检索结果-内蒙古大学图书馆

37th IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology systems, DFT 2024

作者： Chen, Yizhi Zhu, Wenyao Chen, Dejiu Mohammed, Omar Khound, Parthib Lu, Zhonghai School of Electrical Engineering and Computer Science Kth Royal Institute of Technology Stockholm Sweden School of Industrial Engineering and Management Kth Royal Institute of Technology Stockholm Sweden University of Siegen Reliability of Technical Systems and Electrical Measurement Siegen Germany

ISBN: (纸本)9798350366884

Object detection is one of the most fundamental problems in computer vision, and image sensors are commonly used for this. In this paper, we present the impact of image sensor faults on pruned neural networks for object detection. We compare the error sensitivities of networks after network slimming, networks after magnitude-based pruning, and native compact models. We also explore different spatial fault types with three intensities. Furthermore, we have developed a temporal error model based on realistic aging image sensor faults. The results illuminate that the performance on clean images is important as the mean Average Precision (mAP) experiences a decrease with an increase in injected faults. Additionally, we demonstrate that the size of the model does not invariably yield a decisive impact on error tolerance when comparing small models such as pruned models and native compact models. © 2024 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

An Overview and Experimental Study of Learning-Based Optimization Algorithms for the Vehicle Routing Problem

引用

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1115-1138页

作者： Bingjie Li Guohua Wu Yongming He Mingfeng Fan Witold Pedrycz School of Traffic and Transportation Engineering Central South UniversityChangsha 410075China College of Systems Engineering National University of Defense TechnologyChangsha 410073China Department of Electrical and Computer Engineering University of AlbertaEdmontonAB T6G 2V4Canada the Department of Electrical and Computer Engineering Faculty of EngineeringKing Abdulaziz UniversityJeddah 21589Saudi Arabia the Systems Research Institute Polish Academy of SciencesWarsaw 01447Poland IEEE

The vehicle routing problem(VRP)is a typical discrete combinatorial optimization problem,and many models and algorithms have been proposed to solve the VRP and its *** existing approaches have contributed significantly to the development of this field,these approaches either are limited in problem size or need manual intervention in choosing *** solve these difficulties,many studies have considered learning-based optimization(LBO)algorithms to solve the *** paper reviews recent advances in this field and divides relevant approaches into end-to-end approaches and step-by-step *** performed a statistical analysis of the reviewed articles from various aspects and designed three experiments to evaluate the performance of four representative LBO ***,we conclude the applicable types of problems for different LBO algorithms and suggest directions in which researchers can improve LBO algorithms.

关键词： End-to-end approaches learning-based optimization(LBO)algorithms reinforcement learning step-by-step approaches vehicle routing problem(VRP)

来源：评论

学校读者我要写书评

暂无评论

Differentially Private Online Federated Learning with Correlated Noise 63

Differentially Private Online Federated Learning with Correl...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Zhang, Jiaojiao Zhu, Linglingzhi Johansson, Mikael Kth Royal Institute of Technology Division of Decision and Control Systems School of Electrical Engineering and Computer Science StockholmSE-100 44 Sweden Chinese University of Hong Kong Department of Systems Engineering and Engineering Management Hong Kong

ISBN: (纸本)9798350316339

We introduce a novel differentially private algorithm for online federated learning that employs temporally correlated noise to enhance utility while ensuring privacy of continuously released models. To address challenges posed by DP noise and local updates with streaming non-iid data, we develop a perturbed iterate analysis to control the impact of the DP noise on the utility. Moreover, we demonstrate how the drift errors from local updates can be effectively managed under a quasi-strong convexity condition. Subject to an (, δ) DP budget, we establish a dynamic regret bound over the entire time horizon, quantifying the impact of key parameters and the intensity of changes in dynamic environments. Numerical experiments confirm the efficacy of the proposed algorithm. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Long-term radiofrequency electromagnetic fields exposure attenuates cognitive dysfunction in 5×FAD mice by regulating microglial function

引用

Neural Regeneration research 2023年第11期18卷 2497-2503页

作者： Yeonghoon Son Hye-Jin Park Ye Ji Jeong Hyung-Do Choi Nam Kim Hae-June Lee Division of Radiation Biomedical Research Korea Institute of Radiological&Medical SciencesSeoulKorea Department of EMF Research Team Radio and Broadcasting Technology LaboratoryElectronics and Telecommunications Research InstituteDaejonKorea School of Electrical and Computer Engineering Chungbuk National UniversityCheongjuKorea

We have previously found that long-term effects of exposure to radiofrequency electromagnetic fields in 5xFAD mice with severe late-stage Alzheimer’s disease reduced both amyloid-βdeposition and glial activation,including *** examine whether this therapeutic effect is due to the regulation of activated microglia,we analyzed mic roglial gene expression profiles and the existence of microglia in the brain in this study.5xFAD mice at the age of 1.5 months were assigned to sham-and radiofrequency electromagnetic fields-exposed groups and then animals were exposed to 1950 MHz radiofrequency electromagnetic fields at a specific absorption rate of 5 W/kg for 2 hours/day and 5 days/week for 6 *** conducted behavioral tests including the object recognition and Y-maze tests and molecular and histopathological analysis of amyloid precursor protein/a myloid-beta metabolism in brain *** confirmed that radiofrequency electromagnetic field exposure for 6 months ameliorated cognitive impairment and amyloid-β*** expression levels of Iba1(pan-microglial marker)and colony-stimulating factor 1 receptor(CSF1R;regulates microglial prolife ration)in the hippocampus in 5xFAD mice treated with radiofrequency electromagnetic fields were significantly reduced compared with those of the sham-exposed ***,we analyzed the expression levels of genes related to mic rogliosis and microglial function in the radiofrequency electromagnetic fields-exposed group compared to those of a CSF1R inhibitor(PLX3397)-treated *** radiofrequency electromagnetic fields and PLX3397 suppressed the levels of genes related to microgliosis(Csf1r,CD68,and Ccl6)and pro-inflammatory cytokine interleukin-1β.N otably,the expression levels of genes related to mic roglial function,including Trem2,Fcgr1α,Ctss,and Spi1,were decreased after long-term radiofrequency electromagnetic field exposure,which was also observed in response to microglial suppression by *** res

关键词： 5×FAD Alzheimer’s disease CSF1R long term exposure microglial function neuroinflammation radiofrequency electromagnetic fields therapeutic effect

来源：评论

学校读者我要写书评

暂无评论

Sleep-Wake and Body Position Classification with Deep Learning using Pressure Sensor Mat Measurements

Sleep-Wake and Body Position Classification with Deep Learni...

引用

2023 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2023

作者： Green, Carter Bouchard, Martin Goubran, Rafik Robillard, Rebecca Higginson, Caitlin Lee, Elliott Knoefel, Frank University of Ottawa School of Electrical Engineering and Computer Science OttawaON Canada Bruyere Research Institute University of Ottawa School of Electrical Engineering and Computer Science OttawaON Canada Carleton University Bruyere Research Institute Systems and Computer Engineering OttawaON Canada University of Ottawa Sleep Research Unit U. of Ottawa Institute for Mental Health Research at the Royal School of Psychology OttawaON Canada University of Ottawa Institute for Mental Health Research at the Royal Sleep Research Unit OttawaON Canada Royal Ottawa Mental Health Center Sleep Research Unit U. of Ottawa Institute for Mental Health Research at the Royal Sleep Disorders Clinic OttawaON Canada Carleton University Bruyere Research Institute Faculty of Medicine University of Ottawa Systems and Computer Engineering Ottawa Canada

ISBN: (纸本)9781665493840

Polysomnography, the gold standard of sleep measurement, is a time-intensive, costly, and rather invasive procedure. Using under-bed pressure sensor arrays data simultaneously recorded with standard polysomnography, this study demonstrates that deep learning can be used to classify body position and differentiate sleep from wake. All measurements were performed in people with suspected sleep disorders referred for clinical assessments at a sleep laboratory. To perform the classification tasks, we used supervised learning and temporal convolution networks. Performance was assessed with leave-one-out cross validation on 84 participants for body position classification and 70 participants for sleep-wake classification. Results demonstrate that a pressure sensor array placed under the mattress with less than 100 sensors can outperform previous sleep-wake detection methods and is competitive with previous methods for body position classification. Our pressure sensor arrays differ from the mats used in previous work as they use significantly less sensors and are located under the mattress, making them less obtrusive. This tool has great potential as a cost-efficient mean of assessing sleep while reducing patient burden and the workload of specialized staff. © 2023 IEEE.

关键词： Wakes

来源：评论

学校读者我要写书评

暂无评论

Hybrid Quantum-Classical Computing in Federated Learning With Data Heterogeneity 35

Hybrid Quantum-Classical Computing in Federated Learning Wit...

引用

35th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2024

作者： Hisamori, Keita Chiang, Yi-Han Lin, Hai Ji, Yusheng Osaka Metropolitan University Department of Electrical and Electronic Systems Engineering Osaka Japan National Institute of Informatics Information Systems Architecture Science Research Division Tokyo Japan

ISBN: (纸本)9798350362244

Federated learning (FL) has emerged as a promising technique to realize distributed machine learning (ML) in practice. FL enables multiple clients to collaboratively train a common ML model without the need to collect raw data from clients, which therefore has merit in the protection of data privacy. On the other hand, it is known that quantum computing excels in solving specific problems that are computationally prohibitive on classical computers due to its ability to harness quantum superposition and entanglement. However, current noisy intermediate-scale quantum (NISQ) computers have difficulties in dealing with many-qubit computation due to the lack of reliable error-correction schemes, which renders hybrid quantum-classical computing with few qubits a promising alternative. In this paper, we investigate how hybrid quantum-classical computing can be applied to FL while considering the data heterogeneity among clients. To this end, we propose the two-qubit quantum circuit-embedded convolutional neural network (2QCNN) for each client, which incorporates parallel two-qubit variational quantum circuits (VQCs) between the fully connected layers of the CNN. Simulation results show that 2QCNN outperforms the comparison schemes in terms of test accuracies. In addition, the impacts of the number and depth of parallel two-qubit VQCs on the performance of 2QCNN under various degrees of data heterogeneity are further evaluated. © 2024 IEEE.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Low-dose CT image denoising based on residual attention mechanism 6

Low-dose CT image denoising based on residual attention mech...

引用

6th International Conference on Information Science, electrical, and Automation engineering, ISEAE 2024

作者： Zhao, Heng Zhu, Yaqi Yao, Yudong Research Institute for Medical and Biological Engineering Ningbo University Ningbo315211 China Department of Electrical and Computer Engineering Stevens Institute of Technology HobokenNJ07030 United States

ISBN: (纸本)9781510682924

There are complex image noises in LDCT images. Among the existing deep learning models, although there are many excellent models that can restrain the noise of LDCT images, the denoised images of these models will produce a smooth effect and some will be lost. Image details. To improve the image quality and strengthen the correlation between feature channels, inspired by the REDCNN network and CBAM module, this paper proposes an improved REDCNN network (CASA-REDCNN) based on the attention mechanism. By adding channel attention and spatial attention to the residual connection part of REDCNN, the attention module can distinguish the differences between feature channels, focus more attention on channels containing noise and artifacts, and reduce attention on other channels. force. Experiments show that this network can effectively reduce noise and artifacts in LDCT images, and can retain more image details in key areas. It also has good denoising capabilities for LDCT images with different noise levels, proving that this network has good denoising ability and improves the performance of the original model. © 2024 SPIE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Waveform Estimation from Nonlinear systems Using Machine Learning for Rapid Simulation and Design 6

Waveform Estimation from Nonlinear Systems Using Machine Lea...

引用

6th Annual IEEE research and Applications of Photonics in Defense Conference, RAPID 2023

作者： Krzyston, J. Lippiatt, D. Bhattacharjea, R. Stark, A. Ralph, S.E. School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta30332 United States Georgia Tech Research Institute Electro-Optical Systems Laboratory Atlanta30318 United States

ISBN: (纸本)9781665423526

Simulating nonlinear systems featuring a dynamic DSP module is cumbersome, e.g., fiber transport with digital coherent receivers. Machine Learning is used to quickly and accurately estimate waveforms transported through multi-span fiber links over multiple launch powers and OSNRs. Replacing simulation techniques with ML is considered. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Near-Optimal Air Vehicle Energy Management Algorithm Using Surrogate Model 43

A Near-Optimal Air Vehicle Energy Management Algorithm Using...

引用

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

作者： Hsieh, Chao-Yi Wang, Yu-Shun National Chung-Shan Institute of Science and Technology Aeronautical Systems Research Division Avionics and Electrical Engineering Department Taichung40722 Taiwan

ISBN: (纸本)9798350349610

This work aims to introduce the primarily functionalities of the fighter cruise energy management (EM) problems, including Endurance (EDR), Range (RNG), and Home (HOME);discusses the optimization methods wildly used to address this issue (dynamic programming, direct method, and indirect method). The characteristics and limitations of these methods are explained, and the combination of dimensionless analysis and iterative-based method is eventually proposed. First, the relative equation of the overall system is derived. Then the complete data is iteratively generated, to figure out the optimal solution, and constructs an optimization database. Due to the real-time requirement of the fighter's application, this work applies the least squares method (LS) to establish a three-dimensional surrogate model to replace the original database, thereby improving the overall algorithm efficiency. By using the iterative-based method, the simulation results show that the SSE of the surrogate model is 0.0187, indicating excellent approximation. Additionally, the estimation of optimal airspeed takes only 0.002129 seconds, exhibiting good real-time performance. Thus, it can effectively replace the original complex and time-consuming model. © 2024 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Patterned graphene oxide via one-step thermal annealing for controlling collective cell migration

引用

Journal of Materials Chemistry B 2024年第35期12卷 8733-8745页

作者： Huang, Chien-Yu Chen, Chong-You Wei, Chia-Hung Yang, Jia-Wei Lin, Yu-Chien Kao, Chih-Fei Chung, Johnson H. Y. Chen, Guan-Yu Institute of Biomedical Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Department of Electrical and Computer Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Department of Biological Science and Technology College of Biological Science and Technology National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Intelligent Polymer Research Institute Institute for Innovative Materials University of Wollongong NSW2500 Australia National Yang Ming Chiao Tung University Hsinchu300093 Taiwan

Graphene oxide (GO) is a two-dimensional metastable nanomaterial. Interestingly, GO formed oxygen clusterings in addition to oxidized and graphitic phases during the low-temperature thermal annealing process, which could be further used for biomolecule bonding. By harnessing this property of GO, we created a bio-interface with patterned structures with a common laboratory hot plate that could tune cellular behavior by physical contact. Due to the regional distribution of oxygen clustering at the interface, we refer to it as patterned annealed graphene oxide (paGO). In addition, since the paGO was a heterogeneous interface and bonded biomolecules to varying degrees, arginine-glycine-aspartic acid (RGD) was modified on it and successfully regulated cellular-directed growth and migration. Finally, we investigated the FRET phenomenon of this heterogeneous interface and found that it has potential as a biosensor. The paGO interface has the advantages of easy regulation and fabrication, and the one-step thermal reduction method is suitable for biological applications. We believe that this low-temperature thermal annealing method would make GO interfaces more accessible, especially for the development of nano-interfacial modifications for biological applications, revealing its potential for biomedical applications. © 2024 The Royal Society of Chemistry.

关键词： Biomolecules

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：