检索结果-内蒙古大学图书馆

Data Augmentation for deep Receivers

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2023年第11期22卷 8259-8274页

作者： Raviv, Tomer Shlezinger, Nir Ben Gurion Univ Negev Sch Elect & Comp Engn IL-84105 Beer Sheva Israel

deep neural networks (DNNs) allow digital receivers to learn to operate in complex environments. To do so, DNNs should preferably be trained using large labeled data sets with a similar statistical relationship as the one under which they are to infer. For DNN-aided receivers, obtaining labeled data conventionally involves pilot signalling at the cost of reduced spectral efficiency, typically resulting in access to limited data sets. In this paper, we study how one can enrich a small set of labeled pilots data into a larger data set for training deep receivers. Motivated by the widespread use of data augmentation techniques for enriching visual and text data, we propose dedicated augmentation schemes that exploits the characteristics of digital communication data. We identify the key considerations in data augmentations for deep receivers as the need for domain orientation, class (constellation) diversity, and low complexity. Following these guidelines, we devise three complementing augmentations that exploit the geometric properties of digital constellations. Our combined augmentation approach builds on the merits of these different augmentations to synthesize reliable data from a momentary channel distribution, to be used for training deep receivers. Furthermore, we exploit previous channel realizations to increase the reliability of the augmented samples. The superiority of our approach is numerically evaluated for training several deep receiver architectures in different channel conditions. We consider both linear and non-linear synthetic channels, as well as the COST 2100 channel generator, for both single-input single-output and multiple-input multiple-output scenarios. We show that our combined augmentations approach allows DNN-aided receivers to achieve gains of up to 1 dB in bit error rate and of up to $\times 3$ in spectral efficiency, compared to regular non-augmented training. Moreover, we demonstrate that our augmentations benefit training even as the n

关键词： Wireless communications model-based deep learning deep receivers data augmentations

来源：评论

学校读者我要写书评

暂无评论

Markov-based Neural Networks for Heart Sound Segmentation: Using Domain Knowledge in a Principled Way

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2023年第11期27卷 5357-5368页

作者： Martins, Miguel L. Coimbra, Miguel T. Renna, Francesco Univ Porto Inst Syst & Comp Engn Technol & Sci INESC TEC Fac Sci P-4169007 Porto Portugal

This work considers the problem of segmenting heart sounds into their fundamental components. We unify statistical and data-driven solutions by introducing Markov-based Neural Networks (MNNs), a hybrid end-to-end framework that exploits Markov models as statistical inductive biases for an Artificial Neural Network (ANN) discriminator. We show that an MNN leveraging a simple one-dimensional Convolutional ANN significantly outperforms two recent purely data-driven solutions for this task in two publicly available datasets: PhysioNet 2016 (Sensitivity: 0.947 +/- 0.02;Positive Predictive Value : 0.937 +/- 0.025) and the CirCor DigiScope 2022 (Sensitivity: 0.950 +/- 0.008;Positive Predictive Value: 0.943 +/- 0.012). We also propose a novel gradient-based unsupervised learning algorithm that effectively makes the MNN adaptive to unseen datum sampled from unknown distributions. We perform a cross dataset analysis and show that an MNN pre-trained in the CirCor DigiScope 2022 can benefit from an average improvement of 3.90% Positive Predictive Value on unseen observations from the PhysioNet 2016 dataset using this method.

关键词： Hybrid neural networks Markov models model-based deep learning phonocardiogram segmentation

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE KALMANNET: DATA-DRIVEN KALMAN FILTER WITH FAST ADAPTATION 49

ADAPTIVE KALMANNET: DATA-DRIVEN KALMAN FILTER WITH FAST ADAP...

引用

49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ni, Xiaoyong Revach, Guy Shlezinger, Nir Swiss Fed Inst Technol ITET Zurich Switzerland Ben Gurion Univ Negev Sch ECE Beer Sheva Israel

ISBN: (纸本)9798350344868;9798350344851

Combining the classical Kalman filter (KF) with a deep neural network (DNN) enables tracking in partially known state space (SS) models. A major limitation of current DNN-aided designs stems from the need to train them to filter data originating from a specific distribution and underlying SS model. Consequently, changes in the model parameters may require lengthy retraining. While the KF adapts through parameter tuning, the black-box nature of DNNs makes identifying tunable components difficult. Hence, we propose Adaptive KalmanNet (AKNet), a DNN-aided KF that can adapt to changes in the SS model without retraining. Inspired by recent advances in large language model fine-tuning paradigms, AKNet uses a compact hypernetwork to generate context-dependent modulation weights. Numerical evaluation shows that AKNet provides consistent state estimation performance across a continuous range of noise distributions, even when trained using data from limited noise settings.

关键词： model-based deep learning adaptive KF

来源：评论

学校读者我要写书评

暂无评论

LOCAL MONOTONE OPERATOR learning USING NON-MONOTONE OPERATORS: MNM-MOL 21

LOCAL MONOTONE OPERATOR LEARNING USING NON-MONOTONE OPERATOR...

引用

21st IEEE International Symposium on Biomedical Imaging (ISBI)

作者： John, Maneesh Chand, Jyothi Rikhab Jacob, Mathews Univ Iowa Dept Elect & Comp Engn Iowa City IA USA

ISBN: (纸本)9798350313345;9798350313338

model-based deep learning methods, which train convolutional neural network blocks within iterative algorithms in an end-to-end fashion, have been shown to provide state-of-the-art performance in several inverse problems. deep equilibrium (DEQ) models and monotone operator learning (MOL) were introduced to reduce the memory demand of unrolled algorithms. However, the Lipschitz constraint or monotone constraint in DEQ methods often results in a decrease in performance compared to unrolled methods. This work relaxes the monotone constraint in two ways. We impose the monotone constraint on the sum of the gradient of the data term and the CNN block, allowing the CNN to learn possibly non-monotone score functions. Additionally, the operator is only restricted to being monotone in a local neighborhood around the image manifold. We present theoretical results demonstrating that the proposed scheme is guaranteed to converge to the fixed point and that the solution is robust to input perturbations. Empirical results show that the relaxed constraint leads to improved performance, and that the approach has robustness to input perturbations similar to that of MOL.

关键词： model-based deep learning Monotone operator learning deep equilibrium models

来源：评论

学校读者我要写书评

暂无评论

Dynamic PET image reconstruction using deep physiology prior

Dynamic PET image reconstruction using deep physiology prior

引用

Conference on Medical Imaging - Physics of Medical Imaging

作者： Chen, Mengrui Hu, Rui Liu, Huafeng Zhejiang Univ Coll Opt Sci & Engn State Key Lab Extreme Photon & Instrumentat Hangzhou 310027 Zhejiang Peoples R China

ISBN: (纸本)9781510671553;9781510671546

Dynamic positron emission tomography (PET) imaging can provide information about metabolic changes over time, and is widely used in clinical diagnosis and cancer treatment. However, the existing deep learning methods for PET image reconstruction mainly focus on the static mapping paradigm between sinogram and radioactivity concentration distribution, which ignores the inherent dynamic activation process of tracers. In this paper, we establish a physiological model based deep learning framework for dynamic PET image reconstruction using deep physiology prior. First, the objective functions of our physiological model are combined with static mapping and the dynamic activation process of tracers. Then, a data-driven Adaptive Kalman Inspired Network (AKIN) is adopted to solve the proposed objective functions. Specifically, the AKIN consists of three components: a Prediction Net is employed for directly predicting the prior estimation;a Projection Net is employed for predicting the current estimation of the observations based on the prior estimation, furthermore, a Kalman Gain Net (KNet) is employed for adaptively learning the gain coefficient. The experiment of simulation data demonstrates that the proposed method has substantial noise reduction in temporal and spatial domains, outperforming other methods like maximum likelihood expectation maximization, kernel expectation maximization method and deepPET.

关键词： dynamic PET image reconstruction state space model Kalman Filtering model-based deep learning

来源：评论

学校读者我要写书评

暂无评论

NoSENSE: Learned Unrolled Cardiac MRI Reconstruction Without Explicit Sensitivity Maps 14th

NoSENSE: Learned Unrolled Cardiac MRI Reconstruction Without...

引用

14th International Workshop on Statistical Atlases and Computational modelling of the Heart (STACOM)

作者： Zimmermann, Felix Frederik Kofler, Andreas Physikalisch Tech Bundesanstalt PTB Berlin Germany

ISBN: (纸本)9783031524479;9783031524486

We present a novel learned image reconstruction method for accelerated cardiac MRI with multiple receiver coils based on deep convolutional neural networks (CNNs) and algorithm unrolling. In contrast to many existing learned MR image reconstruction techniques that necessitate coil-sensitivity map (CSM) estimation as a distinct network component, our proposed approach avoids explicit CSM estimation. Instead, it implicitly captures and learns to exploit the inter-coil relationships of the images. Our method consists of a series of novel learned image and k-space blocks with shared latent information and adaptation to the acquisition parameters by feature-wise modulation (FiLM), as well as coil-wise data-consistency (DC) blocks. Our method achieved PSNR values of 34.89 and 35.56 and SSIM values of 0.920 and 0.942 in the cine track and mapping track validation leaderboard of the MICCAI STACOM CMRxRecon Challenge, respectively, ranking 4th among different teams at the time of writing. Code is available at https://***/fzimmermann89/CMRx

关键词： Calibration-Free MRI model-based deep learning Accelerated Cardiac MRI Recurrent U-Nets

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Transmission Waveform learning for Ultrafast Pulse-Echo Ultrasound Imaging with Sparse Reconstruction 32

Self-Supervised Transmission Waveform Learning for Ultrafast...

引用

32nd European Signal Processing Conference (EUSIPCO)

作者： Cakiroglu, Ozan Perez, Eduardo Roemer, Florian Schiffner, Martin Fraunhofer Inst Nondestruct Testing IZFP Saarbrucken Germany Tech Univ Ilmenau Ilmenau Germany Ruhr Univ Bochum Bochum Germany

ISBN: (纸本)9789464593617;9798331519773

Ultrafast pulse-echo ultrasound imaging is performed by recording only one measurement cycle, which insonifies the entire region of interest. It has been shown that mathematical model of the received signal is suitable for image reconstruction based on sparsity-promoting algorithms if material parameters of measurement area can be sparsely represented with a suitable basis. However, reconstruction performance of these algorithms is affected by correlation of measured samples, which depends on the scatterer locations in the measurement area and transmitted signal parameters. In this paper, we create a model-based and self-supervised neural network, which learns the transmitted waveforms and delays of each transducer element with the task of minimizing the reconstruction error. It employs forward model as encoder and the Fast Iterative Shrinkage Thresholding Algorithm as decoder. The outcomes are evaluated against two existing scenarios: one involving randomly delayed and weighted transmission signals, and the other based on conventional plane wave imaging. Utilizing learned transmission waveform and time delays outperformed other cases in terms of contrast level and reconstruction accuracy.

关键词： ultrafast pulse-echo ultrasound imaging ultrasound waveform design model-based deep learning sparse reconstruction self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

deep UNFOLDING NETWORK WITH PHYSICS-based PRIORS FOR UNDERWATER IMAGE ENHANCEMENT 30

DEEP UNFOLDING NETWORK WITH PHYSICS-BASED PRIORS FOR UNDERWA...

引用

30th IEEE International Conference on Image Processing (ICIP)

作者： Thuy Thi Pham Truong Thanh Nhat Mai Lee, Chul Dongguk Univ Dept Multimedia Engn Seoul South Korea

ISBN: (纸本)9781728198354

We propose an underwater image enhancement algorithm that leverages both model- and learning-based approaches by unfolding an iterative algorithm. We first formulate the underwater image enhancement task as a joint optimization problem, based on the image formation model with physical model and underwater-related priors. Then, we solve the optimization problem iteratively. Finally, we unfold the iterative algorithm so that, at each iteration, the optimization variables and regularizers for image priors are updated by closed-form solutions and learned deep networks, respectively. Experimental results demonstrate that the proposed algorithm outperforms state-of-the-art underwater image enhancement algorithms.

关键词： Underwater image enhancement algorithm unrolling prior learning model-based deep learning

来源：评论

学校读者我要写书评

暂无评论

STPDNET: SPATIAL-TEMPORAL CONVOLUTIONAL PRIMAL DUAL NETWORK FOR DYNAMIC PET IMAGE RECONSTRUCTION 20

STPDNET: SPATIAL-TEMPORAL CONVOLUTIONAL PRIMAL DUAL NETWORK ...

引用

20th IEEE International Symposium on Biomedical Imaging (ISBI)

作者： Hu, Rui Cui, Jianan Yu, Chengjin Chen, Yunmei Liu, Huafeng Zhejiang Univ Dept Opt Engn State Key Lab Modern Opt Instrumentat Hangzhou 310027 Peoples R China Univ Florida Dept Math Gainesville FL 32611 USA

ISBN: (纸本)9781665473583

Dynamic positron emission tomography (dPET) image reconstruction is extremely challenging due to the limited counts received in individual frame. In this paper, we propose a spatial-temporal convolutional primal dual network (STPDnet) for dynamic PET image reconstruction. Both spatial and temporal correlations are encoded by 3D convolution operators. The physical projection of PET is embedded in the iterative learning process of the network, which provides the physical constraints and enhances interpretability. The experiments of real rat scan data have shown that the proposed method can achieve substantial noise reduction in both temporal and spatial domains and outperform the maximum likelihood expectation maximization (MLEM), spatial-temporal kernel method (KEM-ST), deepPET and Learned Primal Dual (LPD).

关键词： Dynamic PET image reconstruction model-based deep learning spatial-temporal correlation

来源：评论

学校读者我要写书评

暂无评论

learning an interpretable end-to-end network for real-time acoustic beamforming

引用

JOURNAL OF SOUND AND VIBRATION 2024年 591卷

作者： Liang, Hao Zhou, Guanxing Tu, Xiaotong Jakobsson, Andreas Ding, Xinghao Huang, Yue Xiamen Univ Sch Informat Xiamen 361005 Peoples R China Xiamen Univ Inst Artificial Intelligence Xiamen 361005 Peoples R China Lund Univ Ctr Math Sci SE-22100 Lund Sweden

Recently, many forms of audio industrial applications, such as sound monitoring and source localization, have begun exploiting smart multi-modal devices equipped with a microphone array. Regrettably, model-based methods are often difficult to employ for such devices due to their high computational complexity, as well as the difficulty of appropriately selecting the user-determined parameters. As an alternative, one may use deep network-based methods, but these are often difficult to generalize, nor can they generate the desired beamforming map directly. In this paper, a computationally efficient acoustic beamforming algorithm is proposed, which may be unrolled to form a model-based deep learning network for real-time imaging, here termed the DAMAS-FISTA-Net. By exploiting the natural structure of an acoustic beamformer, the proposed network inherits the physical knowledge of the acoustic system, and thus learns the underlying physical properties of the propagation. As a result, all the network parameters may be learned end-to-end, guided by a model-based prior using back-propagation. Notably, the proposed network enables an excellent interpretability and the ability of being able to process the raw data directly. Extensive numerical experiments using both simulated and real-world data illustrate the preferable performance of the DAMAS-FISTA-Net as compared to alternative approaches.

关键词： Acoustic beamforming Acoustic imaging Source localization Array signal processing model-based deep learning Interpretable network

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：