scholarly journals Comparison of Algebraic Reconstruction Technique Methods and Generative Adversarial Network in Image Reconstruction of Magnetic Induction Tomography (MIT)

2021 ◽  
Vol 2071 (1) ◽  
pp. 012044
Author(s):  
A J Lubis ◽  
N F Mohd Nasir ◽  
Z Zakaria ◽  
M Jusoh ◽  
M M Azizan ◽  
...  
Keyword(s):  
Neural Network ◽  
Regularization Method ◽  
Tikhonov Regularization Method ◽  
Reconstruction Technique ◽  
Algebraic Reconstruction Technique ◽  
Training Process ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Non Linear ◽  
Magnetic Induction Tomography

Abstract Magnetic induction tomography (MIT) is a technique used for imaging electromagnetic properties of objects using eddy current effects. The non-linear characteristics had led to more difficulties with its solution especially in dealing with low conductivity imaging materials such as biological tissues. Two methods that could be applied for MIT image processing which is the Generative Adversarial Network (GAN) and the Algebraic Reconstruction Technique (ART). ART is widely used in the industry due to its ability to improve the quality of the reconstructed image at a high scanning speed. GAN is an intelligent method which would be able to carry out the training process. In the GAN method, the MIT principle is used to find the optimum global conductivity distribution and it is described as a training process and later, reconstructed by a generator. The output is an approximate reconstruction of the distribution’s internal conductivity image. Then, the results were compared with the previous traditional algorithm, namely the regularization algorithm of BPNN and Tikhonov Regularization method. It turned out that GAN had able to adjust the non-linear relationship between input and output. GAN was also able to solve non-linear problems that cannot be solved in the previous traditional algorithms, namely Back Propagation Neural Network (BPNN) and Tikhonov Regularization method. There are several other intelligent algorithms such as CNN (Convolution Neural Network) and K-NN (K-Nearest Neighbor), but such algorithms have not been able to produce the expected image quality. Thus, further study is still needed for the improvement of the image quality. The expected result in this study is the comparison of these two techniques, namely ART and GAN to get the best results on the image reconstruction using MIT. Thus, it is shown that GAN is a better candidate for this purpose.

scholarly journals A Stopping Criterion for the Training Process of the Specific Signal Generator

2021 ◽  
Vol 50 (1) ◽  
pp. 153-170
Author(s):  
Lizhi Cui ◽  
Peichao Zhao ◽  
Bingfeng Li ◽  
Xinwei Li ◽  
Keping Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Signal Generator ◽  
Complex Signal ◽  
Explicit Criterion ◽  
Stopping Criterion ◽  
Training Process ◽  
Generative Adversarial Network ◽  
Specific Signal ◽  
Adversarial Network ◽  
Single Neural Network

Mathematical description of a complex signal is very important in engineering but nearly impossible in many occasions. The emergence of the Generative Adversarial Network (GAN) shows the possibility to train a single neural network to be a Specific Signal Generator (SSG), which is only controlled by a random vector with several elements. However, there is no explicit criterion for the GAN training process to stop, and in real applications the training always stops after a certain big iteration. In this paper, a serious issue was discussed during the process to use GAN as a SSG. And, an explicit criterion for the GAN as a SSG to stop the training process were proposed. Several experiments were carried out to illustrate the issues mentioned above and the effectiveness of the stopping criterion proposed in this paper.

scholarly journals Application of a Generative Adversarial Network in Image Reconstruction of Magnetic Induction Tomography

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3869
Author(s):  
Dan Yang ◽  
Jiahua Liu ◽  
Yuchen Wang ◽  
Bin Xu ◽  
Xu Wang
Keyword(s):  
Image Reconstruction ◽  
Magnetic Induction ◽  
Mean Squared Error ◽  
Voltage Measurement ◽  
Generative Adversarial Network ◽  
Conductivity Distribution ◽  
Adversarial Network ◽  
Non Linear ◽  
Ill Posed ◽  
Magnetic Induction Tomography

Image reconstruction of Magnetic induction tomography (MIT) is an ill-posed problem. The non-linear characteristics lead many difficulties to its solution. In this paper, a method based on a Generative Adversarial Network (GAN) is presented to tackle these barriers. Firstly, the principle of MIT is analyzed. Then the process for finding the global optimum of conductivity distribution is described as a training process, and the GAN model is proposed. Finally, the image was reconstructed by a part of the model (the generator). All datasets are obtained from an eight-channel MIT model by COMSOL Multiphysics software. The voltage measurement samples are used as input to the trained network, and its output is an estimate for image reconstruction of the internal conductivity distribution. The results based on the proposed model and the traditional algorithms were compared, which have shown that average root mean squared error of reconstruction results obtained by the proposed method is 0.090, and the average correlation coefficient with original images is 0.940, better than corresponding indicators of BPNN and Tikhonov regularization algorithms. Accordingly, the GAN algorithm was able to fit the non-linear relationship between input and output, and visual images also show that it solved the usual problems of artifact in traditional algorithm and hot pixels in L2 regularization, which is of great significance for other ill-posed or non-linear problems.

scholarly journals Data Augmentation Using Generative Adversarial Network for Automatic Machine Fault Detection Based on Vibration Signals

2021 ◽  
Vol 11 (5) ◽  
pp. 2166
Author(s):  
Van Bui ◽  
Tung Lam Pham ◽  
Huy Nguyen ◽  
Yeong Min Jang
Keyword(s):  
Fault Detection ◽  
Data Augmentation ◽  
Model Performance ◽  
Original Data ◽  
Fault Classification ◽  
Training Process ◽  
Generative Adversarial Network ◽  
Data Set ◽  
Adversarial Network ◽  
Machine Fault

In the last decade, predictive maintenance has attracted a lot of attention in industrial factories because of its wide use of the Internet of Things and artificial intelligence algorithms for data management. However, in the early phases where the abnormal and faulty machines rarely appeared in factories, there were limited sets of machine fault samples. With limited fault samples, it is difficult to perform a training process for fault classification due to the imbalance of input data. Therefore, data augmentation was required to increase the accuracy of the learning model. However, there were limited methods to generate and evaluate the data applied for data analysis. In this paper, we introduce a method of using the generative adversarial network as the fault signal augmentation method to enrich the dataset. The enhanced data set could increase the accuracy of the machine fault detection model in the training process. We also performed fault detection using a variety of preprocessing approaches and classified the models to evaluate the similarities between the generated data and authentic data. The generated fault data has high similarity with the original data and it significantly improves the accuracy of the model. The accuracy of fault machine detection reaches 99.41% with 20% original fault machine data set and 93.1% with 0% original fault machine data set (only use generate data only). Based on this, we concluded that the generated data could be used to mix with original data and improve the model performance.

AN AI-BASED APPROACH TO ENHANCED FRACTURE RESOLUTION IN IMAGE LOGS

2021 ◽  
Author(s):  
James Howard ◽  
◽  
Joe Tracey ◽  
Mike Shen ◽  
Shawn Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Nearest Neighbor ◽  
Rock Fracture ◽  
Short Interval ◽  
Acoustic Properties ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Deep Learning Neural Network ◽  
Borehole Image

Borehole image logs are used to identify the presence and orientation of fractures, both natural and induced, found in reservoir intervals. The contrast in electrical or acoustic properties of the rock matrix and fluid-filled fractures is sufficiently large enough that sub-resolution features can be detected by these image logging tools. The resolution of these image logs is based on the design and operation of the tools, and generally is in the millimeter per pixel range. Hence the quantitative measurement of actual width remains problematic. An artificial intelligence (AI) -based workflow combines the statistical information obtained from a Machine-Learning (ML) segmentation process with a multiple-layer neural network that defines a Deep Learning process that enhances fractures in a borehole image. These new images allow for a more robust analysis of fracture widths, especially those that are sub-resolution. The images from a BHTV log were first segmented into rock and fluid-filled fractures using a ML-segmentation tool that applied multiple image processing filters that captured information to describe patterns in fracture-rock distribution based on nearest-neighbor behavior. The robust ML analysis was trained by users to identify these two components over a short interval in the well, and then the regression model-based coefficients applied to the remaining log. Based on the training, each pixel was assigned a probability value between 1.0 (being a fracture) and 0.0 (pure rock), with most of the pixels assigned one of these two values. Intermediate probabilities represented pixels on the edge of rock-fracture interface or the presence of one or more sub-resolution fractures within the rock. The probability matrix produced a map or image of the distribution of probabilities that determined whether a given pixel in the image was a fracture or partially filled with a fracture. The Deep Learning neural network was based on a Conditional Generative Adversarial Network (cGAN) approach where the probability map was first encoded and combined with a noise vector that acted as a seed for diverse feature generation. This combination was used to generate new images that represented the BHTV response. The second layer of the neural network, the adversarial or discriminator portion, determined whether the generated images were representative of the actual BHTV by comparing the generated images with actual images from the log and producing an output probability of whether it was real or fake. This probability was then used to train the generator and discriminator models that were then applied to the entire log. Several scenarios were run with different probability maps. The enhanced BHTV images brought out fractures observed in the core photos that were less obvious in the original BTHV log through enhanced continuity and improved resolution on fracture widths.

scholarly journals Convolutional Neural Network Audio Classifier for Alarm Sound Detection

2019 ◽  
Vol 8 (6) ◽  
pp. 4554-4557
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Short Term Memory ◽  
Sound Recognition ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Differential Network ◽  
Sound Detection ◽  
Long Short Term Memory ◽  
Lstm Network

Neural Networks (ANN) has evolved through many stages in the last three decades with many researchers contributing in this challenging field. With the power of math complex problems can also be solved by ANNs. ANNs like Convolutional Neural Network (CNN), Deep Neural network, Generative Adversarial Network (GAN), Long Short Term Memory (LSTM) network, Recurrent Neural Network (RNN), Ordinary Differential Network etc., are playing promising roles in many MNCs and IT industries for their predictions and accuracy. In this paper, Convolutional Neural Network is used for prediction of Beep sounds in high noise levels. Based on Supervised Learning, the research is developed the best CNN architecture for Beep sound recognition in noisy situations. The proposed method gives better results with an accuracy of 96%. The prototype is tested with few architectures for the training and test data out of which a two layer CNN classifier predictions were the best.

Sign in / Sign up

Export Citation Format

Share Document