PyTorchKR Papers

최신 논문

총 549편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2105.01800

Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectives

Magnetic Resonance Imaging (MRI) is a vital component of medical imaging. When compared to other image modalities, it has advantages such as the absence of radiation, superior soft tissue contrast, and complementary multiple sequence information. However, one drawback of MRI is its comparatively slow scanning and reconstruction compared to other image modalities, limiting its usage in some clinical applications when imaging time is critical. Traditional compressive sensing based MRI (CS-MRI) reconstruction can speed up MRI acquisition, but suffers from a long iterative process and noise-induced artefacts. Recently, Deep Neural Networks (DNNs) have been used in sparse MRI reconstruction models to recreate relatively high-quality images from heavily undersampled k-space data, allowing for much faster MRI scanning. However, there are still some hurdles to tackle. For example, directly training DNNs based on L1/L2 distance to the target fully sampled images could result in blurry reconstruction because L1/L2 loss can only enforce overall image or patch similarity and does not take into account local information such as anatomical sharpness. It is also hard to preserve fine image details while maintaining a natural appearance. More recently, Generative Adversarial Networks (GAN) based methods are proposed to solve fast MRI with enhanced image perceptual quality. The encoder obtains a latent space for the undersampling image, and the image is reconstructed by the decoder using the GAN loss. In this chapter, we review the GAN powered fast MRI methods with a comparative study on various anatomical datasets to demonstrate the generalisability and robustness of this kind of fast MRI while providing future perspectives.

arXiv:2104.13296

CAIM: Cooperative Angle of Arrival Estimation using the Ising Method

This paper proposes a cooperative angle-of-arrival(AoA) estimation, taking advantage of co-processing channel state information (CSI) from a group of access points that receive signals of the same source. Since received signals are sparse, we use Compressive Sensing (CS) to address the AoA estimation problem. We formulate this problem as a penalized l0-norm minimization, reformulate it as an Ising energy problem, and solve it using Markov Chain Monte Carlo (MCMC). Simulation results show that our proposed method outperforms the existing methods in the literature.

arXiv:2104.13894

Weighed l1 on the simplex: Compressive sensing meets locality

Sparse manifold learning algorithms combine techniques in manifold learning and sparse optimization to learn features that could be utilized for downstream tasks. The standard setting of compressive sensing can not be immediately applied to this setup. Due to the intrinsic geometric structure of data, dictionary atoms might be redundant and do not satisfy the restricted isometry property or coherence condition. In addition, manifold learning emphasizes learning local geometry which is not reflected in a standard $\ell_1$ minimization problem. We propose weighted $\ell_0$ and weighted $\ell_1$ metrics that encourage representation via neighborhood atoms suited for dictionary based manifold learning. Assuming that the data is generated from Delaunay triangulation, we show the equivalence of weighted $\ell_0$ and weighted $\ell_1$. We discuss an optimization program that learns the dictionaries and sparse coefficients and demonstrate the utility of our regularization on synthetic and real datasets.

arXiv:2104.12667공식 코드 · Papers with Code

A Low-Complexity MIMO Channel Estimator with Implicit Structure of a Convolutional Neural Network

A low-complexity convolutional neural network estimator which learns the minimum mean squared error channel estimator for single-antenna users was recently proposed. We generalize the architecture to the estimation of MIMO channels with multiple-antenna users and incorporate complexity-reducing assumptions based on the channel model. Learning is used in this context to combat the mismatch between the assumptions and real scenarios where the assumptions may not hold. We derive a high-level description of the estimator for arbitrary choices of the pilot sequence. It turns out that the proposed estimator has the implicit structure of a two-layered convolutional neural network, where the derived quantities can be relaxed to learnable parameters. We show that by using discrete Fourier transform based pilots the number of learnable network parameters decreases significantly and the online run time of the estimator is reduced considerably, where we can achieve linearithmic order of complexity in the number of antennas. Numerical results demonstrate performance gains compared to state-of-the-art algorithms from the field of compressive sensing or covariance estimation of the same or even higher computational complexity. The simulation code is available online.

arXiv:2104.10959

Compressive lensless endoscopy with partial speckle scanning

The lensless endoscope (LE) is a promising device to acquire in vivo images at a cellular scale. The tiny size of the probe enables a deep exploration of the tissues. Lensless endoscopy with a multicore fiber (MCF) commonly uses a spatial light modulator (SLM) to coherently combine, at the output of the MCF, few hundreds of beamlets into a focus spot. This spot is subsequently scanned across the sample to generate a fluorescent image. We propose here a novel scanning scheme, partial speckle scanning (PSS), inspired by compressive sensing theory, that avoids the use of an SLM to perform fluorescent imaging in LE with reduced acquisition time. Such a strategy avoids photo-bleaching while keeping high reconstruction quality. We develop our approach on two key properties of the LE: (i) the ability to easily generate speckles, and (ii) the memory effect in MCF that allows to use fast scan mirrors to shift light patterns. First, we show that speckles are sub-exponential random fields. Despite their granular structure, an appropriate choice of the reconstruction parameters makes them good candidates to build efficient sensing matrices. Then, we numerically validate our approach and apply it on experimental data. The proposed sensing technique outperforms conventional raster scanning: higher reconstruction quality is achieved with far fewer observations. For a fixed reconstruction quality, our speckle scanning approach is faster than compressive sensing schemes which require to change the speckle pattern for each observation.

arXiv:2104.06470

Joint Matrix Completion and Compressed Sensing for State Estimation in Low-observable Distribution System

Limited measurement availability at the distribution grid presents challenges for state estimation and situational awareness. This paper combines the advantages of two sparsity-based state estimation approaches (matrix completion and compressive sensing) that have been proposed recently to address the challenge of unobservability. The proposed approach exploits both the low rank structure and a suitable transform domain representation to leverage the correlation structure of the spatio-temporal data matrix while incorporating the power-flow constraints of the distribution grid. Simulations are carried out on three phase unbalanced IEEE 37 test system to verify the effectiveness of the proposed approach. The performance results reveal - (1) the superiority over traditional matrix completion and (2) very low state estimation errors for high compression ratios representing very low observability.

arXiv:2005.02571

Identifying Unused RF Channels Using Least Matching Pursuit

Cognitive radio aims at identifying unused radio-frequency (RF) bands with the goal of re-using them opportunistically for other services. While compressive sensing (CS) has been used to identify strong signals (or interferers) in the RF spectrum from sub-Nyquist measurements, identifying unused frequencies from CS measurements appears to be uncharted territory. In this paper, we propose a novel method for identifying unused RF bands using an algorithm we call least matching pursuit (LMP). We present a sufficient condition for which LMP is guaranteed to identify unused frequency bands and develop an improved algorithm that is inspired by our theoretical result. We perform simulations for a CS-based RF whitespace detection task in order to demonstrate that LMP is able to outperform black-box approaches that build on deep neural networks.

arXiv:2007.03570

Crossterm-Free Time-Frequency Representation Exploiting Deep Convolutional Neural Network

Bilinear time-frequency representations (TFRs) provide high-resolution time-varying frequency characteristics of nonstationary signals. However, they suffer from crossterms due to the bilinear nature. Existing crossterm-reduced TFRs focus on optimized kernel design which amounts to low-pass weighting or masking in the ambiguity function domain. Optimization of fixed and adaptive kernels are difficult, particularly for complicated signals whose autoterms and crossterms overlap in the ambiguity function. In this letter, we develop a new method to offer high-resolution TFRs of nonstationary signals with crossterms effectively suppressed. The proposed method exploits a deep convolutional neural network which is trained to construct crossterm-free TFRs. The effectiveness of the proposed method is verified by simulation results which clearly show desirable autoterm preservation and crossterm mitigation capabilities. The proposed technique significantly outperforms state-of-the-art time-frequency analysis algorithms based on adaptive kernels and compressive sensing techniques.

arXiv:2007.03420

Off-grid Multi-Source Passive Localization Using a Moving Array

A novel direct passive localization technique through a single moving array is proposed in this paper using the sparse representation of the array covariance matrix in spatial domain. The measurement is constructed by stacking the vectorized version of all the array covariance matrices at different observing positions. First, an on-grid compressive sensing (CS) based method is developed, where the dictionary is composed of the steering vectors from the searching grids to the observing positions. Convex optimization is applied to solve the `1-norm minimization problem. Second, to get much finer target positions, we develop an on-grid CS based method, where the majorization-minimization technique replaces the atan-sum objective function in each iteration by a quadratic convex function which can be easily minimized. The objective function,atan-sum, is more similar to `0-norm, and more sparsity encouraging than the log-sum function.This method also works more robustly at conditions of low SNR, and fewer observing positions are needed than in the traditional ones. The simulation experiments verify the promises of the proposed algorithm.

arXiv:2006.16628

Beamspace Channel Estimation for Wideband Millimeter-Wave MIMO: A Model-Driven Unsupervised Learning Approach

Millimeter-wave (mmWave) communications have been one of the promising technologies for future wireless networks that integrate a wide range of data-demanding applications. To compensate for the large channel attenuation in mmWave band and avoid high hardware cost, a lens-based beamspace massive multiple-input multiple-output (MIMO) system is considered. However, the beam squint effect in wideband mmWave systems makes channel estimation very challenging, especially when the receiver is equipped with a limited number of radio-frequency (RF) chains. Furthermore, the real channel data cannot be obtained before the mmWave system is used in a new environment, which makes it impossible to train a deep learning (DL)-based channel estimator using real data set beforehand. To solve the problem, we propose a model-driven unsupervised learning network, named learned denoising-based generalized expectation consistent (LDGEC) signal recovery network. By utilizing the Stein's unbiased risk estimator loss, the LDGEC network can be trained only with limited measurements corresponding to the pilot symbols, instead of the real channel data. Even if designed for unsupervised learning, the LDGEC network can be supervisingly trained with the real channel via the denoiser-by-denoiser way. The numerical results demonstrate that the LDGEC-based channel estimator significantly outperforms state-of-the-art compressive sensing-based algorithms when the receiver is equipped with a small number of RF chains and low-resolution ADCs.

arXiv:2009.00305

Regional Total Electron Content Map Generation based on Compressive Sensing

Ionosphere has an important role in long distance HF communications, satellite communications and global navigation systems. Ionosphere is a plasma medium which arises due to solar and cosmic radiation, and the amount of ionization is highly time and location dependent. Eventually, the current state of the ionosphere should be continuously monitored with high accuracy. Total Electron Content (TEC) maps are being used to investigate the state of the ionosphere. There are online services which provide TEC maps, however they mostly have low spatial and temporal resolution and the techniques used for generating these maps are generally not accessible. TEC maps can also be generated from GNSS/GPS based Continuously Operating Receiver Stations (CORS) network measurements. Unfortunately, the GNSS/GPS receiver networks are not dense enough to form a map directly. Therefore, an algorithm should be used to estimate the TEC values at coordinates without a receiver. Based on the observation that TEC maps possess a high degree of sparsity, we propose a modified compressive sensing technique for generating regional TEC maps by using the sparse dataset obtained from a CORS network. We evaluate the performance of the proposed technique both over synthetically generated TEC maps which mimic the common characteristics of the ionosphere, and also over actual measurements taken over the Turkish National Permanent GPS Network (TNPGN) Active. Our analysis reveals that the proposed technique can produce TEC maps with high accuracy and resolution. We also demonstrate the superiority of our technique over other TEC map generation techniques found in the literature.

arXiv:2008.02337

Optimal Data Detection and Signal Estimation in Systems with Input Noise

Practical systems often suffer from hardware impairments that already appear during signal generation. Despite the limiting effect of such input-noise impairments on signal processing systems, they are routinely ignored in the literature. In this paper, we propose an algorithm for data detection and signal estimation, referred to as Approximate Message Passing with Input noise (AMPI), which takes into account input-noise impairments. To demonstrate the efficacy of AMPI, we investigate two applications: Data detection in large multiple-input multiple output (MIMO) wireless systems and sparse signal recovery in compressive sensing. For both applications, we provide precise conditions in the large-system limit for which AMPI achieves optimal performance. We furthermore use simulations to demonstrate that AMPI achieves near-optimal performance at low complexity in realistic, finite-dimensional systems.

arXiv:1906.09867

Compressive Sensing Based Adaptive Active User Detection and Channel Estimation: Massive Access Meets Massive MIMO

This paper considers massive access in massive multiple-input multiple-output (MIMO) systems and proposes an adaptive active user detection and channel estimation scheme based on compressive sensing. By exploiting the sporadic traffic of massive connected user equipments and the virtual angular domain sparsity of massive MIMO channels, the proposed scheme can support massive access with dramatically reduced access latency. Specifically, we design non-orthogonal pseudo-random pilots for uplink broadband massive access, and formulate the active user detection and channel estimation problems as a generalized multiple measurement vector compressive sensing problem. Furthermore, by leveraging the structured sparsity of the uplink channel matrix, we propose an efficient generalized multiple measurement vector approximate message passing (GMMV-AMP) algorithm to realize simultaneous active user detection and channel estimation based on a spatial domain or an angular domain channel model. To jointly exploit the channel sparsity presented in both the spatial and the angular domains for enhanced performance, a Turbo-GMMV-AMP algorithm is developed for detecting the active users and estimating their channels in an alternating manner. Finally, an adaptive access scheme is proposed, which adapts the access latency to guarantee reliable massive access for practical systems with unknown channel sparsity level. Additionally, the state evolution of the proposed GMMV-AMP algorithm is derived to predict its performance. Simulation results demonstrate the superiority of the proposed active user detection and channel estimation schemes compared to several baseline schemes.

arXiv:2010.00199

Fast Uplink Grant-Free NOMA with Sinusoidal Spreading Sequences

Uplink (UL) dominated sporadic transmission and stringent latency requirement of massive machine type communication (mMTC) forces researchers to abandon complicated grant-acknowledgment based legacy networks. UL grant-free non-orthogonal multiple access (NOMA) provides an array of features which can be harnessed to efficiently solve the problem of massive random connectivity and latency. Because of the inherent sparsity in user activity pattern in mMTC, the trend of existing literature specifically revolves around compressive sensing based multi user detection (CS-MUD) and Bayesian framework paradigm which employs either random or Zadoff-Chu spreading sequences for non-orthogonal multiple access. In this work, we propose sinusoidal code as candidate spreading sequences. We show that, sinusoidal codes allow some non-iterative algorithms to be employed in context of active user detection, channel estimation and data detection in a UL grant-free mMTC system. This relaxes the requirement of several impractical assumptions considered in the state-of-art algorithms with added advantages of performance guarantees and lower computational cost. Extensive simulation results validate the performance potential of sinusoidal codes in realistic mMTC environments.

arXiv:2012.10082

Estimating Sparsity Level for Enabling Compressive Sensing of Wireless Channels and Spectra in 5G and Beyond

Applying compressive sensing (CS) allows for sub-Nyquist sampling in several application areas in 5G and beyond. This reduces the associated training, feedback, and computation overheads in many applications. However, the applicability of CS relies on the validity of a signal sparsity assumption and knowing the exact sparsity level. It is customary to assume a foreknown sparsity level. Still, this assumption is not valid in practice, especially when applying learned dictionaries as sparsifying transforms. The problem is more strongly pronounced with multidimensional sparsity. In this paper, we propose an algorithm for estimating the composite sparsity lying in multiple domains defined by learned dictionaries. The proposed algorithm estimates the sparsity level over a dictionary by inferring it from its counterpart with respect to a compact discrete Fourier basis. This inference is achieved by a machine learning prediction. This setting learns the intrinsic relationship between the columns of a dictionary and those of such a fixed basis. The proposed algorithm is applied to estimating sparsity levels in wireless channels, and in cognitive radio spectra. Extensive simulations validate a high quality of sparsity estimation leading to performances very close to the impractical case of assuming known sparsity.

arXiv:2102.00284

Study on Compressed Sensing of Action Potential

Compressive sensing (CS) is a signal processing technique that enables sub-Nyquist sampling and near lossless reconstruction of a sparse signal. The technique is particularly appealing for neural signal processing since it avoids the issues relevant to high sampling rate and large data storage. In this project, different CS reconstruction algorithms were tested on raw action potential signals recorded in our lab. Two numerical criteria were set to evaluate the performance of different CS algorithms: Compression Ratio (CR) and Signal-to-Noise Ratio (SNR). In order to do this, individual CS algorithm testing platforms for the EEG data were constructed within MATLAB scheme. The main considerations for the project were the following. 1) Feasibility of the dictionary 2) Tolerance to non-sparsity 3) Applicability of thresholding or interpolation.

arXiv:2007.03761

Compressive dual-comb spectroscopy

Broadband, high resolution and rapid measurement of dual-comb spectroscopy (DCS) generates a large amount of data stream. We numerically demonstrate significant data compression of DCS spectra by using a compressive sensing technique. Our numerical simulation shows a compression rate of more than 100 with 3% error in mole fraction estimation of mid-infrared (MIR) DCS of two molecular species in a broadband (~30 THz) and high resolution (~115 MHz) condition. We also numerically demonstrate a massively parallel MIR DCS spectrum of 10 different molecular species can be reconstructed with a compression rate of 10.5 with a transmittance error of 0.003 from the original spectrum.

arXiv:2104.02371

Newton-Type Optimal Thresholding Algorithms for Sparse Optimization Problems

Sparse signals can be possibly reconstructed by an algorithm which merges a traditional nonlinear optimization method and a certain thresholding technique. Different from existing thresholding methods, a novel thresholding technique referred to as the optimal $k$-thresholding was recently proposed by Zhao [SIAM J Optim, 30(1), pp. 31-55, 2020]. This technique simultaneously performs the minimization of an error metric for the problem and thresholding of the iterates generated by the classic gradient method. In this paper, we propose the so-called Newton-type optimal $k$-thresholding (NTOT) algorithm which is motivated by the appreciable performance of both Newton-type methods and the optimal $k$-thresholding technique for signal recovery. The guaranteed performance (including convergence) of the proposed algorithms are shown in terms of suitable choices of the algorithmic parameters and the restricted isometry property (RIP) of the sensing matrix which has been widely used in the analysis of compressive sensing algorithms. The simulation results based on synthetic signals indicate that the proposed algorithms are stable and efficient for signal recovery.

arXiv:2104.00636

Distributed Video Adaptive Block Compressive Sensing

Video block compressive sensing has been studied for use in resource constrained scenarios, such as wireless sensor networks, but the approach still suffers from low performance and long reconstruction time. Inspired by classical distributed video coding, we design a lightweight encoder with computationally intensive operations, such as video frame interpolation, performed at the decoder. Straying from recent trends in training end-to-end neural networks, we propose two algorithms that leverage convolutional neural network components to reconstruct video with greatly reduced reconstruction time. At the encoder, we leverage temporal correlation between frames and deploy adaptive techniques based on compressive measurements from previous frames. At the decoder, we exploit temporal correlation by using video frame interpolation and temporal differential pulse code modulation. Simulations show that our two proposed algorithms, VAL-VFI and VAL-IDA-VFI reconstruct higher quality video, achieving state-of-the-art performance.

arXiv:2103.16055

1-Bit Compressive Sensing for Efficient Federated Learning Over the Air

For distributed learning among collaborative users, this paper develops and analyzes a communication-efficient scheme for federated learning (FL) over the air, which incorporates 1-bit compressive sensing (CS) into analog aggregation transmissions. To facilitate design parameter optimization, we theoretically analyze the efficacy of the proposed scheme by deriving a closed-form expression for the expected convergence rate of the FL over the air. Our theoretical results reveal the tradeoff between convergence performance and communication efficiency as a result of the aggregation errors caused by sparsification, dimension reduction, quantization, signal reconstruction and noise. Then, we formulate 1-bit CS based FL over the air as a joint optimization problem to mitigate the impact of these aggregation errors through joint optimal design of worker scheduling and power scaling policy. An enumeration-based method is proposed to solve this non-convex problem, which is optimal but becomes computationally infeasible as the number of devices increases. For scalable computing, we resort to the alternating direction method of multipliers (ADMM) technique to develop an efficient implementation that is suitable for large-scale networks. Simulation results show that our proposed 1-bit CS based FL over the air achieves comparable performance to the ideal case where conventional FL without compression and quantification is applied over error-free aggregation, at much reduced communication overhead and transmission latency.