检索结果-内蒙古大学图书馆

High-performance 5.5 THz coplanar waveguide-fed circular dielectric resonator antenna: a dual-band solution for advanced THz applications

引用

Optical and Quantum Electronics 2024年第12期56卷 1-19页

作者： Rathinakumar, Perinbaraj Vijayalakshmi, K. Department of Signal and Image Processing Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India

An improved circular dielectric resonator antenna (CDRA) with a gain of 5.5 THz and excitation via a keyhole-shaped coplanar waveguide (CPW) is detailed in this research. The structure's feed and ground materials are silver, the substrate is silicon dioxide, and the dielectric resonator antenna (DRA) is silicon. The DRA is 5 μm in radius and 15 Εm in height, and it is placed on a substrate that is 90 × 90 × 20 μm in size. An S11 value of –16.328 dB and a principal resonant frequency of 5.5 THz indicate that the antenna matches impedances admirably and scatters signals with minimal effect. Furthermore, the possibility of dual-band operation is demonstrated by a secondary resonance at 8.6 THz with an S11 of –6.7614 dB. With an operational bandwidth centered on 5.6 THz and a range of 5.0–6.2 THz, it is highly adaptable and may be used for a variety of applications. With a radiation efficiency of 68% and a peak gain of around 19 dB, this antenna exhibits a multi-lobe radiation pattern that is both highly gainful and highly directed. Phased array antennas, terahertz imaging systems, and autonomous vehicles and unmanned aerial vehicles (UAVs) can all benefit from these. Antenna performance is improved due to the creation of orthogonal and higher-order modes, which increase radiation efficiency and lead to high gain. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Antenna lobes

来源：评论

学校读者我要写书评

暂无评论

Training Deep Neural Classifiers with Soft Diamond Regularizers 23

Training Deep Neural Classifiers with Soft Diamond Regulariz...

引用

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Adigun, Olaoluwa Kosko, Bart Signal and Image Processing Institute Department of Electrical and Computer Engineering Los AngelesCA90089-2564 United States

ISBN: (纸本)9798350374889

We introduce new soft diamond regularizers that both improve synaptic sparsity and maintain classification accuracy in deep neural networks. These parametrized regularizers outperform the state-of-the-art hard-diamond Laplacian regularizer of Lasso regression and classification. They use thick-tailed symmetric alpha-stable (Sa S) bell-curve synaptic weight priors that are not Gaussian and so have thicker tails. The geometry of the diamond-shaped constraint set varies from a circle to a star depending on the tail thickness and dispersion of the prior probability density function. Training directly with these priors is computationally intensive because almost all Sa S probability densities lack a closed form. A precomputed lookup table removed this computational bottleneck. We tested the new soft diamond regularizers with deep neural classifiers on the three datasets CIFAR-10, CIFAR-100, and Caltech-256. The regularizers improved the accuracy of the classifiers. The improvements included 4.57% on CIFAR-10, 4.27% on CIFAR-100, and 6.69% on Caltech-256. They also outperformed L2 regularizers on all the test cases. Soft diamond regularizers also outperformed L1 lasso or Laplace regularizers because they better increased sparsity while improving classification accuracy. Soft-diamond priors substantially improved accuracy on CIFAR-10 when combined with dropout, batch, or data-augmentation regularization. © 2024 IEEE.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Backpropagation Autoencoding Networks for image Compression and Denoising 22

Bidirectional Backpropagation Autoencoding Networks for Imag...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Adigun, Olaoluwa Kosko, Bart Signal and Image Processing Institute Department of Electrical and Computer Engineering Los AngelesCA90089-2564 United States

ISBN: (纸本)9798350345346

A bidirectional autoencoder learns or approximates an identity mapping as it trains a single network with a version of the new bidirectional backpropagation algorithm. Ordinary unidirectional autoencoders find many uses in image processing and in large language models. But they use separate networks for encoding and decoding. Bidirectional auto encoders use the same synaptic weights for encoding and decoding. The forward pass encodes while the backward pass decodes. Bidirectional auto encoders improved network performance and significantly reduced memory usage and used fewer parameters. Simulations compared unidirectional with bidirectional autoencoders for image compression and de noising. The models trained on the MNIST handwritten-digit and CIFAR-IO image datasets. The performance measures were the peak signal-to-noise ratio and the index of structural similarity. Bidirectional autoencoders outperformed unidirectional autoencoders and still reduced the number of trainable synaptic parameters by about 50%. © 2023 IEEE.

关键词： autoencoders bidirectional au-toencoders Bidirectional backpropagation bidirectional networks large language models variational autoencoders

来源：评论

学校读者我要写书评

暂无评论

In-band full-duplex MIMO PLC systems for relaying networks

引用

Digital Communications and Networks 2025年第1期11卷 145-159页

作者： Francisco J.Canete Gautham Prasad Lutz Lampe Communications and Signal Processing Lab Telecommunication Research Institute(TELMA)ETS Ingenieria TelecomunicacionUniversidad de MalagaSpain Ofinno RestonVAUSA Department of Electrical and Computer Engineering The University of British ColumbiaCanada

In Power Line Communications(PLC),there are regulatory masks that restrict the transmit power spectral density for electromagnetic compatibility reasons,which creates coverage issues despite the not too long ***,PLC networks often employ repeaters/relays,especially in smart grid neighborhood area *** in broadband indoor PLC systems that offer a notable data rate,relaying may pave the way to new applications like being the backbone for wireless technologies in a cost-effective manner to support the Internet-of-things *** this paper,we study Multiple-Input Multiple-Output(MIMO)PLC systems that incorporate inband full-duplex functionality in relaying *** present several MIMO configurations that allow end-to-end half-duplex or full-duplex operations and analyze the achievable performance with state-of-the-art PLC *** reach this analysis,we get channel realizations from random network layouts for indoor and outdoor *** adopt realistic MIMO channel and noise models and consider transmission techniques according to PLC *** concepts discussed in this work can be useful in the design of future PLC relay-aided networks for different applications that look for a coverage extension and/or throughput:smart grids with enhanced communications in outdoor scenarios,and“last meter”systems for high-speed connections everywhere in indoor ones.

关键词： PLC MIMO Relaying networks OFDM Spatial correlation Performance analysis

来源：评论

学校读者我要写书评

暂无评论

Sign Language Recognition using Spiking Neural Networks 2

Sign Language Recognition using Spiking Neural Networks

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Chaudhari, Pranav Vicente-Sola, Alex Basu, Amlan Manna, Davide L. Kirkland, Paul Caterina, Gaetano Di Department of Information and Communication Technology Manipal Institute of Technology Manipal Academy of Higher Education Manipal576104 India Neuromorphic Sensor Signal Processing Lab Centre for Image and Signal Processing Electrical and Electronic Engineering Department University of Strathclyde Glasgow United Kingdom

In recent years, research in automatic Sign Language Recognition (SLR) has undergone significant progress, serving as a founda-tional base for developing applications that aim to promote the integration of deaf individuals into society. Most of this progress is owed to the recent developments in deep learning. However, the deployment of conventional Artificial Neural Networks (ANNs) can be hindered by their requirements in terms of computational power and energy consumption. Therefore, to improve the ef-ciency of current SLR systems, in this work, we propose the use of the increasingly popular Spiking Neural Networks (SNNs), which, on the one hand, provide more energy-efficient computations than conventional ANNs and, on the other hand, are able to process temporal sequences with simpler architectures thanks to their temporal dynamics. To evaluate our method, we utilize WLASL300, the 300-word (300 classes of signs) dataset from Word-Level American Sign Language, and achieve an improvement in accuracy with the SNN (+2.70%) over the previous state-of-the-art, when working with energy-efficient spiking neurons. Furthermore, we construct a non-spiking version of the same network and evaluate it in a similar manner. Our results demonstrate how the SNN has sparser activations (25% less), thanks to the use of spiking neurons, and therefore can be implemented with a lower power requirement than an ANN version of the same architecture. This work thus demonstrates the possibility of performing SLR in a very effective and efficient way, thus opening up the development of applications that span from the automatic real-time translation of dynamic signs to remote control utilizing sign languages. © 2024 Elsevier B.V.. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

2D MXene Ti_(3)C_(2)T_(x)Enhanced Plasmonic Absorption in Metasurface for Terahertz Shielding

引用

Computers, Materials & Continua 2023年第5期75卷 3453-3464页

作者： Zaka Ullah Muath Al Hasanl Ismail Ben Mabrouk Muhammad Junaid Fawad Sheikh Faculty of Electrical Engineering College of EngineeringAl Ain UniversityAl Ain64141UAE Department of Electrical Engineering Durham UniversityDurhamUK Department of Electrical Engineering Baluchistan University of Technology and management sciencesQuettaPakistan Institute of Digital Signal Processing Universitat Duisburg EssenDuisburgGermany

With the advancement of technology,shielding for terahertz(THz)electronic and communication equipment is increasingly *** metamaterial absorption technique is mostly used to shield electromagnetic interference(EMI)in THz sensing *** most widely used THz metamaterial absorbers suffer from their narrowband properties and the involvement of complex fabrication *** with multifunctional properties,such as adjustable conductivity,broad bandwidth,high flexibility,and robustness,are driving future development to meet THz shielding *** this article,a theoretical simulation approach based on finite difference time domain(FDTD)is utilized to study the absorption and shielding characteristics of a two-dimensional(2D)MXene Ti_(3)C_(2)T_(x) metasurface absorber in the THz *** proposed metamaterial structure is made up of a square-shaped array of MXene that is 50 nmthick and is placed on top of a silicon *** bottom surface of the silicon is metalized with gold to reduce the transmission and ultimately enhance the absorption at 1–3 *** symmetric adjacent space between theMXene array results in a widening of *** proposed metasurface achieves 96%absorption under normal illumination of the incident source and acquires an average of 25 dB shielding at 1 THz bandwidth,with the peak shielding reaching 65 *** results show that 2D MXene-based stacked metasurfaces can be proven in the realization of low-cost devices for THz shielding and sensing applications.

关键词： EMI shielding terahertz plasmonic absorber metasurface

来源：评论

学校读者我要写书评

暂无评论

Training Deep Neural Classifiers with Soft Diamond Regularizers

Training Deep Neural Classifiers with Soft Diamond Regulariz...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Olaoluwa Adigun Bart Kosko Department of Electrical and Computer Engineering Signal and Image Processing Institute Los Angeles California

ISBN: (数字)9798350374889

ISBN: (纸本)9798350374896

We introduce new soft diamond regularizers that both improve synaptic sparsity and maintain classification accuracy in deep neural networks. These parametrized regularizers outperform the state-of-the-art hard-diamond Laplacian regularizer of Lasso regression and classification. They use thick-tailed symmetric alpha-stable $(\mathcal{S}\alpha \mathcal{S})$ bell-curve synaptic weight priors that are not Gaussian and so have thicker tails. The geometry of the diamond-shaped constraint set varies from a circle to a star depending on the tail thickness and dispersion of the prior probability density function. Training directly with these priors is computationally intensive because almost all $\mathcal{S}\alpha \mathcal{S}$ probability densities lack a closed form. A precomputed lookup table removed this computational bottleneck. We tested the new soft diamond regularizers with deep neural classifiers on the three datasets CIFAR-10, CIFAR-100, and Caltech-256. The regularizers improved the accuracy of the classifiers. The improvements included 4.57% on CIFAR-10, 4.27% on CIFAR-100, and 6.69% on Caltech-256. They also outperformed $L_{2}$ regularizers on all the test cases. Soft diamond regularizers also outperformed $L_{1}$ lasso or Laplace regularizers because they better increased sparsity while improving classification accuracy. Soft-diamond priors substantially improved accuracy on CIFAR-10 when combined with dropout, batch, or data-augmentation regularization.

关键词： Training Accuracy Sparse approximation Stars Tail Machine learning Probability density function Diamond Table lookup Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

FastNet for Symbol Detection in Massive MIMO Systems 9

FastNet for Symbol Detection in Massive MIMO Systems

引用

9th IEEE International Conference on Electronics, Computing and Communication Technologies, CONECCT 2023

作者： Bhattacharya, Swati Hari, K.V.S. Indian Institute of Science Statistical Signal Processing Lab Department of Electrical Communication Engineering Bangalore India

ISBN: (纸本)9798350334395

In massive multiple-input-multiple-output (MIMO) systems, a major limiting factor for symbol detection is the amount of computational complexity required. Symbol detection in unquantized massive MIMO systems have been studied in the context of both traditional and machine learning methods. In this paper, we propose a hybrid framework that replaces some neural network layers with simple gradient descent layers to reduce complexity. Simulations showed that a judicious choice of the number of such layers can lead to significant reduction in the range of 35-50%, in computational complexity, with marginal change in performance. © 2023 IEEE.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Controlled Causal Hallucinations Can Estimate Phantom Nodes in Multiexpert Mixtures of Fuzzy Cognitive Maps

arXiv

引用

arXiv 2024年

作者： Panda, Akash Kumar Kosko, Bart Signal and Image Processing Institute Department of Electrical and Computer Engineering University of Southern California United States

An adaptive multiexpert mixture of feedback causal models can approximate missing or phantom nodes in large-scale causal models. The result gives a scalable form of big knowledge. The mixed model approximates a sampled dynamical system by approximating its main limit-cycle equilibria. Each expert first draws a fuzzy cognitive map (FCM) with at least one missing causal node or variable. FCMs are directed signed partial-causality cyclic graphs. They mix naturally through convex combination to produce a new causal feedback FCM. Supervised learning helps each expert FCM estimate its phantom node by comparing the FCM's partial equilibrium with the complete multi-node equilibrium. Such phantom-node estimation allows partial control over these causal hallucinations and helps approximate the future trajectory of the dynamical system. But the approximation can be computationally heavy. Mixing the tuned expert FCMs gives a practical way to find several phantom nodes and thereby better approximate the feedback system's true equilibrium behavior. Copyright © 2024, The Authors. All rights reserved.

关键词： Phantoms

来源：评论

学校读者我要写书评

暂无评论

Learning Structured Compressed Sensing with Automatic Resource Allocation

Learning Structured Compressed Sensing with Automatic Resour...

引用

2025 IEEE International Conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Wang, Han Pérez, Eduardo Huijben, Iris A.M. van Gorp, Hans van Sloun, Ruud Römer, Florian Applied AI Signal Processing and Data Analysis Fraunhofer Institute for Nondestructive Testing IZFP Germany Department of Electrical Engineering Eindhoven University of Technology Netherlands Electronic Measurements and Signal Processing Ilmenau University of Technology Germany

ISBN: (纸本)9798350368741

Multidimensional data acquisition often requires extensive time and poses significant challenges for hardware and software regarding data storage and processing. Rather than designing a single compression matrix as in conventional compressed sensing, structured compressed sensing yields dimension-specific compression matrices, reducing the number of optimizable parameters. Recent advances in machine learning (ML) have enabled task-based supervised learning of subsampling matrices, albeit at the expense of complex downstream models. Additionally, the sampling resource allocation across dimensions is often determined in advance through heuristics. To address these challenges, we introduce Structured COmpressed Sensing with Automatic Resource Allocation (SCOSARA) with an information theory-based unsupervised learning strategy. SCOSARA adaptively distributes samples across sampling dimensions while maximizing Fisher information content. Using ultrasound localization as a case study, we compare SCOSARA to state-of-the-art ML-based and greedy search algorithms. Simulation results demonstrate that SCOSARA can produce high-quality subsampling matrices that achieve lower Cramér Rao Bound values than the baselines. In addition, SCOSARA outperforms other ML-based algorithms in terms of the number of trainable parameters, computational complexity, and memory requirements while automatically choosing the number of samples per axis. © 2025 IEEE.

关键词： Compressed Sensing Information Theory Subsampling Unsupervised Learning

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：