De-bubbling Seismic Data using a Generalized Neural Network

Geophysics ◽  
2021 ◽  
pp. 1-73
Author(s):  
Thomas de Jonge ◽  
Vetle Vinje ◽  
Gordon Poole ◽  
Song Hou ◽  
Einar Iversen
Keyword(s):  
Neural Network ◽  
Continental Shelf ◽  
Test Data ◽  
Near Field ◽  
Real Data ◽  
Training Data ◽  
Source Modeling ◽  
Field Source ◽  
Air Gun ◽  
Norwegian Continental Shelf

Estimating the far-field source signature has always been an important part of seismic processing. However, estimating the source signature from an air gun array is difficult because of the complex interaction between the air bubble oscillations from each air gun, the state of the sea surface, variations in air pressure, the air guns geometry, etc. Removing the bubble noise is important since proper seismic imaging requires a zero-phased, spiky wavelet. De-bubbling has conventionally been done by deconvolution using an (assumed) known source signature. Several methods to estimate the signature and de-bubble the data have been implemented, for instance, source modeling or using near-field hydrophone measurements. We describe an alternative approach using a convolutional neural network for de-bubbling. The network is trained on real data containing a large range of source signatures to make the network robust and adaptive to signature variations. If the signature in the test data is equal to one of the signatures used in the training, the network performs well. Also, if the signature changes in the middle of a sail line, the network can adapt to this change. Moreover, we investigate the network’s sensitivity to changing geology within a survey and on two different surveys on the Norwegian Continental Shelf. If the test data are from similar geology as the training data, the network performs better than if not. Even when applied to a different part of the Norwegian Continental Shelf, the network is still able to remove most of the bubble noise.

scholarly journals Batik pattern recognition using convolutional neural network

2020 ◽  
Vol 9 (4) ◽  
pp. 1430-1437
Author(s):  
Mohammad Arif Rasyidi ◽  
Taufiqotul Bariyah
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Convolutional Neural Network ◽  
Test Data ◽  
Network Architecture ◽  
Experimental Results ◽  
Training Data ◽  
Excellent Performance ◽  
Artistic Value

Batik is one of Indonesia's cultures that is well-known worldwide. Batik is a fabric that is painted using canting and liquid wax so that it forms patterns of high artistic value. In this study, we applied the convolutional neural network (CNN) to identify six batik patterns, namely Banji, Ceplok, Kawung, Mega Mendung, Parang, and Sekar Jagad. 994 images from the 6 categories were collected and then divided into training and test data with a ratio of 8:2. Image augmentation was also done to provide variations in training data as well as to prevent overfitting. Experimental results on the test data showed that CNN produced an excellent performance as indicated by accuracy of 94% and top-2 accuracy of 99% which was obtained using the DenseNet network architecture.

scholarly journals Deep Learning Neural Networks to Predict Serious Complications After Bariatric Surgery: Analysis of Scandinavian Obesity Surgery Registry Data (Preprint)

2019 ◽  
Author(s):  
Yang Cao ◽  
Scott Montgomery ◽  
Johan Ottosson ◽  
Erik Näslund ◽  
Erik Stenberg
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bariatric Surgery ◽  
Deep Learning ◽  
Postoperative Complications ◽  
Obesity Surgery ◽  
Test Data ◽  
Registry Data ◽  
Training Data ◽  
Complications After Bariatric Surgery

BACKGROUND Obesity is one of today’s most visible public health problems worldwide. Although modern bariatric surgery is ostensibly considered safe, serious complications and mortality still occur in some patients. OBJECTIVE This study aimed to explore whether serious postoperative complications of bariatric surgery recorded in a national quality registry can be predicted preoperatively using deep learning methods. METHODS Patients who were registered in the Scandinavian Obesity Surgery Registry (SOReg) between 2010 and 2015 were included in this study. The patients who underwent a bariatric procedure between 2010 and 2014 were used as training data, and those who underwent a bariatric procedure in 2015 were used as test data. Postoperative complications were graded according to the Clavien-Dindo classification, and complications requiring intervention under general anesthesia or resulting in organ failure or death were considered serious. Three supervised deep learning neural networks were applied and compared in our study: multilayer perceptron (MLP), convolutional neural network (CNN), and recurrent neural network (RNN). The synthetic minority oversampling technique (SMOTE) was used to artificially augment the patients with serious complications. The performances of the neural networks were evaluated using accuracy, sensitivity, specificity, Matthews correlation coefficient, and area under the receiver operating characteristic curve. RESULTS In total, 37,811 and 6250 patients were used as the training data and test data, with incidence rates of serious complication of 3.2% (1220/37,811) and 3.0% (188/6250), respectively. When trained using the SMOTE data, the MLP appeared to have a desirable performance, with an area under curve (AUC) of 0.84 (95% CI 0.83-0.85). However, its performance was low for the test data, with an AUC of 0.54 (95% CI 0.53-0.55). The performance of CNN was similar to that of MLP. It generated AUCs of 0.79 (95% CI 0.78-0.80) and 0.57 (95% CI 0.59-0.61) for the SMOTE data and test data, respectively. Compared with the MLP and CNN, the RNN showed worse performance, with AUCs of 0.65 (95% CI 0.64-0.66) and 0.55 (95% CI 0.53-0.57) for the SMOTE data and test data, respectively. CONCLUSIONS MLP and CNN showed improved, but limited, ability for predicting the postoperative serious complications after bariatric surgery in the Scandinavian Obesity Surgery Registry data. However, the overfitting issue is still apparent and needs to be overcome by incorporating intra- and perioperative information. CLINICALTRIAL

scholarly journals Deep Learning Neural Networks to Predict Serious Complications After Bariatric Surgery: Analysis of Scandinavian Obesity Surgery Registry Data

10.2196/15992 ◽  
2020 ◽  
Vol 8 (5) ◽  
pp. e15992 ◽  
Author(s):  
Yang Cao ◽  
Scott Montgomery ◽  
Johan Ottosson ◽  
Erik Näslund ◽  
Erik Stenberg
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bariatric Surgery ◽  
Deep Learning ◽  
Postoperative Complications ◽  
Obesity Surgery ◽  
Test Data ◽  
Registry Data ◽  
Training Data ◽  
Complications After Bariatric Surgery

Background Obesity is one of today’s most visible public health problems worldwide. Although modern bariatric surgery is ostensibly considered safe, serious complications and mortality still occur in some patients. Objective This study aimed to explore whether serious postoperative complications of bariatric surgery recorded in a national quality registry can be predicted preoperatively using deep learning methods. Methods Patients who were registered in the Scandinavian Obesity Surgery Registry (SOReg) between 2010 and 2015 were included in this study. The patients who underwent a bariatric procedure between 2010 and 2014 were used as training data, and those who underwent a bariatric procedure in 2015 were used as test data. Postoperative complications were graded according to the Clavien-Dindo classification, and complications requiring intervention under general anesthesia or resulting in organ failure or death were considered serious. Three supervised deep learning neural networks were applied and compared in our study: multilayer perceptron (MLP), convolutional neural network (CNN), and recurrent neural network (RNN). The synthetic minority oversampling technique (SMOTE) was used to artificially augment the patients with serious complications. The performances of the neural networks were evaluated using accuracy, sensitivity, specificity, Matthews correlation coefficient, and area under the receiver operating characteristic curve. Results In total, 37,811 and 6250 patients were used as the training data and test data, with incidence rates of serious complication of 3.2% (1220/37,811) and 3.0% (188/6250), respectively. When trained using the SMOTE data, the MLP appeared to have a desirable performance, with an area under curve (AUC) of 0.84 (95% CI 0.83-0.85). However, its performance was low for the test data, with an AUC of 0.54 (95% CI 0.53-0.55). The performance of CNN was similar to that of MLP. It generated AUCs of 0.79 (95% CI 0.78-0.80) and 0.57 (95% CI 0.59-0.61) for the SMOTE data and test data, respectively. Compared with the MLP and CNN, the RNN showed worse performance, with AUCs of 0.65 (95% CI 0.64-0.66) and 0.55 (95% CI 0.53-0.57) for the SMOTE data and test data, respectively. Conclusions MLP and CNN showed improved, but limited, ability for predicting the postoperative serious complications after bariatric surgery in the Scandinavian Obesity Surgery Registry data. However, the overfitting issue is still apparent and needs to be overcome by incorporating intra- and perioperative information.

scholarly journals Classifying online corporate reputation with machine learning: a study in the banking domain

2019 ◽  
Vol 30 (1) ◽  
pp. 45-66 ◽  
Author(s):  
Anette Rantanen ◽  
Joni Salminen ◽  
Filip Ginter ◽  
Bernard J. Jansen
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Social Media ◽  
Corporate Reputation ◽  
Real Data ◽  
High Volume ◽  
Training Data ◽  
Real World Data ◽  
Content Type ◽  
Classification Framework

Purpose User-generated social media comments can be a useful source of information for understanding online corporate reputation. However, the manual classification of these comments is challenging due to their high volume and unstructured nature. The purpose of this paper is to develop a classification framework and machine learning model to overcome these limitations. Design/methodology/approach The authors create a multi-dimensional classification framework for the online corporate reputation that includes six main dimensions synthesized from prior literature: quality, reliability, responsibility, successfulness, pleasantness and innovativeness. To evaluate the classification framework’s performance on real data, the authors retrieve 19,991 social media comments about two Finnish banks and use a convolutional neural network (CNN) to classify automatically the comments based on manually annotated training data. Findings After parameter optimization, the neural network achieves an accuracy between 52.7 and 65.2 percent on real-world data, which is reasonable given the high number of classes. The findings also indicate that prior work has not captured all the facets of online corporate reputation. Practical implications For practical purposes, the authors provide a comprehensive classification framework for online corporate reputation, which companies and organizations operating in various domains can use. Moreover, the authors demonstrate that using a limited amount of training data can yield a satisfactory multiclass classifier when using CNN. Originality/value This is the first attempt at automatically classifying online corporate reputation using an online-specific classification framework.

Elimination of the Collision States of the Effectors of Industrial Robots by Application of Neural Networks

2015 ◽  
Vol 798 ◽  
pp. 276-281
Author(s):  
Erik Prada ◽  
Lenka Baločková ◽  
Michael Valášek
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Test Data ◽  
Learning Algorithms ◽  
Robotic System ◽  
Industrial Robots ◽  
Training Data ◽  
Methods Of Learning ◽  
In The Beginning

The article deals with the usage of methods of learning algorithms of neural networks for solving of collision states problem within multi-robotic cooperation. Nowadays, multi-robotic cooperation is a highly used method of work of two or more industrial robots. The requirements for elimination of collision states are getting more difficult when the multi-robotic system is more complicated. Methods of neural networks provide suitable tools for solving of complex cooperating problems. In the beginning of the article, we discuss the term “collision state” and the possibilities of its solving. In the following chapter, we discuss the theory of neural networks and learning algorithms, which we applied in solving of the collision states. In the final chapter, we implemented the practical verification of the model neural network in JSNN programme. It consisted of creating and learning of the training data and subsequent verification of the test data.

Estimating adsorption isotherm parameters in chromatography via a virtual injection promoting double feed-forward neural network

2022 ◽  
Vol 0 (0) ◽  
Author(s):  
Chen Xu ◽  
Ye Zhang
Keyword(s):  
Neural Network ◽  
Adsorption Isotherms ◽  
Regularization Parameter ◽  
Real Data ◽  
Training Data ◽  
Inversion Method ◽  
Feed Forward Neural Network ◽  
Feed Forward ◽  
Ill Posed ◽  
Physics Model

Abstract The means to obtain the adsorption isotherms is a fundamental open problem in competitive chromatography. A modern technique of estimating adsorption isotherms is to solve a nonlinear inverse problem in a partial differential equation so that the simulated batch separation coincides with actual experimental results. However, this identification process is usually ill-posed in the sense that the uniqueness of adsorption isotherms cannot be guaranteed, and moreover, the small noise in the measured response can lead to a large fluctuation in the traditional estimation of adsorption isotherms. The conventional mathematical method of solving this problem is the variational regularization, which is formulated as a non-convex minimization problem with a regularized objective functional. However, in this method, the choice of regularization parameter and the design of a convergent solution algorithm are quite difficult in practice. Moreover, due to the restricted number of injection profiles in experiments, the types of measured data are extremely limited, which may lead to a biased estimation. In order to overcome these difficulties, in this paper, we develop a new inversion method – the virtual injection promoting double feed-forward neural network (VIP-DFNN). In this approach, the training data contain various types of artificial injections and synthetic noisy measurement at outlet, generated by a conventional physics model – a time-dependent convection-diffusion system. Numerical experiments with both artificial and real data from laboratory experiments show that the proposed VIP-DFNN is an efficient and robust algorithm.

Use of multiattribute transforms to predict log properties from seismic data

Geophysics ◽  
2001 ◽  
Vol 66 (1) ◽  
pp. 220-236 ◽  
Author(s):  
Daniel P. Hampson ◽  
James S. Schuelke ◽  
John A. Quirein
Keyword(s):  
Neural Network ◽  
Seismic Data ◽  
Prediction Error ◽  
Probabilistic Neural Network ◽  
Real Data ◽  
Analysis Data ◽  
Training Data ◽  
Average Error ◽  
Validation Data ◽  
Linear Mode

We describe a new method for predicting well‐log properties from seismic data. The analysis data consist of a series of target logs from wells which tie a 3-D seismic volume. The target logs theoretically may be of any type; however, the greatest success to date has been in predicting porosity logs. From the 3-D seismic volume a series of sample‐based attributes is calculated. The objective is to derive a multiattribute transform, which is a linear or nonlinear transform between a subset of the attributes and the target log values. The selected subset is determined by a process of forward stepwise regression, which derives increasingly larger subsets of attributes. An extension of conventional crossplotting involves the use of a convolutional operator to resolve frequency differences between the target logs and the seismic data. In the linear mode, the transform consists of a series of weights derived by least‐squares minimization. In the nonlinear mode, a neural network is trained, using the selected attributes as inputs. Two types of neural networks have been evaluated: the multilayer feedforward network (MLFN) and the probabilistic neural network (PNN). Because of its mathematical simplicity, the PNN appears to be the network of choice. To estimate the reliability of the derived multiattribute transform, crossvalidation is used. In this process, each well is systematically removed from the training set, and the transform is rederived from the remaining wells. The prediction error for the hidden well is then calculated. The validation error, which is the average error for all hidden wells, is used as a measure of the likely prediction error when the transform is applied to the seismic volume. The method is applied to two real data sets. In each case, we see a continuous improvement in predictive power as we progress from single‐attribute regression to linear multiattribute prediction to neural network prediction. This improvement is evident not only on the training data but, more importantly, on the validation data. In addition, the neural network shows a significant improvement in resolution over that from linear regression.

scholarly journals Identification of Non-linear Systems through Convolutional Neural Network

2019 ◽  
Vol 8 (3) ◽  
pp. 3429-3434
Keyword(s):  
Neural Network ◽  
Nonlinear Systems ◽  
Convolutional Neural Network ◽  
Control Systems ◽  
Linear Systems ◽  
Test Data ◽  
Training Data ◽  
Analysis And Design ◽  
Non Linear ◽  
Non Linear Systems

The theory of control systems deals with the analysis and design of interacting components of a system in a configuration that provides the desired behavior. This paper deals with the problem of the identification of non-linear systems through Convolutional Neural Network (CNN). We propose a structure of a CNN and perform simulations with test data using unsupervised learning for the identification of nonlinear systems. Also, MLP is used to compare the results when there is noise in the training data, which allows us to see that the proposed CNN has better performance and can be used for cases where the noise is present. The proposed CNN is validated with test data. Tests are carried out with Gas oven data, comparing the proposed structure of CNN with a MLP. When there is noise in the data, CNN has better performance than MLP.

scholarly journals Gorontalo Medicinal Plants Image Identification System Using Artificial Neural Network with Back Propagation

2018 ◽  
Vol 2 (2) ◽  
Author(s):  
Mukhlisulfatih Latief ◽  
Rampi Yusuf
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Artificial Neural Network ◽  
Medicinal Plants ◽  
Digital Image Processing ◽  
Test Data ◽  
Digital Image ◽  
Back Propagation ◽  
Training Data ◽  
Artificial Neural

The purpose of this research is to design the application of digital image processing system to identify the image of medicinal plants of Gorontalo region using artificial neural network method using back propagation. This research used a digital image processing method with segmentation and extraction techniques. Segmentation process was carried out using thresholding method. Furthermore, a process of characteristic extraction from medicinal plants drawings was carried out using feature and color feature extractions to obtain the value of metric, eccentricity, hue, saturation and value. these five values were used as parameters for input neurons and one output neuron which denoted the class of the medicinal plants image. Data of this research consisted of 91 images which had been divided into two types, training data and test data. The training data consisted of 80 images and the test data consisted of eleven images. A network architecture was obtained from the training result and it provided the highest accuracy level (100%) and least number of iteration with a number of 50 neurons on hidden layer and 143 epochs. The testing result showed a lower accuracy of 54.54%.

scholarly journals Improvement of E-learning Based via Learning Management Systems (LMS) Using Artificial Neural Networks

2019 ◽  
pp. 1-9
Author(s):  
Khaled . M. G Noama ◽  
Ahmed Khalid ◽  
Arafat A. Muharram ◽  
Ibrahim A. Ahmed
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Real Data ◽  
Feedforward Neural Network ◽  
Learning System ◽  
Training Data ◽  
Factors Affecting ◽  
Virtual Class ◽  
Innovative Learning ◽  
E Learning

E-Learning nowadays is one of the learning system which uses the latest technologies in the field of innovative learning, it has been an extension of traditional education. The effectiveness of E-Learning lies in achievement of education and improving the student's performance and its reflection on the demands of students by discovering the weaknesses and strengths of the factors affecting distance learning. In this research we have used the multilayered neural networks (feedforward neural network) with an input of five neurons which represent the five criteria (virtual class presence, Discussion during semester, Solving Quiz, Mid-term examination, Assignment), hidden layer has two neurons and the output layers have one neuron. to estimate the performance of the students attending an E-Learning course, feedforward neural network was  applied to real data )400 student records (80%) are used for training data and the remaining 100 records (20%) are used as test data, performance = 0.0699), to  predict the performance of  the students   that reflect their real grades.

Sign in / Sign up

Export Citation Format

Share Document