检索结果-内蒙古大学图书馆

Asilomar Conference on signals, Systems & Computers

作者： Kai-Bor Yu GE Corporate Research and Development Center Schenectady NY USA

暂无评论

Soft Symbol Decoding in Sweep-Spread-Carrier Underwater Acoustic Communications: A Novel Variational Bayesian Algorithm and Its Analysis

引用

IEEE TRANSACTIONS ON signal processing 2020年 68卷 2435-2448页

作者： Arunkumar, K. P. Murthy, Chandra R. Naval Phys Oceanog Lab Kochi 682021 Kerala India Indian Inst Sci Dept ECE Bangalore 560012 Karnataka India

Sweep spread carrier (S2C) based underwater acoustic (UWA) communications is a practically attractive but less explored modulation scheme in the published literature. In this paper, we present a rigorous treatment of the S2C communication receiver design and propose a data detection scheme that can handle challenging UWA channels. State-of-the-art S2C receivers based on the gradient heterodyne processing are only effective when the path delay and Doppler spread are moderate. We develop a new variational soft symbol decoding (VSSD) algorithm based on the principle of variational Bayes' inference for a general linear channel model. In channels with moderate delay and Doppler spreads, we show that the VSSD algorithm is equivalent to the existing gradient heterodyne receivers for S2C communications. We apply the VSSD algorithm to the i.i.d. Gaussian multiple-input multiple-output channel and show, through numerical simulations, that it far outperforms the minimum mean squared error (MMSE) data detection. We illustrate the dramatic improvement in the performance of the VSSD based S2C receiver in two different models of simulated UWA channels and two contrasting measured UWA environments publicly available in the WATERMARK channel dataset. The proposed VSSD algorithm recovers data symbols at a signal-to-noise ratio (SNR) which is at least 10 dB (8 dB) lower than the MMSE decoder for uncoded (rate 2/3 LDPC coded) communications over UWA channels where the existing receivers either fail completely or must compromise on the data rate to maintain the bit error rate (BER) performance.

关键词： Receivers Delays Doppler effect Decoding Chirp signal processing algorithms Channel estimation Underwater acoustic communications sweep spread carrier communication variational Bayes'

来源：评论

学校读者我要写书评

暂无评论

FAST ALGORITHM FOR MINIMUM-NORM DIRECTION-OF-ARRIVAL ESTIMATION

引用

IEEE TRANSACTIONS ON signal processing 1994年第9期42卷 2389-2394页

作者： ERMOLAEV, VT GERSHMAN, AB GORKY STATE UNIV GORKIRUSSIA

The original minimum-norm direction-of-arrival estimator, proposed by Kumaresan and Tufts, employs the noise-subspace projection matrix, calculated by the eigendecomposition of spatial covariance matrix. In this paper we propose a novel noneigenvector fast algorithm, which calculates the required minimum-norm function using the special power basis instead of eigenvector basis. Proposed algorithm provides a substantial saving as compared with computational loads of eigendecomposition-based minimum-norm algorithm in cases when the number of multiple sources is much lower than the number of array sensors. Some computer simulation results, verifying the high performance and accuracy of the proposed algorithm, are presented.

关键词： Direction of arrival estimation Sensor arrays Covariance matrix signal resolution signal processing algorithms Computer simulation Spatial resolution Additive noise Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

SEOFP-NET: Compression and Acceleration of Deep Neural Networks for Speech Enhancement Using Sign-Exponent-Only Floating-Points

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE processing 2022年 30卷 1016-1031页

作者： Lin, Yu-Chen Yu, Cheng Hsu, Yi-Te Fu, Szu-Wei Tsao, Yu Kuo, Tei-Wei Acad Sinica Res Ctr Informat Technol Innovat Taipei 11529 Taiwan Johns Hopkins Univ Dept Comp Sci Baltimore MD 21287 USA Natl Taiwan Univ Dept Comp Sci & Informat Engn Taipei 10617 Taiwan City Univ Hong Kong Coll Engn Kowloon Tong Hong Kong Peoples R China

Numerous compression and acceleration strategies have achieved outstanding results on classification tasks in various fields. Nevertheless, the same strategies may yield unsatisfactory performance on regression tasks because the nature between regression and classification tasks differs. In this paper, a novel sign-exponent-only floating-point network (SEOFP-NET) technique is proposed to compress the model size and accelerate the inference time for speech enhancement, a regression task of speech signal processing. The proposed method compressed the sizes of deep neural network (DNN)-based speech enhancement models by quantizing the fraction bits of single-precision floating-point parameters during training. Before inference implementation, all parameters in the trained SEOFP-NET model are adjusted to accelerate the inference time by replacing the floating-point multiplier with an integer-adder. The experimental results indicate that the size of SEOFP-NET models can be significantly compressed by up to 81.249% without noticeably downgrading their speech enhancement performance, and the inference time can be accelerated to 1.212x compared with the baseline models. The results also verify that SEOFP-NET can cooperate with other efficiency strategies to achieve a synergy effect for model compression. In addition, results of a just noticeable difference experiment show that the listeners cannot facilely differentiate between the enhanced speech signals processed by the baseline model and SEOFP-NET. To the best of our knowledge, this study is one of the first works that aims to compress the model size and reduce the inference time of speech enhancement while maintaining satisfactory performance. The promising results confirm the potential applicability of SEOFP-NET to lightweight embedded devices.

关键词： Speech enhancement Task analysis Noise reduction Computational modeling Inference algorithms Noise measurement signal processing algorithms Speech enhancement speech dereverberation deep neural network model compression inference acceleration floating-point integer arithmetic circuit

来源：评论

学校读者我要写书评

暂无评论

A General Joint Matrix Factorization Framework for Data Integration and Its Systematic Algorithmic Exploration

引用

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2020年第9期28卷 1971-1983页

作者： Zhang, Lihua Zhang, Shihua Chinese Acad Sci NCMIS CEMS RCSDSAcad Math & Syst Sci Beijing 100190 Peoples R China Chinese Acad Sci Ctr Excellence Anim Evolut & Genet Kunming 650223 Yunnan Peoples R China

Nonnegative matrix factorization (NMF) is a powerful tool in data exploratory analysis by discovering hidden features and part-based patterns from high-dimensional data. NMF and its variants have been successfully applied into diverse fields such as pattern recognition, signal processing, data mining, bioinformatics, and so on. Recently, NMF has been extended to analyze multiple matrices simultaneously. However, a general framework and its systematic algorithmic exploration are still lacking. In this paper, we first introduce a sparse multiple relationship data regularized joint matrix factorization (JMF) framework and two adapted prediction models for pattern recognition and data integration. Next, we present four update algorithms to solve this framework in a very comprehensive manner. The merits and demerits of these algorithms are systematically explored. Furthermore, extensive computational experiments using both synthetic data and real data demonstrate the effectiveness of JMF framework and related algorithms on pattern recognition and data mining.

关键词： Sparse matrices Pattern recognition Data integration Prediction algorithms Data models Matrix decomposition signal processing algorithms Bioinformatics data integration network-regularized constraint nonnegative matrix factorization (NMF) pattern recognition

来源：评论

学校读者我要写书评

暂无评论

CONTOUR-GAIN VECTOR QUANTIZATION

引用

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND signal processing 1988年第6期36卷 862-870页

作者： MALONE, KT FISCHER, TR Department of Electrical Engineering Texas A and M University College Station TX USA

An information-theory motivation for considering a contour-gain codebook structure is given and an iterative contour-gain vector quantizer (CGVQ) algorithm allowing optimization of the shape codebook for a fixed-gain codebook is described. Numerical results are presented for CGVQ encoding of first-, second-, and tenth-order Gauss-Markov sources, and a clear improvement over SGVQ (shape-gain vector quantizer) performance is demonstrated. Numerical results are also presented for CGVQ waveform encoding of speech, and again an improvement over SGVQ performance is demonstrated. The perceptual quality of the encoded speech was roughly equivalent for the two models.< >

关键词： Vector quantization signal processing algorithms Product codes Clustering algorithms Shape Algorithm design and analysis Gaussian processes Iterative algorithms Speech coding Encoding

来源：评论

学校读者我要写书评

暂无评论

Conservative Stochastic Optimization With Expectation Constraints

引用

IEEE TRANSACTIONS ON signal processing 2021年 69卷 3190-3205页

作者： Akhtar, Zeeshan Bedi, Amrit Singh Rajawat, Ketan Indian Inst Technol Kanpur Dept Elect Engn Kanpur 208016 Uttar Pradesh India US Army Res Lab Adelphi MD 20783 USA

This paper considers stochastic convex optimization problems where the objective and constraint functions involve expectations with respect to the data indices or environmental variables, in addition to deterministic convex constraints on the domain of the variables. Since the underlying data distribution is unknown a priori, a closed-form solution is generally not available, and classical deterministic optimization paradigms are not applicable. State-of-the-art approaches, such as those using the saddle point framework, are able to ensure that the optimality gap as well as the constraint violation decay as O(T-1/2) where T is the number of stochastic gradients. In this work, we propose a novel conservative stochastic optimization algorithm (CSOA) that achieves zero average constraint violation and O(T-1/2) optimality gap. Further, we also consider the scenario where carrying out a projection step onto the convex domain constraints at every iteration is not viable. Traditionally, the projection operation can be avoided by considering the conditional gradient or Frank-Wolfe (FW) variant of the algorithm. The state-of-the-art stochastic FW variants achieve an optimality gap of O(T-1/3) after T iterations, though these algorithms have not been applied to problems with functional expectation constraints. In this work, we propose the FW-CSOA algorithm that is not only projection-free but also achieves zero average constraint violation with O(T-1/4) decay of the optimality gap. The efficacy of the proposed algorithms is tested on two relevant problems: fair classification and structured matrix completion.

关键词： signal processing algorithms Convergence Approximation algorithms Optimization signal processing Machine learning Extrapolation Convex Optimization Stochastic Optimization Primal-Dual methods Projection-Free algorithms

来源：评论

学校读者我要写书评

暂无评论

USING THE DFT TO SYNTHESIZE BIVARIATE ORTHOGONAL WHITE-NOISE SERIES

引用

IEEE TRANSACTIONS ON signal processing 1995年第3期43卷 749-758页

作者： NIEDERLINSKI, A FIGWER, J Instytut Automatyki Politechnika Slaska Gliwice Poland

The discrete Fourier transform (DFT) is used to generate bivariate orthogonal series in the form of bivariate random-phase multisine series. The properties of those series are presented. The concept of N/2-lag white series is introduced as series whose ac function coincides with the ac function of white noise for lags 0.1.....N/2 - 1. It is shown how to turn bivariate orthogonal multisine series into corresponding bivariate orthogonal N/2-lag white series and into asymptotically Gaussian bivariate orthogonal white series. The main part of the algorithm for generating such series via DFT is presented. The spectral, correlation, and Gaussian properties of the introduced series are illustrated by three numerical examples.

关键词： White noise Discrete Fourier transforms Frequency domain analysis signal processing algorithms Decorrelation Autocorrelation Integrated circuit noise Integrated circuit synthesis Aging Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Generalized multivariate analysis of variance

引用

IEEE signal processing MAGAZINE 2003年第5期20卷 39-54页

作者： Dogandzic, A Nehorai, A Iowa State Univ Dept Elect & Comp Engn Ames IA USA Univ Illinois Chicago IL USA

Generalized multivariate analysis of variance (GMANOVA) and related reduced-rank regression are general statistical models that comprise versions of regression, canonical correlation, and profile analyses as well as analysis of variance (ANOVA) and covariance in univariate and multivariate settings. It is a powerful and, yet, not very well-known tool. We develop a unified framework for explaining, analyzing, and extending signal processing methods based on GMANOVA. We show the applicability of this framework to a number of detection and estimation problems in signal processing and communications and provide new and simple ways to derive numerous existing algorithms. Many of the methods were originally derived "from scratch", without knowledge of their close relationship with the GMANOVA model. We explicitly show this relationship and present new insights and guidelines for generalizing these methods. Our results could inspire applications of the general framework of GMANOVA to new problems in signal processing. We present such an application to flaw detection in nondestructive evaluation (NDE) of materials. A promising area for future growth is image processing.

关键词： Analysis of variance Covariance matrix signal processing algorithms Radar detection Radar signal processing signal analysis Position measurement signal processing Nuclear magnetic resonance Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Distributed Banach-Picard Iteration: Application to Distributed Parameter Estimation and PCA

引用

IEEE TRANSACTIONS ON signal processing 2023年 71卷 17-30页

作者： Andrade, Francisco Figueiredo, Mario A. T. Xavier, Joao Univ Lisbon Inst Super Tecn P-1049001 Lisbon Portugal Inst Telecomunicacoes P-1049001 Lisbon Portugal Inst Syst & Robot Lab Robot & Engn Syst P-1600011 Lisbon Portugal

We recently proposed an algorithmic framework, distributed Banach-Picard iteration (DBPI), allowing a set of agents linked by a communication network to find a fixed point of a map that: (a) is the average of individual maps held by said agents;(b) is locally contractive (LC). Given such a map, DBPI yields a distributed algorithm provably inheriting the local linear convergence (LLC) of the standard Banach-Picard iteration for the centralized (average) map. Here, we instantiate DBPI in two classical problems, which amounts to proving that the conditions guaranteeing the LLC of DBPI hold. First, taking Sanger's algorithm for principal component analysis (PCA), we show that it corresponds to iterating an LC map that can be written as the average of local maps held by agents with private data subsets. Applying DBPI then recovers a previous distributed PCA algorithm, which lacked a convergence proof, thus closing that gap. In the second instantiation, we show that a variant of the expectation-maximization (EM) algorithm for parameter estimation from noisy, faulty measurements in sensor networks can be written as iterating an LC map that is the average of local maps. Consequently, the DBPI framework yields a distributed algorithm automatically inheriting the LLC guarantee of its centralized counterpart. Verifying the LC condition for EM is nontrivial (as the underlying operator depends on random samples) and a contribution in itself, possibly of independent interest. Finally, we illustrate experimentally the linear convergence of the proposed distributed EM algorithm, contrasting with the sub-linear rate of the previous version.

关键词： Task analysis Convergence Principal component analysis signal processing algorithms Distributed algorithms Dimensionality reduction Computational modeling Distributed computation banach-picard iteration fixed points distributed EM distributed PCA consensus

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：