Advancing Digital Rock Imaging with Generative Adversarial Networks

Conditional Generative Adversarial Network (GAN) is a GAN that generates data with the desired condition from the latent vector. The auxiliary classifier GAN is the most used among the variations of conditional GANs. In this study, we explain the problem of auxiliary classifier GAN and propose conditional activation GAN that can replace auxiliary classifier GAN to reduce the number of hyperparameters and improve training speed. The loss function of conditional activation GAN is defined as the sum of the loss of each GAN created for each condition. Since each GAN shares all hidden layers, the GANs can be considered as a single GAN and it does not increase the amount of computation much. Also, in order to prevent ignorance of conditions in the discriminator of conditional GANs with batch normalization, we propose a mixed batch training, in which each batch for discriminator is always configured to have the same ratio of real data and generated data so that each batch always has the similar condition distribution

Load validity discrimination for telescopic boom of rock drilling jumbo

We propose a deep-learning approach based on generative adversarial networks (GANs) to reduce noise in weak lensing mass maps under realistic conditions. We apply image-to-image translation using conditional GANs to the mass map obtained from the first-year data of Subaru Hyper Suprime-Cam (HSC) Survey. We train the conditional GANs by using 25 000 mock HSC catalogues that directly incorporate a variety of observational effects. We study the non-Gaussian information in denoised maps using one-point probability distribution functions (PDFs) and also perform matching analysis for positive peaks and massive clusters. An ensemble learning technique with our GANs is successfully applied to reproduce the PDFs of the lensing convergence. About $60{{\ \rm per\ cent}}$ of the peaks in the denoised maps with height greater than 5σ have counterparts of massive clusters within a separation of 6 arcmin. We show that PDFs in the denoised maps are not compromised by details of multiplicative biases and photometric redshift distributions, nor by shape measurement errors, and that the PDFs show stronger cosmological dependence compared to the noisy counterpart. We apply our denoising method to a part of the first-year HSC data to show that the observed mass distribution is statistically consistent with the prediction from the standard ΛCDM model.

Generative adversarial network (GAN) has been extensively applied in many fields since it was first proposed in 2014. There have been ongoing attempts at improving the model and developing its extensions. The basic idea behind GAN stems from the two-player zero-sum game. Composed of a generator and a discriminator, GAN is trained through a “battle” between the two networks, where the generator tries to fool the discriminator. In contrast, the discriminator tries not to be deceived. The purpose is to estimate the potential distribution of data samples and generate new data samples. GAN is currently being studied in computer vision, language processing, and information security and is still far from reaching its potential. Since there are limited existing resources on GAN reviews, this paper provides a comprehensive review of a few of the most important GAN variants. We divided the variants into three categories: foundation, extension, and advanced, gave an overview of each architecture, and analyzed their advantages and disadvantages. We also summarized some of the most popular applications of GAN, and finally, we brought up the problems of GAN-based architectures that have yet to be solved and pointed out the future direction of GAN research and development.

Applications of generative adversarial networks in neuroimaging and clinical neuroscience

Mechanical fault diagnosis is crucial for ensuring the normal operation of mechanical equipment. With the rapid development of deep learning technology, the methods based on big data-driven provide a new perspective for the fault diagnosis of machinery. However, mechanical equipment operates in the normal condition most of the time, resulting in the collected data being imbalanced, which affects the performance of mechanical fault diagnosis. As a new approach for generating data, generative adversarial network (GAN) can effectively address the issues of limited data and imbalanced data in practical engineering applications. This paper provides a comprehensive review of GAN for mechanical fault diagnosis. Firstly, the development of GAN-based mechanical fault diagnosis, the basic theory of GAN and various GAN variants (GANs) are briefly introduced. Subsequently, GANs are summarized and categorized from the perspective of labels and models, and the corresponding applications are outlined. Lastly, the limitations of current research, future challenges, future trends and selecting the GAN in the practical application are discussed.

As a promising generative modeling method, Generative Adversarial Networks are a deep-learning-based generative model, in which two networks, namely the generative network and the discriminant network, contest with each other in a game during which the generator “learns” and get trained to be able to fool the discriminator of believing a specific image is (superficially) authentic. It is widely used to generate pictures based on existing data. Based on the MNIST data set, this paper studies and analyzes the application of Generative Adversarial Networks in the generation of handwritten digital images. In addition, by studying the Deep Convolutional Generative Adversarial Network and the Conditional Generation Adversarial Network model, we compared the connections and differences between these three models in training the MNIST dataset to generate handwritten digits algorithms, and gave an optimization method for generating handwritten digits.

Adopting an accurate anomaly detection mechanism is crucial for industrial software systems in order to prevent system outages that can deteriorate system availability. However, employing a supervised machine learning technique to detect anomalies in large production scale industrial software systems is highly impractical due to the requirement of annotated data. This raises the need for comprehensive semi-supervised and unsupervised anomaly detection mechanisms. This paper presents the application of Generative Adversarial Network (GAN) based models to detect system anomalies using semi-supervised one-class learning. We show that the use of a variant of GAN known as bidirectional GAN (BiGAN) gives augmented results when compared to the traditional GAN based anomaly detection, for the selected industrial system. Moreover, the experiments clearly show that the performance of the BiGAN has a direct correlation with the dimensions of the dataset used for training. The BiGAN even tends to outperform the well-established semi-supervised One-class SVM classifier and a prominent generative network for semi-supervised anomaly detection, Variational Autoencoders (VAEs) when the size of the feature space increases.

ABSTRACTData mining and natural language processing (NLP) are fundamental fields that interact in many ways. Text mining shares many topics, such as sentiment analysis and content understanding. Combining these two fields enables more efficient mining of text data and the extraction of valuable information. In particular, the GAN (Generative Adversarial Network) architecture has achieved success in image generation and has started to be used on text data. However, training GANs is fraught with difficulties due to the complexity of text data. Linguistic studies show important differences between languages. Language is characterized by fluidity, ambiguity, and context‐sensitive interpretations, and text‐generating GAN models can struggle to deal with these complexities. The interaction between data quality, language structure, and complex interpretation can lead to inconsistency and ambiguity in the text production of GAN models. These problems are particularly pronounced when complexities such as semantic subtleties, idiomatic expressions, and context‐dependent usages come into play. Text generation is an area of GAN models used in NLP to generate language and enrich text‐based applications. Work in this area can contribute to analyzing, classifying, and processing text data. Many methods and techniques have been proposed to improve the performance of text GANs. However, some problems may be encountered in the optimization of these methods. Therefore, it is essential to use optimized methods. In conclusion, GANs can be an important tool to improve text generation in NLP. Still, they require continuous research and innovation to deal with factors such as language complexity and data quality.

Due to the real working conditions, the collected mechanical fault datasets are actually limited and always highly imbalanced, which restricts the diagnosis accuracy and stability. To solve these problems, we present an imbalanced fault diagnosis method based on the generative model of conditional-deep convolutional generative adversarial network (C-DCGAN) and provide a study in detail. Deep convolutional generative adversarial network (DCGAN), based on traditional generative adversarial networks (GAN), introduces convolutional neural network into the training for unsupervised learning to improve the effect of generative networks. Conditional generative adversarial network (CGAN) is a conditional model obtained through introducing conditional extension into GAN. C-DCGAN is a combination of DCGAN and CGAN. In C-DCGAN, based on the feature extraction ability of convolutional networks, through the structural optimization, conditional auxiliary generative samples are used as augmented data and applied in machine fault diagnosis. Two datasets (Bearing dataset and Planetary gear box dataset) are carried out to validate. The simulation experiments showed that the improved performance is mainly due to the generated signals from C-DCGAN to balance the dataset. The proposed method can deal with imbalanced fault classification problem much more effectively. This model could improve the accuracy of fault diagnosis and the generalization ability of the classifier in the case of small samples and display better fault diagnosis performance.

A conditional variational autoencoding generative adversarial networks with self-modulation for rolling bearing fault diagnosis

Due to the high acoustic variability, children speech recognition suffers significant performance reduction on most ASR systems which are optimized mainly using adults speech with limited or even none children speech. One of the most straight ideas to solve this problem is to increase the children's speech data during training, however, it is restricted by the more difficult process and higher cost when collecting children's speech compared to adults'. In this work, we develop a generative adversarial network (GANs) based data augmentation method to increase the size of children's training data to improve speech recognition performance for children's speech. Two different types of GANs are explored under WGAN-GP training framework, including the unconditional GANs with an unsupervised learning framework and the conditional GANs using acoustic states as conditions. The proposed data augmentation approaches are evaluated on a Mandarin speech recognition task, with only 40-hour children speech or further including 100-hour adult speech in the training. The results show that more than relative 20% WER reduction can be obtained on children speech testset with the proposed method, and the generated children speech with GAN even can improve the adults' speech within our experimental setups.

Over the last few decades, generative adversarial network (GAN) methods have been increasingly applied and improved in fashion-related scenes, especially during the pandemic. This article provides an overview of several mainstream GAN models for fashion recommendation and fashion transformation, including compatibility matrix-regularized GAN, Outfit GAN, transformer-based GAN, conditional analogy GAN, disentangled cycle-consistency try-on network, and flow-navigated warping GAN. Within each GAN method, the improvements made to perform more related and deliciated are presented with detailed loss functions, the specific evaluation matrixes, and the examinations of generators or discriminators. Moreover, possible directions of improvements for future research and problems with existing models are involved. As for the common restrictions of included methods, including the problem of incomprehensive and non-diverse datasets, the standard evaluation of modish aesthetic value, and the number of fashion items involved in one outfit, are analyzed within fashion outfit recommendation and fashion transformation. Therefore, such restrictions provide possible directions for future analysis in fashion-related networks.

Bangla handwritten character recognition is known to be one of the most classical problem in the field of machine learning. In order to solve a machine learning problem one must thing is dataset. The more varied data a model sees the better it learns. Generative adversarial networks (GANs) are a group of neural networks that are used in unsupervised machine learning. It helps to resolve many difficult operations such as image generation from description, transforming low resolution image into high resolution, retrieving image contents given a small pattern etc. GAN's have many other promising applications in machine learning. There are many variations available for GAN. One of the variation of GAN is Conditional Generative Adversarial Networks(cGAN). This kind of GAN is used for generating a specific type of image. In this work we have used cGAN for generating Class Based Character Generation. This work can help researchers to generate handwritten characters to enhance the perfomance of deep learning models. We have trained this model to generate 50 Basic Bangla Characters, 10 Bangla Numerals and 24 Compound characters.

High-entropy alloys (HEAs) have emerged as promising candidates for solid-state hydrogen storage, yet the vast compositional space poses a major challenge for targeted materials discovery. Here, we develop a deep generative framework based on generative adversarial networks (GANs) and conditional GANs (CGANs) to enable the inverse design of HEAs with optimized hydride formation enthalpy and hydrogen storage capacity. The GAN accurately captures the underlying compositional distributions, achieving high novelty and diversity while reproducing known chemical trends and empirical phase-formation rules. By incorporating property labels as conditional inputs, the CGAN allows directional control over the generation process, steering the model toward alloys with targeted enthalpy and capacity ranges. Density functional theory (DFT) calculations are performed to validate a representative GAN-generated composition, Mn18V2Fe16Ti18, confirming its structural stability and hydrogen uptake, in good agreement with machine-learning predictions. These results demonstrate that GAN model can autonomously learn distribution characteristics of data set and efficiently explore unexplored regions of the HEAs design space, providing a powerful strategy for the inverse design of advanced hydrogen storage materials.