach for Secure Integrated Sensin...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

ISBN: (纸本)9798350351255

This paper considers an integrated sensing and communication (ISAC) system framework, in which an aerial eavesdropper poses the threat to intercept the downlink communication from a base station to a set of users. The eavesdropper is moving and its unknown location is estimated based on the echo signal. A maximum likelihood-based scheme is developed to estimate the eavesdropper channel, which performs a coarse estimation and further refines the estimated parameters. A long short-term memory deep network is employed to predict the eavesdropper channel and also to enable a less frequent estimation process. Based on the predicted eavesdropper's channel, a precoding optimization algorithm is developed to improve the sum secrecy rate for the users. Simulation results illustrate that the developed framework provides substantial improvement in the communication secrecy when compared with other benchmark approaches. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Voltage Overshoots Mitigation in a Long Cable PWM-Fed Induction Machine Using dv/dt Filters 3

Voltage Overshoots Mitigation in a Long Cable PWM-Fed Induct...

引用

3rd International Conference on electrical Machines and Drives, ICEMD 2023

作者： Toulabi, Mohammad Sedigh Filizadeh, Shaahin Wang, Liwei Farahzadi, Mohammad Nasiri-Zarandi, Reza Abbaszadeh, Karim University of Windsor Department of Electrical and Computer Engineering WindsorON Canada University of Manitoba Department of Electrical and Computer Engineering WinnipegMB Canada University of British Columbia Department of Electrical and Computer Engineering KelownaBC Canada University of Science and Culture Faculty of Electrical Engineering Tehran Iran Niroo Research Institute Electric Machines Research Centre Tehran Iran K.N. Toosi University of Technology Faculty of Electrical Engineering Tehran Iran

ISBN: (纸本)9798350393743

Significant voltage overshoots are observed in the input terminals of long cable pulse-width modulation (PWM)-fed induction machines, which can detrimentally impact the machine's lifespan and performance. To mitigate this concerning phenomenon, dv/dt filters consisting of R, L, and C elements are used in the circuit. In this paper, the high-frequency model of a long cable PWM-fed induction machine is established, incorporating the high-frequency models of the machine and long cable, as well as the pulses generated by the PWM converter and filters. Differential mode and common mode impedance measurements are employed to develop the high-frequency model of the induction machine, while short circuit and open circuit impedance tests are conducted to establish the high-frequency models of the long cable. The transmission line modeling approach is then utilized to incorporate the high-frequency modeled machine and long cable, enabling the prediction of voltage overshoots at the machine's terminal. Three distinct dv/dt filters are placed at the beginning, middle, and end of the long cable to mitigate the voltage overshoots in the terminal of the PWM-fed induction machine. Test results are presented for a 100 m cable, 2 hp machine fed by a PWM converter in the presence of the dv/dt filters, aiming to identify the appropriate filter location for minimizing voltage overshoots in the terminals of the machine. © 2023 IEEE.

关键词： Pulse width modulation

来源：评论

学校读者我要写书评

暂无评论

AccuMO: Accuracy-Centric Multitask Offloading in Edge-Assisted Mobile Augmented Reality 23

AccuMO: Accuracy-Centric Multitask Offloading in Edge-Assist...

引用

29th Annual International Conference on Mobile Computing and Networking, MobiCom 2023

作者： Kong, Z. Jonny Xu, Qiang Meng, Jiayi Hu, Y. Charlie School of Electrical and Computer Engineering Purdue University West LafayetteIN60009254 United States Department of Computer Science Purdue University West LafayetteIN60028629 United States

ISBN: (纸本)9781450399906

Immersive applications such as Augmented Reality (AR) and Mixed Reality (MR) often need to perform multiple latency-critical tasks on every frame captured by the camera, which all require results to be available within the current frame interval. While such tasks are increasingly supported by Deep Neural Networks (DNNs) offloaded to edge servers due to their high accuracy but heavy computation, prior work has largely focused on offloading one task at a time. Compared to offloading a single task, where more frequent offloading directly translates into higher task accuracy, offloading of multiple tasks competes for shared edge server resources, and hence faces the additional challenge of balancing the offloading frequencies of different tasks to maximize the overall accuracy and hence app *** this paper, we formulate this accuracy-centric multitask offloading problem, and present a framework that dynamically schedules the offloading of multiple DNN tasks from a mobile device to an edge server while optimizing the overall accuracy across tasks. Our design employs two novel ideas: (1) task-specific lightweight models that predict offloading accuracy drop as a function of offloading frequency and frame content, and (2) a general two-level control feedback loop that concurrently balances offloading among tasks and adapts between offloading and using local algorithms for each task. Evaluation results show that our framework improves the overall accuracy significantly in jointly offloading two core tasks in AR - - depth estimation and odometry - - by on average 7.6% - 14.3% over the best baselines under different accuracy weight ratios. © 2023 ACM.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Random Forest Empowered Shade and Fault Detection in Photovoltaic Panel 14

Random Forest Empowered Shade and Fault Detection in Photovo...

引用

14th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2023

作者： Mahto, Rakeshkumar Sood, Kanika Ruppert, Nathaniel California State University Fullerton Department of Electrical and Computer Engineering California United States California State University Fullerton Department of Computer Science California United States

ISBN: (纸本)9798350304138

In recent years, the role of drones in disaster management has garnered substantial attention due to their ability to respond to a variety of hostile environments effectively. Unmanned aerial vehicles have demonstrated value in rapid damage assessment, search-and-rescue operations, and navigating challenging terrains. This paper explores integrating photovoltaic (PV) based power sources in drones for disaster response. While PV power sources offer sustainability and endurance advantages, they face challenges in low light conditions and susceptibility to physical damage or short circuits. To address these challenges, the incorporation of Complementary Metal-Oxide-Semiconductor (CMOS) embedded PV panels is proposed, enabling real-time reconfiguration of the electrical layout to optimize power generation. However, accurate detection of shade and faults becomes crucial for this strategy. This paper emphasizes applying machine learning (ML) classification techniques for reliable shade and fault detection. Notably, the Random Forest Technique is investigated for identifying faults in CMOS-embedded PV panels. Leveraging multiple decision trees, this ensemble learning approach enhances accuracy in fault classification. By training on diverse fault scenarios, the model can discern normal and faulty PV panel behavior, facilitating the detection of shaded, open circuit, and short circuit faults. This real-time response ensures optimal power generation and drone functionality. The presented ML classifier achieves 94.50% accuracy in detecting shade and faults, thus contributing to the enhanced reliability and effectiveness of PV-powered drones in disaster scenarios. © 2023 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

On-chip meta-lens based Adaptive Integrated Photonic Imager

On-chip meta-lens based Adaptive Integrated Photonic Imager

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Kim, Jong Ryul Jeong, Heijun Gu, Tingyi Quantum Science and Engineering Program University of Delaware NewarkDE19711 United States Electrical and Computer Engineering University of Delaware NewarkDE19711 United States

ISBN: (纸本)9781957171395

关键词： Adaptive optics

来源：评论

学校读者我要写书评

暂无评论

Recursive Estimation of User Intent From Noninvasive Electroencephalography Using Discriminative Models 48

Recursive Estimation of User Intent From Noninvasive Electro...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Smedemark-Margulies, Niklas Celik, Basak Imbiriba, Tales Kocanaogullari, Aziz Erdoǧmuş, Deniz Northeastern University Khoury College of Computer Science BostonMA United States Northeastern University Dept. of Electrical & Computer Engineering BostonMA United States

ISBN: (纸本)9781728163277

We study the problem of inferring user intent from noninvasive electroencephalography (EEG) to restore communication for people with severe speech and physical impairments (SSPI). The focus of this work is improving the estimation of posterior symbol probabilities in a typing task. At each iteration of the typing procedure, a subset of symbols is chosen for the next query based on the current probability estimate. Evidence about the user's response is collected from event-related potentials (ERP) in order to update symbol probabilities, until one symbol exceeds a predefined confidence threshold. We provide a graphical model describing this task, and derive a recursive Bayesian update rule based on a discriminative probability over label vectors for each query, which we approximate using a neural network classifier. We evaluate the proposed method in a simulated typing task and show that it outperforms previous approaches based on generative modeling. © 2023 IEEE.

关键词： Brain-computer interfaces (BCI) Discriminative neural networks Event-related potentials (ERP) Noninvasive EEG P300 speller

来源：评论

学校读者我要写书评

暂无评论

Benchmark Study on YOLOv8 Variants in Localized Multiclass Fault Detection in PCBs 6

Benchmark Study on YOLOv8 Variants in Localized Multiclass F...

引用

6th International Conference on electrical engineering and Information and Communication Technology, ICEEICT 2024

作者： Najib, Taeef Muntasir, Fahim Wasi, Wasif Al Wazed Sidetrek Dhaka Bangladesh Brac University Dept. of Computer Science and Engineering Dhaka Bangladesh Rajshahi University of Engineering and Technology Dept. of Electrical and Electronic Engineering Rajshahi Bangladesh

ISBN: (纸本)9798350385779

Detecting surface faults on PCBs is critical for ensuring device dependability and performance. Manual PCB inspection methods like X-ray imaging struggle to ensure quality control due to limitations in speed and defect characterization. However, advanced automated technologies, such as object detection models like YOLOv8, have emerged as a more efficient solution. This study focuses on evaluating the performance of different YOLOv8 variants in identifying and classifying various defects on PCBs. A benchmark of how each modification of the model performs detection and the factors behind were investigated here. It was determined that, YOLOv8 is sensitive to the amount of data it is being trained on, as the larger models tend to overlearn on smaller datasets. YOLOv8-m had the best performance, 97.1% precision, concerning the time taken and epoch count, over others. Large YOLOv8 variants, such as YOLOv8x, are also computationally expensive. The models were trained for 200 epochs with a patience value set at 50. Both increasing the number of data points and the resources will improve the performance and facilitate the overall training procedures. A significant gap in automated electronics production is addressed by this study: precise PCB fault localization for higher reliability of the product. © 2024 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

CiC-NET: a real-time semantic segmentation network for dam surface crack detection

引用

Multimedia Tools and Applications 2024年 1-23页

作者： Li, Linjing Zhao, Hao Liu, Ran Nayyar, Anand Ali, Rashid Li, Yonglong Zhang, Hua School of Information Engineering Southwest University of Science and Technology Mianyang China University of Science and Technology of China Heifei China School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore School of Computer Science Duy Tan University Da Nang550000 Viet Nam Department of Computer Science University of Turbat Turbat Pakistan Department of Electronic Engineering Tsinghua University Beijing China Tianfu Institute of Research and Innovation Southwest University of Science and Technology Chengdu China

Crack detection is vital for maintaining hydraulic engineering infrastructure. However, achieving a balance between real-time processing and high precision in semantic segmentation models presents a significant challenge, especially given the intricate details of cracks and complex backgrounds. To tackle this issue, this paper proposes a real-time, high-precision crack segmentation model. Initially, a four-branch feature extraction structure is devised to capture the edge details of cracks, with a focus on enhancing segmentation accuracy. Subsequently, an image pyramid is constructed at the input end to feed small-scale samples into high-dimensional feature extraction branches, thereby reducing computational costs and improving segmentation speed. Finally, an effective feature fusion module is designed for the feature extraction structure to capture sufficient crack features and achieve precise crack localization. Extensive experiments validate the superior performance of the proposed method, with Pixel Accuracy, Recall, Intersection over Union, and F1 score reaching 68.45%, 67.04%, 51.22%, and 67.74%, respectively, while maintaining a modest parameter count of 13.12M. This model provides a reliable and efficient solution for the health monitoring and maintenance of hydraulic engineering. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A real-time detection of battery pole before welding based on improved YOLOX 24

A real-time detection of battery pole before welding based o...

引用

2024 7th International Conference on computer Information science and Artificial Intelligence, CISAI 2024

作者： Tian, Hongling Fang, Zaojun Zheng, Tianjiang Faculty of Electrical Engineering and Computer Science Ningbo University Zhejiang Ningbo China Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Zhejiang Ningbo China

ISBN: (纸本)9798400707254

Rapid and accurate detection of the power battery pole area before welding is the prerequisite for accurately locating the welding starting point, and its performance determines the assembly efficiency and quality of the battery module. In view of the complex welding environment, low color contrast, and small area ratio, an improved model based on YOLOX is proposed. A multi-scale mixed attention module is introduced after the backbone feature to infer attention from different scales and enhance the key features of the target. A complex bidirectional fusion strategy that is conducive to small target detection is introduced at the neck of the model. The feature gradient flow is enriched through deep separable convolutions of multiple kernel sizes, and the original features are effectively utilized with the help of residual structures and multi-scale information is integrated. Experiments have shown that the optimized model is more stable to various environmental interferences while maintaining lightweight. The detection accuracy of the model is improved by 4.13% compared with the baseline model, the parameters are 6.27M, and the detection speed is 93 FPS. The overall performance is better than other models, providing an effective solution to the problem of welding initial point detection in power battery assembly. © 2024 Copyright held by the owner/author(s).

关键词： Poles

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：