检索结果-内蒙古大学图书馆

2024 Prognostics and System Health Management Conference, PHM 2024

作者： Cai, Congrui Lu, Zhonghai School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Embedded Systems Master Program Sweden School of Electrical Engineering and Computer Science Department of Electrical Engineering KTH Royal Institute of Technology Sweden

ISBN: (纸本)9798350360585

Recurrent Neural Networks (RNNs) are commonly used in data-driven approaches to estimate the Remaining Useful Lifetime (RUL) of power electronic devices. RNNs are preferred because their intrinsic feedback mechanisms are better suited to model time-series data. However, the impact of RNN complexity on estimation accuracy is rarely discussed in the literature. This issue is important because choosing a lower-complexity model that delivers the same or similar performance as a higher-complexity model can increase implementation efficiency. In the paper, we use three RNN models, namely, the vanilla version, LSTM (Long Short Term Memory) and GRU (Gated Recurrent Unit) to conduct RUL estimation for power electronic devices. We use two accelerated aging datasets, one dataset targeting the package failure of MOSFETs, and the other dataset targeting package failure of power diodes. Our study shows that a lower-complexity RNN does not necessarily deliver a lower performance. Similarly, a higher-complexity model does not assure a higher performance. As such, our work highlights the importance of selecting a proper neural network for RUL estimation not biased towards complex models. This is especially useful and important for implementing such RUL estimation techniques in embedded resource-constrained and speed-limited computins platforms. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Survey on Supervised,Unsupervised,and Semi-Supervised Approaches in Crowd Counting

引用

Computers, Materials & Continua 2024年第12期81卷 3561-3582页

作者： Jianyong Wang Mingliang Gao Qilei Li Hyunbum Kim Gwanggil Jeon School of Electrical and Electronic Engineering Shandong University of TechnologyZibo255000China School of Electronic Engineering and Computer Science Queen Mary University of LondonLondonE14NSUK Department of Embedded Systems Engineering Incheon National UniversityIncheon22012Republic of Korea

Quantifying the number of individuals in images or videos to estimate crowd density is a challenging yet crucial task with significant implications for fields such as urban planning and public *** counting has attracted considerable attention in the field of computer vision,leading to the development of numerous advanced models and *** approaches vary in terms of supervision techniques,network architectures,and model ***,most crowd counting methods rely on fully supervised learning,which has proven to be ***,this approach presents challenges in real-world scenarios,where labeled data and ground-truth annotations are often *** a result,there is an increasing need to explore unsupervised and semi-supervised methods to effectively address crowd counting tasks in practical *** paper offers a comprehensive review of crowd counting models,with a particular focus on semi-supervised and unsupervised approaches based on their supervision *** summarize and critically analyze the key methods in these two categories,highlighting their strengths and ***,we provide a comparative analysis of prominent crowd counting methods using widely adopted benchmark *** believe that this survey will offer valuable insights and guide future advancements in crowd counting technology.

关键词： Crowd counting density estimation convolutional neural network(CNN) un/semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Supervised Local Training With Backward Links for Deep Neural Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 854-867页

作者： Guo, Wenzhe Fouda, Mohammed E. Eltawil, Ahmed M. Salama, Khaled Nabil King Abdullah University of Science and Technology Division of Computer Electrical and Mathematical Sciences and Engineering Thuwal23955 Saudi Arabia University of California Center for Embedded and Cyber-Physical Systems IrvineCA92612 United States

The restricted training pattern in the standard backpropagation (BP) requires end-to-end error propagation, causing large memory costs and prohibiting model parallelization. Existing local training methods aim to resolve the training obstacles by completely cutting off the backward path between modules and isolating their gradients. These methods prevent information exchange between modules and result in inferior performance. This work proposes a novel local training algorithm, BackLink, which introduces intermodule backward dependence and facilitates information to flow backward along with the network. To preserve the computational advantage of local training, BackLink restricts the error propagation length within the module. Extensive experiments performed in various deep convolutional neural networks demonstrate that our method consistently improves the classification performance of local training algorithms over other methods. For example, our method can surpass the conventional greedy local training method by 6.45% in accuracy in ResNet32 classifying CIFAR100 and recent work by 2.58% in ResNet110 classifying STL-10 with much lower complexity. Analysis of computational costs reveals that small overheads are incurred in GPU memory costs and runtime on multiple GPUs. Our method can lead up to a 79% reduction in memory cost and 52% in simulation runtime in ResNet110 compared to the standard BP. Therefore, our method could create new opportunities for improving training algorithms toward better efficiency for real-time learning applications. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Traffic Density Estimation by Distributed Proxy Model Learning for Internet-of-Vehicle

引用

IEEE Internet of Things Journal 2025年第12期12卷 19972-19980页

作者： Li, Qilei Cheng, Jing-An Gao, Mingliang Chen, Jinyong Jeon, Gwanggil Shandong University of Technology School of Electrical and Electronic Engineering Zibo255000 China Queen Mary University of London School of Electronic Engineering and Computer Science LondonE1 4NS United Kingdom Incheon National University Department of Embedded Systems Engineering Incheon22012 Korea Republic of

Autonomous driving has been significantly advanced in todays society, which revolutionized daily routines and facilitated the development of the Internet of Vehicles (IoV). A crucial aspect of this system is understanding traffic density to enable intelligent traffic management. With the rapid improvement in deep neural networks (DNNs), the accuracy of density estimation has markedly improved. However, there are two main issues that remain unsolved. Firstly, current DNN-based models are excessively heavy, characterized by an overwhelming number of training parameters (millions or even billions) and substantial computational complexity, indicated by a high number of FLOPs. These requirements for storage and computation severely limit the practical application of these models, especially on edge devices with limited capacity and computational power. Secondly, despite the superior performance of DNN models, their effectiveness largely depends on the availability of large-scale data for training. Growing privacy concerns have made individuals increasingly hesitant to allow their data to be publicly used for model training, particularly in vehicle-related applications that might reveal personal movements, which leads to data isolation issues. In this paper, we address these two problems at once with a systematic framework. Specifically, we introduce the Proxy Model Distributed Learning (PMDL) model for traffic density estimation. PMDL model is composed of two main components. First, we introduce a proxy model learning strategy that transfers fine-grained knowledge from a larger master model to a lightweight proxy model, i.e., a proxy model. Second, we design a distributed learning strategy that trains multiple proxy models with privacy-aware local data and seamlessly aggregates these models via a global parameter server. This ensures privacy protection while significantly improving estimation performance compared to training models with limited, isolated data. We tested

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

RUL Estimation for Power Electronic Devices Using RNNs

RUL Estimation for Power Electronic Devices Using RNNs

引用

Prognostics and System Health Management Conference (PHM)

作者： Congrui Cai Zhonghai Lu Embedded Systems Master Program School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Department of Electrical Engineering School of Electrical Engineering and Computer Science KTH Royal Institute of Technology

ISBN: (数字)9798350360585

ISBN: (纸本)9798350360592

关键词： Performance evaluation Semiconductor device modeling Recurrent neural networks Computational modeling Estimation Power electronics Data models

来源：评论

学校读者我要写书评

暂无评论

Analysis of the acoustoelectric response of SAW gas sensors using a COM model

引用

Microsystems & Nanoengineering 2024年第3期10卷 87-96页

作者： Yang Yuan Tao Yang Xi Chen Linglang Yu Xiaoxiao Hou Guangzu Zhang Wen Dong Zixiao Lu Honglang Li Leonhard Reindl Wei Luo School of Integrated Circuits Huazhong University of Science and Technology430074 WuhanPeople’s Republic of China CAS Center for Excellence in Nanoscience National Center for Nanoscience and Technology100190 BeijingPeople’s Republic of China Department of Microsystems Engineering Laboratory for Electrical Instrumentation and Embedded SystemsUniversity of Freiburg79110 FreiburgGermany Research Institute of Huazhong University of Science and Technology in Shenzhen 518057 ShenzhenPeople’s Republic of China

Surface acoustic wave(SAW)gas sensors based on the acoustoelectric effect exhibit wide application prospects for in situ gas ***,establishing accurate models for calculating the scattering parameters of SAW gas sensors remains a ***,we present a coupling of modes(COM)model that includes the acoustoelectric effect and specifically explains the nonmonotonic variation in the center frequency with respect to the sensing film’s sheet *** sensing parameters of the gas sensors,including the center frequency,insertion loss,and phase,were experimentally compared for accuracy and ***,the frequency of the phase extremum(FPE)shift was determined to vary monotonically,and the range of selectable test points was wide,making the FPE an appropriate response parameter for leveraging in SAW gas *** simulation results of the COM model were highly consistent with the experimental *** study is proposed to provide theoretical guidance for the future development of gas SAW sensors.

关键词： COM SAW establishing

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fuzzy Control of Autonomous Surface Vehicles for Fast Accurate Trajectory Tracking

引用

International Journal of Fuzzy systems 2023年第6期25卷 2411-2422页

作者： Zhang, Xuefeng Su, Shun-Feng Chen, Yang-Quan College of Sciences Northeastern University Shenyang110819 China Department of Electrical Engineering National Taiwan University of Science and Technology Taipei106 Taiwan Embedded Systems and Automation Laboratory School of Engineering University of California at Merced MercedCA95343 United States

This paper investigates the trajectory tracking control problem for the autonomous surface vehicles with unknown dynamics and environmental disturbances. A novel adaptive fuzzy constrained control approach is put forward to deal with this problem. Instead of the exponentially decaying functions, a new-type performance envelop is designed to offer a way to explicitly and freely preassign the settling time and the accuracy of trajectory tracking. Moreover, in lieu of involving the approach angle or azimuth angle, a new idea for tackling underactuation is proposed that yields a singularity-free continuous control solution. The fuzzy logic systems are employed to address the unknown and lumped nonlinearities in the closed-loop system. The resulting control system possesses inherent robustness to the external disturbances and the second derivative of the reference trajectory, thus without the need for employing disturbance observers or assuming the available derivative information. It is demonstrated by the constraint analysis based on dialectic by contradiction that the developed control achieves arbitrarily fast and accurate trajectory tracking for the vehicle. Finally, the effectiveness and superiority of our approach are verified by a comparative simulation. © 2023, The Author(s) under exclusive licence to Taiwan Fuzzy systems Association.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Development of a Wireless Real-Time Computation System for Fast and Accurate Heart Rate Monitoring using Photoplethysmography (PPG) Signals 16

Development of a Wireless Real-Time Computation System for F...

引用

16th IEEE Malaysia International Conference on Communication, MICC 2023

作者： Lim, Ben Dong Chong, Kim Soon Tiang, Sew Sun Lim, Wei Hong Mokayef, Mastaneh Tan, Bee Sian UCSI University Department Electrical & Electronic Engineering Selangor Malaysia Tunku Abdul Rahman University of Management and Technology Department of Computer Science and Embedded Systems Kuala Lumpur Malaysia

ISBN: (纸本)9798350304343

This manuscript presents the development of a wireless system for fast and accurate heart rate monitoring. The system utilizes Seeed XIAO BLE and MAX86150 components to capture and process the photoplethysmogram (PPG) signal. Real-Time computation of heart rate is achieved through the deployment of a modified HeartPy algorithm on the microcontroller. The accuracy of the system was evaluated through experiments involving six patients, comparing the results with those obtained from a commercial pulse oximeter (A310) by AEON Technology. The Mean Percentage Error values demonstrated a close agreement between the test system and the commercial device, with an error falling within 0.31%. Additionally, the system achieved a 30% to 40% shorter refresh time compared to the commercial pulse oximeter, allowing for more frequent and up-To-date heart rate monitoring. The development of this wireless system contributes to the advancement of healthcare technology, aligning with the Sustainable Development Goal of Good Health and Well-being. Future improvements include incorporating oxygen saturation (SpO2) and electrocardiogram (ECG) detection into the system and designing a compact and portable form factor. By combining fast and accurate heart rate monitoring with wireless data transmission, this system holds promise for enhancing healthcare applications and improving patient well-being. © 2023 IEEE.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

Enhancing Drone Surveillance with NeRF: Real-World Applications and Simulated Environments 43

Enhancing Drone Surveillance with NeRF: Real-World Applicati...

引用

43rd AIAA DATC/IEEE Digital Avionics systems Conference, DASC 2024

作者： Lindén, Joakim Burresi, Giovanni Forsberg, Håkan Daneshtalab, Masoud Söderquis, Ingemar School of Innovation Design and Engineering Mälardalen University Division of Intelligent Future Technologies Västerås Sweden Saab Aeronautics Stockholm Sweden School of Electrical Engineering and Computer Science Royal Institute of Technology Division of Electronics and Embedded Systems Stockholm Sweden

ISBN: (纸本)9798350349610

Machine Learning (ML) systems require representative and diverse datasets to accurately learn the objective task. In supervised learning data needs to be accurately annotated, which is an expensive and error-prone process. We present a method for generating synthetic data tailored to the use-case achieving excellent performance in a real-world usecase. We provide a method for producing automatically annotated synthetic visual data of multi rotor unmanned aerial vehicles (UAV) and other airborne objects in a simulated environment with a high degree of scene diversity, from collection of 3D models to generation of annotated synthetic datasets (synthsets). In our data generation framework SynRender we introduce a novel method of using Neural Radiance Field (NeRF) methods to capture photo-realistic high-fidelity 3D-models of multirotor UAVs in order to automate data generation for an object detection task in diverse environments. By producing data tailored to the real-world setting, our NeRF-derived results show an advantage over generic 3D asset collection-based methods where the domain gap between the simulated and real-world is unacceptably large. In the spirit of keeping research open and accessible to the research community we release our dataset VISER DroneDiversity used in this project, where visual images, annotated boxes, instance segmentation and depth maps are all generated for each image sample. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Multiscale aggregation and illumination-aware attention network for infrared and visible image fusion

Multiscale aggregation and illumination-aware attention netw...

引用

作者： Song, Wenhao Zhai, Wenzhe Gao, Mingliang Li, Qilei Chehri, Abdellah Jeon, Gwanggil School of Electrical and Electronic Engineering Shandong University of Technology Zibo China School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom Department of Mathematics and Computer Science Royal Military College of Canada Kingston Canada Department of Embedded Systems Engineering Incheon National University Incheon Korea Republic of

Image fusion plays a significant role in computer vision since numerous applications benefit from the fusion results. The existing image fusion methods are incapable of perceiving the most discriminative regions under varying illumination circumstances and thus fail to emphasize the salient targets and ignore the abundant texture details of the infrared and visible images. To address this problem, a multiscale aggregation and illumination-aware attention network (MAIANet) is proposed for infrared and visible image fusion. Specifically, the MAIANet consists of four modules, namely multiscale feature extraction module, lightweight channel attention module, image reconstruction module, and illumination-aware module. The multiscale feature extraction module attempts to extract multiscale features in the images. The role of the lightweight channel attention module is to assign different weights to each channel so as to focus on the essential regions in the infrared and visible images. An illumination-aware module is employed to assess the probability distribution regarding the illumination factor. Meanwhile, an illumination perception loss is formulated by the illumination probabilities to enable the proposed MAIANet to better adjust to the changes in illumination. Experimental results on three datasets, that is, MSRS, TNO, and RoadSence, verify the effectiveness of the MAIANet in both qualitative and quantitative evaluations. © 2023 John Wiley & Sons, Ltd.

关键词： Image fusion

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：