Bayesian feature learning for seismic compressive sensing and denoising

Geophysics ◽  
2017 ◽  
Vol 82 (6) ◽  
pp. O91-O104 ◽  
Author(s):  
Georgios Pilikos ◽  
A. C. Faul
Keyword(s):  
Compressive Sensing ◽  
State Of The Art ◽  
Feature Learning ◽  
Seismic Signal ◽  
Basis Functions ◽  
Sparse Signals ◽  
Seismic Signals ◽  
Process Factor ◽  
Learned Features ◽  
Fixed Basis

Extracting the maximum possible information from the available measurements is a challenging task but is required when sensing seismic signals in inaccessible locations. Compressive sensing (CS) is a framework that allows reconstruction of sparse signals from fewer measurements than conventional sampling rates. In seismic CS, the use of sparse transforms has some success; however, defining fixed basis functions is not trivial given the plethora of possibilities. Furthermore, the assumption that every instance of a seismic signal is sparse in any acquisition domain under the same transformation is limiting. We use beta process factor analysis (BPFA) to learn sparse transforms for seismic signals in the time slice and shot record domains from available data, and we use them as dictionaries for CS and denoising. Algorithms that use predefined basis functions are compared against BPFA, with BPFA obtaining state-of-the-art reconstructions, illustrating the importance of decomposing seismic signals into learned features.

scholarly journals High-Performance 3D Compressive Sensing MRI Reconstruction Using Many-Core Architectures

2011 ◽  
Vol 2011 ◽  
pp. 1-11 ◽  
Author(s):  
Daehyun Kim ◽  
Joshua Trzasko ◽  
Mikhail Smelyanskiy ◽  
Clifton Haider ◽  
Pradeep Dubey ◽  
...  
Keyword(s):  
Compressive Sensing ◽  
High Performance ◽  
State Of The Art ◽  
Sparse Signals ◽  
Mri Scan ◽  
Nyquist Criterion ◽  
Mri Reconstruction ◽  
Computationally Intensive ◽  
Many Core ◽  
Significant Attention

Compressive sensing (CS) describes how sparse signals can be accurately reconstructed from many fewer samples than required by the Nyquist criterion. Since MRI scan duration is proportional to the number of acquired samples, CS has been gaining significant attention in MRI. However, the computationally intensive nature of CS reconstructions has precluded their use in routine clinical practice. In this work, we investigate how different throughput-oriented architectures can benefit one CS algorithm and what levels of acceleration are feasible on different modern platforms. We demonstrate that a CUDA-based code running on an NVIDIA Tesla C2050 GPU can reconstruct a 256 × 160 × 80 volume from an 8-channel acquisition in 19 seconds, which is in itself a significant improvement over the state of the art. We then show that Intel's Knights Ferry can perform the same 3D MRI reconstruction in only 12 seconds, bringing CS methods even closer to clinical viability.

An Optimized Approach for Breast Cancer Classification for Histopathological Images Based on Hybrid Feature Set

2020 ◽  
Vol 16 ◽  
Author(s):  
Inzamam Mashood Nasir ◽  
Muhammad Rashid ◽  
Jamal Hussain Shah ◽  
Muhammad Sharif ◽  
Muhammad Yahiya Haider Awan ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Cancer Detection ◽  
State Of The Art ◽  
Hybrid Approach ◽  
Classification Performance ◽  
Diagnose Breast Cancer ◽  
Histopathological Images ◽  
And Performance ◽  
Learned Features ◽  
Intelligent Healthcare

Background: Breast cancer is considered as the most perilous sickness among females worldwide and the ratio of new cases is expanding yearly. Many researchers have proposed efficient algorithms to diagnose breast cancer at early stages, which have increased the efficiency and performance by utilizing the learned features of gold standard histopathological images. Objective: Most of these systems have either used traditional handcrafted features or deep features which had a lot of noise and redundancy, which ultimately decrease the performance of the system. Methods: A hybrid approach is proposed by fusing and optimizing the properties of handcrafted and deep features to classify the breast cancer images. HOG and LBP features are serially fused with pretrained models VGG19 and InceptionV3. PCR and ICR are used to evaluate the classification performance of proposed method. Results: The method concentrates on histopathological images to classify the breast cancer. The performance is compared with state-of-the-art techniques, where an overall patient-level accuracy of 97.2% and image-level accuracy of 96.7% is recorded. Conclusion: The proposed hybrid method achieves the best performance as compared to previous methods and it can be used for the intelligent healthcare systems and early breast cancer detection.

NOISE AND TARGET SIGNALS SIMULATION IN PASSIVE SEISMIC LOCATION SYSTEMS

2018 ◽  
pp. 73-78
Author(s):  
Yu. V. Morozov ◽  
M. A. Rajfeld ◽  
A. A. Spektor
Keyword(s):  
Pulse Sequence ◽  
Signal To Noise Ratio ◽  
Seismic Signal ◽  
Seismic Signals ◽  
Simulation Procedure ◽  
Proposed Model ◽  
Seismic Location ◽  
Passive Seismic ◽  
System Characteristics ◽  
Primary Pulse

The paper proposes the model of a person seismic signal with noise for the investigation of passive seismic location system characteristics. The known models based on Gabor and Berlage pulses have been analyzed. These models are not able wholly to consider statistical properties of seismic signals. The proposed model is based on almost cyclic character of seismic signals, Gauss character of fluctuations inside a pulse, random amplitude change from pulse to pulse and relatively small fluctuation of separate pulses positions. The simulation procedure consists of passing the white noise through a linear generating filter with characteristics formed by real steps of a person, and the primary pulse sequence modulation by Gauss functions. The model permits to control the signal-to-noise ratio after its reduction to unity and to vary pulse shifts with respect to person steps irregularity. It has been shown that the model of a person seismic signal with noise agrees with experimental data.

Local seismic attributes

Geophysics ◽  
2007 ◽  
Vol 72 (3) ◽  
pp. A29-A33 ◽  
Author(s):  
Sergey Fomel
Keyword(s):  
Image Registration ◽  
Seismic Signal ◽  
Seismic Attributes ◽  
Data Sets ◽  
Local Similarity ◽  
Seismic Signals ◽  
Practical Applications ◽  
Regularized Inversion ◽  
Signal Characteristics ◽  
Land Survey

Local seismic attributes measure seismic signal characteristics not instantaneously, at each signal point, and not globally, across a data window, but locally in the neighborhood of each point. I define local attributes with the help of regularized inversion and demonstrate their usefulness for measuring local frequencies of seismic signals and local similarity between different data sets. I use shaping regularization for controlling the locality and smoothness of local attributes. A multicomponent-image-registration example from a nine-component land survey illustrates practical applications of local attributes for measuring differences between registered images.

scholarly journals Capsule-LPI: a LncRNA–protein interaction predicting tool based on a capsule network

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Ying Li ◽  
Hang Sun ◽  
Shiyao Feng ◽  
Qi Zhang ◽  
Siyu Han ◽  
...  
Keyword(s):  
Protein Interactions ◽  
State Of The Art ◽  
Recognition Performance ◽  
Feature Learning ◽  
Biological Processes ◽  
Multimodal Features ◽  
Learning Architectures ◽  
Motif Information ◽  
Experimental Comparisons ◽  
Better Than

Abstract Background Long noncoding RNAs (lncRNAs) play important roles in multiple biological processes. Identifying LncRNA–protein interactions (LPIs) is key to understanding lncRNA functions. Although some LPIs computational methods have been developed, the LPIs prediction problem remains challenging. How to integrate multimodal features from more perspectives and build deep learning architectures with better recognition performance have always been the focus of research on LPIs. Results We present a novel multichannel capsule network framework to integrate multimodal features for LPI prediction, Capsule-LPI. Capsule-LPI integrates four groups of multimodal features, including sequence features, motif information, physicochemical properties and secondary structure features. Capsule-LPI is composed of four feature-learning subnetworks and one capsule subnetwork. Through comprehensive experimental comparisons and evaluations, we demonstrate that both multimodal features and the architecture of the multichannel capsule network can significantly improve the performance of LPI prediction. The experimental results show that Capsule-LPI performs better than the existing state-of-the-art tools. The precision of Capsule-LPI is 87.3%, which represents a 1.7% improvement. The F-value of Capsule-LPI is 92.2%, which represents a 1.4% improvement. Conclusions This study provides a novel and feasible LPI prediction tool based on the integration of multimodal features and a capsule network. A webserver (http://csbg-jlu.site/lpc/predict) is developed to be convenient for users.

Compressive Sensing Methods for Reconstruction of Big Sparse Signals

2018 ◽  
pp. 133-150
Author(s):  
Ljubiša Stanković ◽  
Miloš Daković ◽  
Isidora Stanković
Keyword(s):  
Compressive Sensing ◽  
Sparse Signals

scholarly journals Centralized Ranking Loss with Weakly Supervised Localization for Fine-Grained Object Retrieval

2018 ◽  
Author(s):  
Xiawu Zheng ◽  
Rongrong Ji ◽  
Xiaoshuai Sun ◽  
Yongjian Wu ◽  
Feiyue Huang ◽  
...  
Keyword(s):  
State Of The Art ◽  
Feature Learning ◽  
Target Object ◽  
Object Retrieval ◽  
Unified Framework ◽  
Fine Grained ◽  
Discriminative Feature ◽  
Triplet Loss ◽  
Weakly Supervised ◽  
Ranking Loss

Fine-grained object retrieval has attracted extensive research focus recently. Its state-of-the-art schemesare typically based upon convolutional neural network (CNN) features. Despite the extensive progress, two issues remain open. On one hand, the deep features are coarsely extracted at image level rather than precisely at object level, which are interrupted by background clutters. On the other hand, training CNN features with a standard triplet loss is time consuming and incapable to learn discriminative features. In this paper, we present a novel fine-grained object retrieval scheme that conquers these issues in a unified framework. Firstly, we introduce a novel centralized ranking loss (CRL), which achieves a very efficient (1,000times training speedup comparing to the triplet loss) and discriminative feature learning by a ?centralized? global pooling. Secondly, a weakly supervised attractive feature extraction is proposed, which segments object contours with top-down saliency. Consequently, the contours are integrated into the CNN response map to precisely extract features ?within? the target object. Interestingly, we have discovered that the combination of CRL and weakly supervised learning can reinforce each other. We evaluate the performance ofthe proposed scheme on widely-used benchmarks including CUB200-2011 and CARS196. We havereported significant gains over the state-of-the-art schemes, e.g., 5.4% over SCDA [Wei et al., 2017]on CARS196, and 3.7% on CUB200-2011.  

scholarly journals Disentangled Feature Learning Network for Vehicle Re-Identification

2020 ◽  
Author(s):  
Yan Bai ◽  
Yihang Lou ◽  
Yongxing Dai ◽  
Jun Liu ◽  
Ziqian Chen ◽  
...  
Keyword(s):  
State Of The Art ◽  
Feature Learning ◽  
Feature Representation ◽  
Public Security ◽  
The Public ◽  
Common Features ◽  
Learning Network ◽  
Single Feature ◽  
Art Performance

Vehicle Re-Identification (ReID) has attracted lots of research efforts due to its great significance to the public security. In vehicle ReID, we aim to learn features that are powerful in discriminating subtle differences between vehicles which are visually similar, and also robust against different orientations of the same vehicle. However, these two characteristics are hard to be encapsulated into a single feature representation simultaneously with unified supervision. Here we propose a Disentangled Feature Learning Network (DFLNet) to learn orientation specific and common features concurrently, which are discriminative at details and invariant to orientations, respectively. Moreover, to effectively use these two types of features for ReID, we further design a feature metric alignment scheme to ensure the consistency of the metric scales. The experiments show the effectiveness of our method that achieves state-of-the-art performance on three challenging datasets.

Retrieving the leaked signals from noise using a fast dictionary learning method

Geophysics ◽  
2021 ◽  
pp. 1-86
Author(s):  
Wei Chen ◽  
Omar M. Saad ◽  
Yapo Abolé Serge Innocent Oboué ◽  
Liuqing Yang ◽  
Yangkang Chen
Keyword(s):  
Dictionary Learning ◽  
Seismic Data ◽  
State Of The Art ◽  
Computational Cost ◽  
Learning Method ◽  
Global Parameter ◽  
Radius Parameter ◽  
Orthogonalization Method ◽  
Value Decomposition ◽  
Learned Features

Most traditional seismic denoising algorithms will cause damages to useful signals, which are visible from the removed noise profiles and are known as signal leakage. The local signal-and-noise orthogonalization method is an effective method for retrieving the leaked signals from the removed noise. Retrieving leaked signals while rejecting the noise is compromised by the smoothing radius parameter in the local orthogonalization method. It is not convenient to adjust the smoothing radius because it is a global parameter while the seismic data is highly variable locally. To retrieve the leaked signals adaptively, we propose a new dictionary learning method. Because of the patch-based nature of the dictionary learning method, it can adapt to the local feature of seismic data. We train a dictionary of atoms that represent the features of the useful signals from the initially denoised data. Based on the learned features, we retrieve the weak leaked signals from the noise via a sparse co ding step. Considering the large computational cost when training a dictionary from high-dimensional seismic data, we leverage a fast dictionary up dating algorithm, where the singular value decomposition (SVD) is replaced via the algebraic mean to update the dictionary atom. We test the performance of the proposed method on several synthetic and field data examples, and compare it with that from the state-of-the-art local orthogonalization method.

scholarly journals Bayesian Compressive Sensing of Sparse Signals with Unknown Clustering Patterns

Entropy ◽  
2019 ◽  
Vol 21 (3) ◽  
pp. 247 ◽  
Author(s):  
Mohammad Shekaramiz ◽  
Todd Moon ◽  
Jacob Gunther
Keyword(s):  
Compressive Sensing ◽  
Bayesian Learning ◽  
Sparse Signals ◽  
Sparsity Pattern ◽  
Multiple Measurement Vectors ◽  
Measurement Vector ◽  
Clustering Pattern ◽  
Clustering Patterns ◽  
Recovery Problem ◽  
Solution Matrix

We consider the sparse recovery problem of signals with an unknown clustering pattern in the context of multiple measurement vectors (MMVs) using the compressive sensing (CS) technique. For many MMVs in practice, the solution matrix exhibits some sort of clustered sparsity pattern, or clumpy behavior, along each column, as well as joint sparsity across the columns. In this paper, we propose a new sparse Bayesian learning (SBL) method that incorporates a total variation-like prior as a measure of the overall clustering pattern in the solution. We further incorporate a parameter in this prior to account for the emphasis on the amount of clumpiness in the supports of the solution to improve the recovery performance of sparse signals with an unknown clustering pattern. This parameter does not exist in the other existing algorithms and is learned via our hierarchical SBL algorithm. While the proposed algorithm is constructed for the MMVs, it can also be applied to the single measurement vector (SMV) problems. Simulation results show the effectiveness of our algorithm compared to other algorithms for both SMV and MMVs.

Sign in / Sign up

Export Citation Format

Share Document