检索结果-内蒙古大学图书馆

Towards an Analytical Definition of Sufficient Data

SN computer science 2023年第2期4卷 1-23页

作者： Byerly, Adam Kalganova, Tatiana Department of Electronic and Electrical Engineering Brunel University London Uxbridge UB8 3PH United Kingdom Department of Computer Science and Information Systems Bradley University Peoria 61615 IL United States

We show that, for each of five datasets of increasing complexity, certain training samples are more informative of class membership than others. These samples can be identified a priori to training by analyzing their position in reduced dimensional space relative to the classes’ centroids. Specifically, we demonstrate that for the datasets studied, samples that are nearer to their classes’ centroids are less informative than those that are furthest from them. For all five datasets studied, we show that there is no statistically significant difference between training on the entire training set and when excluding up to 2% of the data nearest to each class’s centroid. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Class separation Data reduction Dataset severability Dimensional reduction UMAP

来源：评论

学校读者我要写书评

暂无评论

Tracking changes using Kullback-Leibler divergence for the continual learning

Tracking changes using Kullback-Leibler divergence for the c...

引用

2022 IEEE International Conference on systems, Man, and Cybernetics, SMC 2022

作者： Basterrech, Sebastian Wozniak, Michal VŠB-Technical University of Ostrava Faculty of Electrical Engineering and Computer Science Ostrava Czech Republic Wroclaw University of Science and Technology Department of Systems and Computer Networks Wroclaw Poland

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Recently, continual learning has received a lot of attention. One of the significant problems is the occurrence of concept drift, which consists of changing probabilistic characteristics of the incoming data. In the case of the classification task, this phenomenon destabilizes the model's performance and negatively affects the achieved prediction quality. Most current methods apply statistical learning and similarity analysis over the raw data. However, similarity analysis in streaming data remains a complex problem due to time limitation, non-precise values, fast decision speed, scalability, etc. This article introduces a novel method for monitoring changes in the probabilistic distribution of multi-dimensional data streams. As a measure of the rapidity of changes, we analyze the popular Kullback-Leibler divergence. During the experimental study, we show how to use this metric to predict the concept drift occurrence and understand its nature. The obtained results encourage further work on the proposed methods and its application in the real tasks where the prediction of the future appearance of concept drift plays a crucial role, such as predictive maintenance. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

An Efficient Federated Transfer Learning Approach for Multi-UAV systems

An Efficient Federated Transfer Learning Approach for Multi-...

引用

National Conference on Communications (NCC)

作者： Vedang Bhupesh Shenvi Nadkarni Sandeep Joshi L. Rajya Lakshmi Department of Computer Science and Information Systems Department of Electrical and Electronics Engineering Birla Institute of Technology and Science Pilani Rajasthan India

ISBN: (数字)9798331536015

ISBN: (纸本)9798331536022

Recent advances in multi-unmanned aerial vehicle (UAV) based federated learning do not take into consideration the massive computational requirements of modern deep learning models on mobile UAV s. Additionally, there has been significant progress that shows that the information transmitted between the federated agent and the central hub can be attacked to undermine the privacy of the data. We propose a novel multi-UAV-based federated transfer learning system that drastically reduces the computational burden overall, shifts it from UAV s to the ground fusion center, and reduces the bandwidth requirements while enhancing its secure nature. The proposed system makes multi-UAV learning significantly fast, reliable, power efficient, and practically feasible. Furthermore, we provide simulation and experimental results to demonstrate the effectiveness of the proposed system.

关键词： Deep learning Image segmentation Data privacy Federated learning Power supplies Transfer learning Object detection Autonomous aerial vehicles Data models Reliability

来源：评论

学校读者我要写书评

暂无评论

Deep CNN Model for Multimodal Medical Image Denoising

引用

computers, Materials & Continua 2022年第11期73卷 3795-3814页

作者： Walid El-Shafai Amira A.Mahmoud Anas M.Ali El-Sayed M.El-Rabaie Taha E.Taha Osama F.Zahran Adel S.El-Fishawy Naglaa F.Soliman Amel A.Alhussan Fathi E.Abd El-Samie Department Electronics and Electrical Communications Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Security Engineering Laboratory Department of Computer SciencePrince Sultan UniversityRiyadh11586Saudi Arabia Alexandria Higher Institute of Engineering&Technology(AIET) AlexandriaEgypt Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadhSaudi Arabia

In the literature,numerous techniques have been employed to decrease noise in medical image modalities,including X-Ray(XR),Ultrasonic(Us),Computed Tomography(CT),Magnetic Resonance Imaging(MRI),and Positron Emission Tomography(PET).These techniques are organized into two main classes:the Multiple Image(MI)and the Single Image(SI)*** the MI techniques,images usually obtained for the same area scanned from different points of view are used.A single image is used in the entire procedure in the SI *** denoising techniques can be carried out both in a transform or spatial *** paper is concerned with single-image noise reduction techniques because we deal with single medical *** most well-known spatial domain noise reduction techniques,including Gaussian filter,Kuan filter,Frost filter,Lee filter,Gabor filter,Median filter,Homomorphic filter,Speckle reducing anisotropic diffusion(SRAD),Nonlocal-Means(NL-Means),and Total Variation(TV),are ***,the transform domain noise reduction techniques,including wavelet-based and Curvelet-based techniques,and some hybridization techniques are ***,a deep(Convolutional Neural Network)CNN-based denoising model is proposed to eliminate Gaussian and Speckle noises in different medical image *** model utilizes the Batch Normalization(BN)and the ReLU as a basic *** a result,it attained a considerable improvement over the traditional *** previously mentioned techniques are evaluated and compared by calculating qualitative visual inspection and quantitative parameters like Peak Signal-to-Noise Ratio(PSNR),Correlation Coefficient(Cr),and system complexity to determine the optimum denoising algorithm to be applied *** on the quality metrics,it is demonstrated that the proposed deep CNN-based denoising model is efficient and has superior denoising performance over the traditionaldenoising techniques.

关键词： Image enhancement medical imaging speckle noise Gaussian noise denoising filters CNN denoising

来源：评论

学校读者我要写书评

暂无评论

Subwavelength Fano Resonant Porous Silicon Metasurfaces for Sensing and Dynamic Structural Color

Subwavelength Fano Resonant Porous Silicon Metasurfaces for ...

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Gafsi, Saddam Dos Santos, Estevao Marques Kravchenko, Ivan Ryckman, Judson D. Holcombe Department of Electrical and Computer Engineering Clemson University ClemsonSC29634 United States Center for Nanophase Materials Science Oak Ridge National Laboratory Oak RidgeTN37831 United States

ISBN: (纸本)9781957171395

We introduce the design, fabrication, and experimental investigation of subwavelength Fano resonant porous silicon metasurfaces functioning on the principle of guided mode resonance. These metasurfaces exhibit promise for dynamic structural coloration and sensing applications. CLEO 2024 © Optica Publishing Group 2024 © 2024 The Author(s)

关键词： Mesoporous materials

来源：评论

学校读者我要写书评

暂无评论

Tuning the number of chiral edge channels in a fixed quantum anomalous Hall system

引用

Physical Review B 2024年第20期109卷 L201402-L201402页

作者： Peng Deng Yulei Han Peng Zhang Su Kong Chong Zhenhua Qiao Kang L. Wang Beijing Academy of Quantum Information Sciences Beijing 100193 China Department of Electrical and Computer Engineering University of California Los Angeles California 90095 USA Department of Physics Fuzhou University Fuzhou Fujian 350108 China International Center for Quantum Design of Functional Materials CAS Key Laboratory of Strongly-Coupled Quantum Matter Physics and Department of Physics University of Science and Technology of China Anhui 230026 China Hefei National Laboratory University of Science and Technology of China Hefei 230088 China

Quantum anomalous Hall (QAH) insulators exhibit chiral edge channels characterized by vanishing longitudinal conductance and quantized Hall conductance of Ce2/h, wherein the Chern number C is an integer equal to the number of the parallel chiral edge channels. These chiral edge channels conduct dissipationless transport in QAH insulators, making them pivotal for applications in low-consumption electronics and topological quantum computing. While the QAH effect with multiple chiral edge channels (i.e., C > 1) has been demonstrated in multilayers consisting of magnetic topological insulators and normal insulators, the channel number remains fixed for a given sample. Here, we unveil the tunability of the number of chiral edge channels within a single QAH insulator device. By tuning the magnetization of individual layers within the multilayer system, Chern insulating states with different Chern numbers are unveiled. The tunable Chern number was corroborated by our theoretical calculations. Furthermore, we conducted layer-dependent calculations to elucidate the contribution of the Chern number from different layers in the multilayer. Our findings demonstrate an extra degree of freedom in manipulating the chiral edge channels in QAH insulators. This tunability offers an extra dimension for the implementation of the QAH-based multichannel dissipationless transport.

关键词： Quantum anomalous Hall effect Quantum transport Topological insulators Molecular beam epitaxy

来源：评论

学校读者我要写书评

暂无评论

Subwavelength Fano Resonant Porous Silicon Metasurfaces for Sensing and Dynamic Structural Color

Subwavelength Fano Resonant Porous Silicon Metasurfaces for ...

引用

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

关键词： Porous materials

来源：评论

学校读者我要写书评

暂无评论

A Multi-Sequence Prophet Inequality Under Observation Constraints

A Multi-Sequence Prophet Inequality Under Observation Constr...

引用

IEEE International Symposium on Information Theory

作者： Aristomenis Tsopelakos Olgica Milenkovic Department of Electrical and Computer Engineering Coordinated Science Laboratory University of Illinois at Urbana-Champaign

ISBN: (数字)9798350382846

ISBN: (纸本)9798350382853

In our problem, we are given access to a number of sequences of nonnegative i.i.d. random variables, whose realizations are observed sequentially. All sequences are of the same finite length. The goal is to pick one element from each sequence in order to maximize a reward equal to the expected value of the sum of the selections from all sequences. The decision on which element to pick is irrevocable, i.e., rejected observations cannot be revisited. Furthermore, the procedure terminates upon having a single selection from each sequence. Our observation constraint is that we cannot observe the current realization of all sequences at each time instant. Instead, we can observe only a smaller, yet arbitrary, subset of them. Thus, together with a stopping rule that determines whether we choose or reject the sample, the solution requires a sampling rule that determines which sequence to observe at each instant. The problem can be solved via dynamic programming, but with an exponential complexity in the length of the sequences. In order to make the solution computationally tractable, we introduce a decoupling approach and determine each stopping time using either a single-sequence dynamic programming, or a Prophet Inequality inspired threshold method, with polynomial complexity in the length of the sequences. We prove that the decoupling approach guarantees at least 0.745 of the optimal expected reward of the joint problem. In addition, we describe how to efficiently compute the optimal number of samples for each sequence, and its' dependence on the variances.

关键词： Polynomials Finite element analysis Dynamic programming Complexity theory Random variables Information theory

来源：评论

学校读者我要写书评

暂无评论

A Cyber-Physical Smart Grid Testbed for Validation of GOOSE-Based Protection Strategies

A Cyber-Physical Smart Grid Testbed for Validation of GOOSE-...

引用

2022 IEEE Industry Applications Society Annual Meeting, IAS 2022

作者： Abdelrahman, Mahmoud S. Kharchouf, Ibtissam Alrashide, Abdulmueen Mohammed, Osama A. Florida International University Energy Systems Research Laboratory Department of Electrical and Computer Engineering MiamiFL33174 United States

ISBN: (数字)9781665478151

ISBN: (纸本)9781665478151

Although smart grid technologies bring valuable economic, social, and environmental benefits, testing the combination of heterogeneous and co-existing cyber-physical grid structure with legacy technologies presents many challenges. To overcome these challenges without adversely affecting the real-time environment, testbeds are required to explore, develop, evaluate, and validate security controls and protection algorithms in the power system. This paper presents an improved hardware/software design of the smart grid testbed at the Energy systems Research laboratory, Florida International University. The hardware/software-based system includes implementing protection and control strategies for power systems with industrial-grade commercial devices to represent the holistic real-time operation of smart power grid. By leveraging resources available at FIU's smart grid testbed, an in-depth experimental analysis is performed to demonstrate and verify the successful operation of the GOOSE publish-subscribe protocol towards the substation protection within the smart grid setup. © 2022 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Comparison of multi-distance and multi-frequency methods in frequency-domain near-infrared spectroscopy 15

Comparison of multi-distance and multi-frequency methods in ...

引用

Optical Tomography and Spectroscopy of Tissue XV 2023

作者： Abdalsalam, Ola Ross, Nicholas Perkins, Guy A. Dale, Robin Dehghani, Hamid O’Sullivan, Thomas D. Ferradal, Silvina L. Department of Electrical Engineering University of Notre Dame IN46556 United States School of Computer Science University of Birmingham Birmingham United Kingdom Department of Intelligent Systems Engineering Indiana University BloomingtonIN47408 United States

ISBN: (纸本)9781510658578

Functional Near-Infrared Spectroscopy (fNIRS) is a non-invasive, non-ionizing imaging tool that can map brain hemodynamics. While not the most common fNIRS approach, frequency-domain NIRS (FD-NIRS) has shown an ability to estimate the absolute optical properties of tissues and, consequently, accurately estimate tissue chromophores concentrations. FD-NIRS can probe different depths in the tissue using multiple source-detector separations (multi-distance) or multiple modulation frequencies (multi-frequency). In this work, through experimental and simulation results, we demonstrate that using multi-distance and multi-frequency FD-NIRS yields similar results when estimating the optical properties of homogeneous and multi-layered tissues with less than ±10% error in estimations. We also examined some parameters that can affect the accuracy of the estimated optical properties, such as using different modulation frequencies in a multi-distance configuration and different source-detector separations for multi-frequency configuration. © 2023 SPIE.

关键词： Optical properties

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：