检索结果-内蒙古大学图书馆

Robust diffusion LMS with masked measurements

学校读者我要写书评

暂无评论

signal processing 2026年 238卷

作者： Mahdi Shamsi Hadi Zayyani Farokh Marvasti Multimedia and Signal processing Lab (MSL) Advanced Communications Research Institute (ACRI) EE Department of Sharif University of Technology Tehran Islamic Republic of Iran Department of Electrical and Computer Engineering Qom University of Technology (QUT) Qom Islamic Republic of Iran

In distributed algorithms, multiple processing nodes collaborate to achieve a common objective. One such algorithm, the Diffusion Least Mean Square (DLMS), is widely utilized across various applications due to its reliability, robustness, and fast convergence. However, the presence of masked measurements can significantly limit the effectiveness of these algorithms. To address this challenge, this paper presents a comprehensive framework designed to mitigate masking effects while also analyzing the convergence of diffusion strategies. Accordingly, we modify the cost function to promote data exchange among estimator nodes, enhancing data flow across the network and improving the estimation of masked components. We demonstrate how the gradient noise in stochastic gradient descent can be bounded to ensure it grows no faster than the estimation error. The proposed approach is grounded in the minimum disturbance principle and is specifically crafted to counteract the adverse effects of impulsive noise. Our findings show that the proposed method significantly outperforms conventional DLMS approaches in scenarios with masked measurements, improving performance by over 40 dB compared to the standard DLMS and by over 20 dB compared to Mask-aware DLMS in terms of Mean Square Deviation (MSD). This advancement promises enhanced performance and reliability in challenging environments.

关键词： Masked measurement Partial observation Diffusion LMS Distributed estimation Impulsive noise Robust estimation

Fault Diagnosis of Wind Energy Conversion Systems Using Gaussian Process Regression-based Multi-Class Random Forest

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2022年第6期55卷 127-132页

作者： Majdi Mansouri Radhia Fezai Mohamed Trabelsi Hajji Mansour Hazem Nounou Mohamed Nounou Electrical and Computer Engineering Program Texas A&M University at Qatar Doha Qatar Department of Mathematics and Sciences Prince Sultan University Riyadh 11586 Saudi Arabia Research Laboratory of Automation Signal Processing and Image National Engineering School of Monastir 5019 Tunisia Electronic and Communications Engineering Department Kuwait College of Science and Technology P. O. Box 27235 Kuwait Higher Institute of Applied Science and Technology of Kasserine University of Kairouan PO Box 471 1200 Kasserine Tunisia Chemical Engineering Program Texas A&M University at Qatar Doha Qatar

This work proposes a new fault diagnosis approach for a wind energy conversion (WEC) system. The proposed technique merges the benefits of feature extraction based on Gaussian Process Regression (GPR) and Multi-Class Random Forest (MCRF)-based fault classification where instances are classified into one or more classes. In the developed GPR-MCRF approach, the nonlinear statistical features including the mean vector M GPR and the variance matrix C GPR are computed using the GPR model with aim of extracting the most relevant features from the WEC system. Then, these features are introduced to the RF classifier for classification and diagnosis purposes. Therefore, the application of the GPR-MCRF technique for WEC systems aims to enhance the use of the classical raw data-based MCRF and diagnosis accuracy. Three kinds of faults (wear-out, open-circuit, and short-circuit faults) are considered in this work. Different case studies are investigated in order to illustrate the effectiveness and robustness of the developed technique compared to the state-of-the-art methods. The obtained results show that the the developed GPR-MCRF technique is an effective feature extraction and fault diagnosis technique for WEC systems.

关键词： Random Forest (RF) Multi-Class Gaussian Process Regression (GPR) Fault Diagnosis Wind Energy Conversion Systems

Resource allocation using deep learning in mobile small cell networks

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2021年

作者： Zafar, Saniya Jangsher, Sobia Al-Dweik, Arafat Wireless and Signal Processing Lab Institute of Space Technology Islamabad Pakistan The Center for Cyber Physical Systems Khalifa University Abu Dhabi United Arab Emirates The Department of Electrical and Computer Engineering Western University LondonON Canada

The deployment of mobile-Small cells (mScs) is widely adopted to intensify the quality-of-service (QoS) in high mobility vehicles. However, the rapidly varying interference patterns among densely deployed mScs make the resource allocation (RA) highly challenging. In such scenarios, RA problem needs to be solved nearly in real-time, which can be considered as drawback for most existing RA algorithms. To overcome this constraint and solve the RA problem efficiently, we use deep learning (DL) in this work due to its ability to leverage the historical data in RA problem and to deal with computationally expensive tasks offline. More specifically, this paper considers the RA problem in vehicular environment comprising of city buses, where DL is explored for optimization of network performance. Simulation results reveal that RA in a network using Long Short-Term Memory (LSTM) algorithm outperforms other machine learning (ML) and DL-based RA mechanisms. Moreover, RA using LSTM provides less accurate results as compared to existing Time Interval Dependent Interference Graph (TIDIG)-based, and Threshold Percentage Dependent Interference Graph (TPDIG)based RA but shows improved results when compared to RA using Global Positioning System Dependent Interference Graph (GPSDIG). However, the proposed scheme is computationally less expensive in comparison with TIDIG and TPDIG-based algorithms. © 2021, CC BY.

关键词： Wireless networks

6G Wireless communications: From Far-field Beam Steering to Near-field Beam Focusing

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Haiyang Shlezinger, Nir Guidi, Francesco Dardari, Davide Eldar, Yonina C. The School of Communication and Information Engineering Nanjing University of Posts and Telecommunications China The School of Electrical and Computer Engineering Ben-Gurion University Israel Electronics Telecommunications and Information Technologies from Ecole Polytechnique Paris-Tech France Computer Science Specialty The University of Bologna Italy IEIIT-CNR Italy The University of Bologna WiLAB-CNIT Italy The Department of Math and Computer Science Weizmann Institute of Science Israel The Center for Biomedical Engineering and Signal Processing The Israel Academy of Sciences and Humanities IEEE Fellow EURASIP Fellow

6G networks will be required to support higher data rates, improved energy efficiency, lower latency, and more diverse users compared with 5G systems. To meet these requirements, electrically extremely large-scale antenna arrays are envisioned to be key physical-layer technologies. As a consequence, it is expected that some portion of future 6G wireless communications may take place in the radiating near-field (Fresnel) region, in addition to the far-field operation as in current wireless technologies. In this article, we discuss the opportunities and challenges that arise in radiating near-field communications. We begin by discussing the key physical characteristics of near-field communications, where the standard plane-wave propagation assumption no longer holds, and clarifying its implication on the modelling of wireless channels. Then, we elaborate on the ability to leverage spherical wavefronts via beam focusing, highlighting its advantages for 6G systems. We point out several appealing application scenarios which, with proper design, can benefit from near-field operation, including interference mitigation in multi-user communications, accurate localization and focused sensing, as well as wireless power transfer with minimal energy pollution. We conclude by discussing some of the design challenges and research directions that are yet to be explored to fully harness the potential of near-field operation. Copyright © 2022, The Authors. All rights reserved.

关键词： Antenna arrays

Single-layer dual-band frequency selective surface for coverage-enhancing applications in millimeter-wave 5G

学校读者我要写书评

暂无评论

Results in Engineering

Results in engineering 2025年 27卷

作者： Mousa Abdollahvand Eduardo Martinez-de-Rioja Kanishka Katoch Ana Arboleya Celia Fontá Department of Electrical and Computer Engineering University of Mohaghegh Ardabili Ardabil Iran Department of Signal Theory and Communications and Telematic Systems and Computing Universidad Rey Juan Carlos 28942 Fuenlabrada Spain Department of Electronics and Communication Engineering JUIT Waknaghat Solan Himachal Pradesh India Information Processing and Telecommunications Center Department of Signals Systems and Radiocommunications Universidad Politecnica de Madrid 28040 Madrid Spain

This work presents a dual-band Frequency Selective Surface (FSS) for improving 5G communications at millimeter-wave bands. The FSS is based on a single-layer configuration which supports dual polarization, with a unit-cell period of 4 mm x 4 mm. The structure exhibits two reflection bands at 28 GHz and 39 GHz. An equivalent circuit model has been developed for the proposed FSS, showing good agreement with full-wave electromagnetic simulations. A 200 mm x 200 mm prototype of the FSS, comprising an array of 50 × 50 unit-cells has been fabricated and tested, and the measured transmission and reflection coefficients agree well with the simulations. Moreover, the frequency response of the FSS shows good stability for incidence angles up to 40°. The proposed single-layer dual-band FSS has applications in the design of smart reflecting surfaces to enhance wireless communications in 5G networks operating at the 28 and 39 GHz bands, either alone or in combination with metasurface or reflectarray elements that could be placed on its upper side.

关键词： 5G communications Coverage enhancement Dual band Electromagnetic skin Frequency selective surface Millimeter waves

Coded Data Rebalancing: Fundamental Limits and Constructions

学校读者我要写书评

暂无评论

Coded Data Rebalancing: Fundamental Limits and Constructions

IEEE International Symposium on Information Theory

作者： Prasad Krishnan V. Lalitha Lakshmi Natarajan Signal Processing & Communications Research Center International Institute of Information Technology Hyderabad India Department of Electrical Engineering Indian Institute of Technology Hyderabad

ISBN: (数字)9781728164328

ISBN: (纸本)9781728164335

Distributed databases often suffer unequal distribution of data among storage nodes, which is known as `data skew'. Data skew arises from a number of causes such as removal of existing storage nodes and addition of new empty nodes to the database. Data skew leads to performance degradations and thus necessitates `rebalancing' at regular intervals to reduce the amount of skew. We define an r-balanced distributed database as a distributed database in which the storage across the nodes has uniform size, and each bit of the data is replicated in r distinct storage nodes. We consider the problem of designing such balanced databases along with associated rebalancing schemes which maintain the r-balanced property under node removal and addition operations. We present a class of r-balanced databases (parameterized by the number of storage nodes) which have the property of structural invariance, i.e., the databases designed for different number of storage nodes have the same structure. For this class of r-balanced databases, we present rebalancing schemes which use coded transmissions between storage nodes, and characterize their communication loads under node addition and removal. We show that the communication cost incurred to rebalance our distributed database for node addition and removal is optimal, i.e., it achieves the minimum possible cost among all possible balanced distributed databases and rebalancing schemes.

关键词：

Faster convergence in deep-predictive-coding networks to learn deeper representations

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sledge, Isaac J. Príncipe, José C. The Advanced Signal Processing and Automated Target Recognition Branch Naval Surface Warfare Center Panama CityFL United States The Department of Electrical and Computer Engineering University of Florida GainesvilleFL United States The Department of Biomedical Engineering University of Florida GainesvilleFL United States

Deep-predictive-coding networks (DPCNs) are hierarchical, generative models. They rely on feed-forward and feed-back connections to modulate latent feature representations of stimuli in a dynamic and context-sensitive manner. A crucial element of DPCNs is a forward-backward inference procedure to uncover sparse, invariant features. However, this inference is a major computational bottleneck. It severely limits the network depth due to learning stagnation. Here, we prove why this bottleneck occurs. We then propose a new forward-inference strategy based on accelerated proximal gradients. This strategy has faster theoretical convergence guarantees than the one used for DPCNs. It overcomes learning stagnation. We also demonstrate that it permits constructing deep and wide predictive-coding networks. Such convolutional networks implement receptive fields that capture well the entire classes of objects on which the networks are trained. This improves the feature representations compared with our lab's previous non-convolutional and convolutional DPCNs. It yields unsupervised object recognition that surpass convolutional autoencoders and are on par with convolutional networks trained in a supervised manner. © 2021, CC BY.

关键词： Convolution

Coded Data Rebalancing: Fundamental Limits and Constructions

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Krishnan, Prasad Lalitha, V. Natarajan, Lakshmi Signal Processing & Communications Research Center International Institute of Information Technology Hyderabad India Department of Electrical Engineering Indian Institute of Technology Hyderabad

Distributed databases often suffer unequal distribution of data among storage nodes, which is known as ‘data skew’. Data skew arises from a number of causes such as removal of existing storage nodes and addition of new empty nodes to the database. Data skew leads to performance degradations and necessitates ‘rebalancing’ at regular intervals to reduce the amount of skew. We define an r-balanced distributed database as a distributed database in which the storage across the nodes has uniform size, and each bit of the data is replicated in r distinct storage nodes. We consider the problem of designing such balanced databases along with associated rebalancing schemes which maintain the r-balanced property under node removal and addition operations. We present a class of r-balanced databases (parameterized by the number of storage nodes) which have the property of structural invariance, i.e., the databases designed for different number of storage nodes have the same structure. For this class of r-balanced databases, we present rebalancing schemes which use coded transmissions between storage nodes, and characterize their communication loads under node addition and removal. We show that the communication cost incurred to rebalance our distributed database for node addition and removal is optimal, i.e., it achieves the minimum possible cost among all possible balanced distributed databases and rebalancing schemes. Copyright © 2020, The Authors. All rights reserved.

关键词： Digital storage

Annotating motion primitives for simplifying action search in reinforcement learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sledge, Isaac J. Bryner, Darshan W. Príncipe, José C. The Advanced Signal Processing and Automated Target Recognition Branch Naval Surface Warfare Center Panama CityFL United States The Branch Head of the Advanced Signal Processing and Automated Target Recognition Branch Naval Surface Warfare Center Panama CityFL32407 United States The Department of Electrical and Computer Engineering The Department of Biomedical Engineering University of Florida GainesvilleFL32611 United States The Computational NeuroEngineering Laboratory University of Florida United States

Reinforcement learning in large-scale environments is challenging due to the many possible actions that can be taken in specific situations. We have previously developed a means of constraining, and hence speeding up, the search process through the use of motion primitives;motion primitives are sequences of pre-specified actions taken across a state series. As a byproduct of this work, we have found that if the motion primitives' motions and actions are labeled, then the search can be sped up further. Since motion primitives may initially lack such details, we propose a theoretically viewpoint-insensitive and speed-insensitive means of automatically annotating the underlying motions and actions. We do this through a differential-geometric, spatio-temporal kinematics descriptor, which analyzes how the poses of entities in two motion sequences change over time. We use this descriptor in conjunction with a weighted-nearest-neighbor classifier to label the primitives using a limited set of training examples. In our experiments, we achieve high motion and action annotation rates for human-action-derived primitives with as few as one training sample. We also demonstrate that reinforcement learning using accurately labeled trajectories leads to high-performing policies more quickly than standard reinforcement learning techniques. This is partly because motion primitives encode prior domain knowledge and preempt the need to re-discover that knowledge during training. It is also because agents can leverage the labels to systematically ignore action classes that do not facilitate task objectives, thereby reducing the action space. © 2021, CC BY.

关键词： Reinforcement learning