Iterative deblending for simultaneous source data using the deep neural network

Geophysics ◽  
2020 ◽  
Vol 85 (2) ◽  
pp. V131-V141 ◽  
Author(s):  
Shaohuan Zu ◽  
Junxing Cao ◽  
Shan Qu ◽  
Yangkang Chen
Keyword(s):  
Neural Network ◽  
Field Data ◽  
Deep Neural Network ◽  
Numerical Test ◽  
Synthetic Data ◽  
Data Set ◽  
Source Data ◽  
Simultaneous Source ◽  
Iterative Framework ◽  
Trained Network

Simultaneous source technology can accelerate data acquisition and improve subsurface illumination. But those advantages are compromised due to dense interference. To address the intense interference in simultaneous source data, we have investigated a method based on a deep neural network. The designed architecture consists of convolutional and deconvolutional networks. The convolutional network can learn the local features of the training data set, and the deconvolutional network constructs the output using the extracted features to match the ground truth. Because the main computational cost results from the optimization of the network parameters, the trained network can separate simultaneous source data efficiently. Besides, with the given dithering code, we embed the trained network into an iterative framework that can further improve the deblending. A numerical test on synthetic data demonstrates that the iterative framework with the trained network can obtain comparable performance with high efficiency compared to the conventional method. Next, we test our method with two different trained networks (one is from a synthetic data set, and the other is from a field data set) on field data. The test results confirm the performance of our method.

A periodically varying code for improving deblending of simultaneous sources in marine acquisition

Geophysics ◽  
2016 ◽  
Vol 81 (3) ◽  
pp. V213-V225 ◽  
Author(s):  
Shaohuan Zu ◽  
Hui Zhou ◽  
Yangkang Chen ◽  
Shan Qu ◽  
Xiaofeng Zou ◽  
...  
Keyword(s):  
Field Data ◽  
Synthetic Data ◽  
Data Sets ◽  
Ocean Bottom ◽  
Data Set ◽  
Acceptable Model ◽  
Model Subspace ◽  
New Form ◽  
Simultaneous Source ◽  
Practical Field

We have designed a periodically varying code that can avoid the problem of the local coherency and make the interference distribute uniformly in a given range; hence, it was better at suppressing incoherent interference (blending noise) and preserving coherent useful signals compared with a random dithering code. We have also devised a new form of the iterative method to remove interference generated from the simultaneous source acquisition. In each iteration, we have estimated the interference using the blending operator following the proposed formula and then subtracted the interference from the pseudodeblended data. To further eliminate the incoherent interference and constrain the inversion, the data were then transformed to an auxiliary sparse domain for applying a thresholding operator. During the iterations, the threshold was decreased from the largest value to zero following an exponential function. The exponentially decreasing threshold aimed to gradually pass the deblended data to a more acceptable model subspace. Two numerically blended synthetic data sets and one numerically blended practical field data set from an ocean bottom cable were used to demonstrate the usefulness of our proposed method and the better performance of the periodically varying code over the traditional random dithering code.

Method of determination of the text direction on the image with the use of convolutional neural network

2020 ◽  
pp. 96-99
Author(s):  
P.L. Nikolaev
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Deep Neural Network ◽  
Binary Classification ◽  
Synthetic Data ◽  
Real Data ◽  
Method Of Determination ◽  
Classification Of Images

This article deals with method of binary classification of images with small text on them Classification is based on the fact that the text can have 2 directions – it can be positioned horizontally and read from left to right or it can be turned 180 degrees so the image must be rotated to read the sign. This type of text can be found on the covers of a variety of books, so in case of recognizing the covers, it is necessary first to determine the direction of the text before we will directly recognize it. The article suggests the development of a deep neural network for determination of the text position in the context of book covers recognizing. The results of training and testing of a convolutional neural network on synthetic data as well as the examples of the network functioning on the real data are presented.

scholarly journals An efficient technique for CT scan images classification of COVID-19

2020 ◽  
pp. 1-14
Author(s):  
Esraa Hassan ◽  
Noha A. Hikal ◽  
Samir Elmuogy
Keyword(s):  
Neural Network ◽  
Diagnostic Tool ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Performance Metrics ◽  
Classification Model ◽  
Data Set ◽  
Training Models ◽  
The Earth ◽  
Diagnostic Time

Nowadays, Coronavirus (COVID-19) considered one of the most critical pandemics in the earth. This is due its ability to spread rapidly between humans as well as animals. COVID_19 expected to outbreak around the world, around 70 % of the earth population might infected with COVID-19 in the incoming years. Therefore, an accurate and efficient diagnostic tool is highly required, which the main objective of our study. Manual classification was mainly used to detect different diseases, but it took too much time in addition to the probability of human errors. Automatic image classification reduces doctors diagnostic time, which could save human’s life. We propose an automatic classification architecture based on deep neural network called Worried Deep Neural Network (WDNN) model with transfer learning. Comparative analysis reveals that the proposed WDNN model outperforms by using three pre-training models: InceptionV3, ResNet50, and VGG19 in terms of various performance metrics. Due to the shortage of COVID-19 data set, data augmentation was used to increase the number of images in the positive class, then normalization used to make all images have the same size. Experimentation is done on COVID-19 dataset collected from different cases with total 2623 where (1573 training,524 validation,524 test). Our proposed model achieved 99,046, 98,684, 99,119, 98,90 In terms of Accuracy, precision, Recall, F-score, respectively. The results are compared with both the traditional machine learning methods and those using Convolutional Neural Networks (CNNs). The results demonstrate the ability of our classification model to use as an alternative of the current diagnostic tool.

scholarly journals Deep Neural Network for Gender-Based Violence Detection on Twitter Messages

Mathematics ◽  
2021 ◽  
Vol 9 (8) ◽  
pp. 807
Author(s):  
Carlos M. Castorena ◽  
Itzel M. Abundez ◽  
Roberto Alejo ◽  
Everardo E. Granda-Gutiérrez ◽  
Eréndira Rendón ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Gender Violence ◽  
Strategic Decision ◽  
Learning Approaches ◽  
Gender Based Violence ◽  
Data Set ◽  
Violence Detection ◽  
Governmental Institutions ◽  
Gender Based

The problem of gender-based violence in Mexico has been increased considerably. Many social associations and governmental institutions have addressed this problem in different ways. In the context of computer science, some effort has been developed to deal with this problem through the use of machine learning approaches to strengthen the strategic decision making. In this work, a deep learning neural network application to identify gender-based violence on Twitter messages is presented. A total of 1,857,450 messages (generated in Mexico) were downloaded from Twitter: 61,604 of them were manually tagged by human volunteers as negative, positive or neutral messages, to serve as training and test data sets. Results presented in this paper show the effectiveness of deep neural network (about 80% of the area under the receiver operating characteristic) in detection of gender violence on Twitter messages. The main contribution of this investigation is that the data set was minimally pre-processed (as a difference versus most state-of-the-art approaches). Thus, the original messages were converted into a numerical vector in accordance to the frequency of word’s appearance and only adverbs, conjunctions and prepositions were deleted (which occur very frequently in text and we think that these words do not contribute to discriminatory messages on Twitter). Finally, this work contributes to dealing with gender violence in Mexico, which is an issue that needs to be faced immediately.

scholarly journals RISC-V Virtual Platform-Based Convolutional Neural Network Accelerator Implemented in SystemC

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1514
Author(s):  
Seung-Ho Lim ◽  
WoonSik William Suh ◽  
Jin-Young Kim ◽  
Sang-Young Cho
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Model ◽  
Neural Network Model ◽  
Deep Neural Network ◽  
System Level ◽  
Neural Network Models ◽  
Data Set ◽  
Embedded Device ◽  
Virtual Platform

The optimization for hardware processor and system for performing deep learning operations such as Convolutional Neural Networks (CNN) in resource limited embedded devices are recent active research area. In order to perform an optimized deep neural network model using the limited computational unit and memory of an embedded device, it is necessary to quickly apply various configurations of hardware modules to various deep neural network models and find the optimal combination. The Electronic System Level (ESL) Simulator based on SystemC is very useful for rapid hardware modeling and verification. In this paper, we designed and implemented a Deep Learning Accelerator (DLA) that performs Deep Neural Network (DNN) operation based on the RISC-V Virtual Platform implemented in SystemC in order to enable rapid and diverse analysis of deep learning operations in an embedded device based on the RISC-V processor, which is a recently emerging embedded processor. The developed RISC-V based DLA prototype can analyze the hardware requirements according to the CNN data set through the configuration of the CNN DLA architecture, and it is possible to run RISC-V compiled software on the platform, can perform a real neural network model like Darknet. We performed the Darknet CNN model on the developed DLA prototype, and confirmed that computational overhead and inference errors can be analyzed with the DLA prototype developed by analyzing the DLA architecture for various data sets.

scholarly journals Coupled hydrogeophysical parameter estimation using a sequential Bayesian approach

2010 ◽  
Vol 14 (3) ◽  
pp. 545-556 ◽  
Author(s):  
J. Rings ◽  
J. A. Huisman ◽  
H. Vereecken
Keyword(s):  
Water Content ◽  
Particle Filtering ◽  
Field Data ◽  
Synthetic Data ◽  
Time Domain Reflectometry ◽  
Second Step ◽  
Parameter Estimates ◽  
Posterior Distributions ◽  
Data Set ◽  
Resistivity Tomography

Abstract. Coupled hydrogeophysical methods infer hydrological and petrophysical parameters directly from geophysical measurements. Widespread methods do not explicitly recognize uncertainty in parameter estimates. Therefore, we apply a sequential Bayesian framework that provides updates of state, parameters and their uncertainty whenever measurements become available. We have coupled a hydrological and an electrical resistivity tomography (ERT) forward code in a particle filtering framework. First, we analyze a synthetic data set of lysimeter infiltration monitored with ERT. In a second step, we apply the approach to field data measured during an infiltration event on a full-scale dike model. For the synthetic data, the water content distribution and the hydraulic conductivity are accurately estimated after a few time steps. For the field data, hydraulic parameters are successfully estimated from water content measurements made with spatial time domain reflectometry and ERT, and the development of their posterior distributions is shown.

scholarly journals Deep Neural Network Algorithm Feedback Model with Behavioral Intelligence and Forecast Accuracy

Symmetry ◽  
2020 ◽  
Vol 12 (9) ◽  
pp. 1465
Author(s):  
Taikyeong Jeong
Keyword(s):  
Neural Network ◽  
Classification Accuracy ◽  
Deep Neural Network ◽  
Time Series Data ◽  
Training Data ◽  
Series Data ◽  
Context Aware ◽  
Data Set ◽  
Feedback Model ◽  
Data Connection

When attempting to apply a large-scale database that holds the behavioral intelligence training data of deep neural networks, the classification accuracy of the artificial intelligence algorithm needs to reflect the behavioral characteristics of the individual. When a change in behavior is recognized, that is, a feedback model based on a data connection model is applied, an analysis of time series data is performed by extracting feature vectors and interpolating data in a deep neural network to overcome the limitations of the existing statistical analysis. Using the results of the first feedback model as inputs to the deep neural network and, furthermore, as the input values of the second feedback model, and interpolating the behavioral intelligence data, that is, context awareness and lifelog data, including physical activities, involves applying the most appropriate conditions. The results of this study show that this method effectively improves the accuracy of the artificial intelligence results. In this paper, through an experiment, after extracting the feature vector of a deep neural network and restoring the missing value, the classification accuracy was verified to improve by about 20% on average. At the same time, by adding behavioral intelligence data to the time series data, a new data connection model, the Deep Neural Network Feedback Model, was proposed, and it was verified that the classification accuracy can be improved by about 8 to 9% on average. Based on the hypothesis, the F (X′) = X model was applied to thoroughly classify the training data set and test data set to present a symmetrical balance between the data connection model and the context-aware data. In addition, behavioral activity data were extrapolated in terms of context-aware and forecasting perspectives to prove the results of the experiment.

3D plane-wave migration in tilted coordinates: A field data example

Geophysics ◽  
2009 ◽  
Vol 74 (6) ◽  
pp. WCA199-WCA209 ◽  
Author(s):  
Guojian Shan ◽  
Robert Clapp ◽  
Biondo Biondi
Keyword(s):  
Plane Wave ◽  
Field Data ◽  
Synthetic Data ◽  
Data Set ◽  
Wave Source ◽  
Surface Data ◽  
The One ◽  
Wave Migration ◽  
Wavefield Extrapolation ◽  
Slant Stacking

We have extended isotropic plane-wave migration in tilted coordinates to 3D anisotropic media and applied it on a Gulf of Mexico data set. Recorded surface data are transformed to plane-wave data by slant-stack processing in inline and crossline directions. The source plane wave and its corresponding slant-stacked data are extrapolated into the subsurface within a tilted coordinate system whose direction depends on the propagation direction of the plane wave. Images are generated by crosscorrelating these two wavefields. The shot sampling is sparse in the crossline direction, and the source generated by slant stacking is not really a plane-wave source but a phase-encoded source. We have discovered that phase-encoded source migration in tilted coordinates can image steep reflectors, using 2D synthetic data set examples. The field data example shows that 3D plane-wave migration in tilted coordinates can image steeply dipping salt flanks and faults, even though the one-way wave-equation operator is used for wavefield extrapolation.

CENTROID NEURAL NETWORK WITH WEIGHTED FEATURES

2009 ◽  
Vol 18 (08) ◽  
pp. 1353-1367 ◽  
Author(s):  
DONG-CHUL PARK
Keyword(s):  
Neural Network ◽  
Image Compression ◽  
Objective Function ◽  
Lagrange Multiplier ◽  
Synthetic Data ◽  
Feature Weighting ◽  
The Self ◽  
Self Organizing Map ◽  
Data Set ◽  
Self Organizing

A Centroid Neural Network with Weighted Features (CNN-WF) is proposed and presented in this paper. The proposed CNN-WF is based on a Centroid Neural Network (CNN), an effective clustering tool that has been successfully applied to various problems. In order to evaluate the importance of each feature in a set of data, a feature weighting concept is introduced to the Centroid Neural Network in the proposed algorithm. The weight update equations for CNN-WF are derived by applying the Lagrange multiplier procedure to the objective function constructed for CNN-WF in this paper. The use of weighted features makes it possible to assess the importance of each feature and to reject features that can be considered as noise in data. Experiments on a synthetic data set and a typical image compression problem show that the proposed CNN-WF can assess the importance of each feature and the proposed CNN-WF outperforms conventional algorithms including the Self-Organizing Map (SOM) and CNN in terms of clustering accuracy.

scholarly journals Deep Neural Networks for the Classification of Bank Marketing Data using Data Reduction Techniques

2019 ◽  
Vol 8 (3) ◽  
pp. 4373-4378
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Data Reduction ◽  
Deep Neural Network ◽  
Training Data ◽  
Neural Network Classifier ◽  
Data Set ◽  
Reduction Techniques ◽  
Marketing Data ◽  
Bank Marketing

The amount of data belonging to different domains are being stored rapidly in various repositories across the globe. Extracting useful information from the huge volumes of data is always difficult due to the dynamic nature of data being stored. Data Mining is a knowledge discovery process used to extract the hidden information from the data stored in various repositories, termed as warehouses in the form of patterns. One of the popular tasks of data mining is Classification, which deals with the process of distinguishing every instance of a data set into one of the predefined class labels. Banking system is one of the realworld domains, which collects huge number of client data on a daily basis. In this work, we have collected two variants of the bank marketing data set pertaining to a Portuguese financial institution consisting of 41188 and 45211 instances and performed classification on them using two data reduction techniques. Attribute subset selection has been performed on the first data set and the training data with the selected features are used in classification. Principal Component Analysis has been performed on the second data set and the training data with the extracted features are used in classification. A deep neural network classification algorithm based on Backpropagation has been developed to perform classification on both the data sets. Finally, comparisons are made on the performance of each deep neural network classifier with the four standard classifiers, namely Decision trees, Naïve Bayes, Support vector machines, and k-nearest neighbors. It has been found that the deep neural network classifier outperforms the existing classifiers in terms of accuracy

Sign in / Sign up

Export Citation Format

Share Document